To see the other types of publications on this topic, follow the link: Superior Predictive Ability test.
Journal articles on the topic 'Superior Predictive Ability test'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Superior Predictive Ability test.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Hansen, Peter Reinhard. "A Test for Superior Predictive Ability." Journal of Business & Economic Statistics 23, no. 4 (October 2005): 365–80. http://dx.doi.org/10.1198/073500105000000063.
Full text
2
Cai, Zongwu, Jiancheng Jiang, Jingshuang Zhang, and Xibin Zhang. "A new semiparametric test for superior predictive ability." Empirical Economics 48, no. 1 (December 3, 2014): 389–405. http://dx.doi.org/10.1007/s00181-014-0887-6.
Full text
3
Cenciarelli, Velia Gabriella, Giulio Greco, and Marco Allegrini. "Does intellectual capital help predict bankruptcy?" Journal of Intellectual Capital 19, no. 2 (March 12, 2018): 321–37. http://dx.doi.org/10.1108/jic-03-2017-0047.
Full textAbstract:
Purpose The purpose of this paper is to explore whether intellectual capital affects the probability that a particular firm will default. The authors also test whether including intellectual capital performance in bankruptcy prediction models improves their predictive ability. Design/methodology/approach Using a sample of US public companies from the period stretching from 1985 to 2015, the authors test whether intellectual capital performance reduces the probability of bankruptcy. The authors use the VAIC as an aggregate measure of corporate intellectual capital performance. Findings The findings show that the intellectual capital performance is negatively associated with the probability of default. The findings also indicate that the bankruptcy prediction models that include intellectual capital have a superior predictive ability over the standard models. Research limitations/implications This paper contributes to prior research on intellectual capital and firm performance. To the best of the knowledge, this is the first study to show that the benefits of intellectual capital extend from superior performance to long-term financial stability. The research can also contribute to bankruptcy studies. By using a time frame covering decades, the findings suggest that intellectual capital performance measures can be included in bankruptcy prediction models and can effectively complement traditional performance measures. Originality/value This paper highlights that intellectual capital is associated with long-term financial stability and a lower bankruptcy risk. Firms realising the potential of their intellectual capital can produce a virtuous circle between higher performance and greater financial stability.
4
Lv, Yang, Ning Pu, Wei-lin Mao, Wen-qi Chen, Huan-yu Wang, Xu Han, Yuan Ji, et al. "Development of predictive prognostic nomogram for NECs of rectum on population-based exploration." Endocrine Connections 7, no. 11 (November 2018): 1178–85. http://dx.doi.org/10.1530/ec-18-0353.
Full textAbstract:
Aim We aim to investigate the clinical characteristics of the rectal NECs and the prognosis-related factors and construct a nomogram for prognosis prediction. Methods The data of 41 patients and 1028 patients with rectal NEC were retrieved respectively from our institution and SEER database. OS or PFS was defined as the major study outcome. Variables were compared by chi-square test and t-test when appropriate. Kaplan–Meier analysis with log-rank test was used for survival analysis and the Cox regression analysis was applied. The nomogram integrating risk factors for predicting OS was constructed by R to achieve superior discriminatory ability. Predictive utility of the nomogram was determined by concordance index (C-index) and calibration curve. Results In the univariate and multivariate analyses, tumor differentiation, N stage, M stage and resection of primary site were identified as independent prognostic indicators. The linear regression relationship was found between the value of Ki-67 index and the duration of OS (P < 0.05). Furthermore, the independent prognostic factors were added to formulate prognostic nomogram. The constructed nomogram showed good performance according to the C-index. Conclusions Contrary to WHO classification guideline, we found that the rectal NEC diseases are heterogeneous and should be divided as different categories according to the pathological differentiation. Besides, the nomogram formulated in this study showed excellent discriminative capability to predict OS for those patients. More advanced predictive model for this disease is required to assist risk stratification via the formulated nomogram.
5
Jiang, Brian Gabriel, Dong-Wook Kim, Lee-Yung Shih, Charles Chuah, Hein Than, Ming-Chung Kuo, HuiHua Li, et al. "Sokal Risk Score Is Superior to Hasford and EUTOS in Determining Survival Outcomes for Newly Diagnosed Chronic Phase Chronic Myeloid Leukemia Patients." Blood 126, no. 23 (December 3, 2015): 4044. http://dx.doi.org/10.1182/blood.v126.23.4044.4044.
Full textAbstract:
Abstract Despite being developed in eras when standard treatments for Chronic Phase Chronic Myeloid Leukemia (CP-CML) differ, Sokal, Hasford, and European Treatment and Outcome Study (EUTOS) scores each remain in use for predicting survival outcomes. The European LeukemiaNet (ELN) 2013 guidelines state that no one score is superior to the other. Furthermore, no studies have examined how a combination of scores may improve prognostic value. This retrospective, multicenter study compared the scores, individually and in combination, on predicting Overall Survival (OS), Progression-Free Survival (PFS) and Event-Free Survival (EFS) for CP-CML patients in Singapore General Hospital (Singapore), Seoul St. Mary's Hospital (South Korea) and Chang Gung Memorial Hospital (Taiwan). A total of 1222 newly diagnosed CP-CML patients (2013 ELN criteria) between July 1998 to December 2013 with follow-up period ≥18 months were reviewed. OS was defined as death from any cause, PFS was defined as transformation to accelerated or blastic phase and CML-related death. EFS was defined as failure according to the 2009 ELN criteria, treatment changes, progression, and death. Log likelihood ratio (LR) test of nested models was performed to compare dual combination scores with its individual components. Adequacy index was used to quantify the percentage of variation explained by each pair of scores. Harrell's c-index was also calculated to evaluate the predictive ability of the scores. Linear contrast test was used to further stratify the individual risk groups in dual combination scores. For OS, comparison of Sokal + EUTOS vs. EUTOS (LR 40.44 vs. 0.49) or Sokal + Hasford vs. Hasford (LR 31.78 vs. 11.81) showed that the combined model was significantly better than the individual models alone (p-value<0.01 for both). However, comparison of Sokal + EUTOS vs. Sokal or Sokal + Hasford vs. Sokal was not significantly better. Comparison of Hasford + EUTOS vs. EUTOS was significantly better (LR 21.37 vs. 0.92, p-value<0.01). Thus, for OS, the predictive ability order of the models are Sokal>Hasford>EUTOS, which are supported by Harrell's c-indices of 0.665, 0.591, 0.514, respectively. Similar predictive ability order for individual scores were also drawn for EFS (refer to table 1). For PFS, comparison of Sokal + Hasford vs. Hasford showed the combined model was significantly better (LR 34.05 vs. 12.32, p-value<0.01). However comparison of Sokal + Hasford vs. Sokal was not significantly better, indicating the predictive ability of Sokal>Hasford, which is in agreement with the c-indices (0.620 vs. 0.569, respectively). Comparison of Sokal + EUTOS to either Sokal or EUTOS alone was both significantly better (LR 42.50 vs. 35.76, LR 42.50 vs. 20.33, respectively; p-value<0.01 for both). This is supported by similar c-indices for Sokal and EUTOS individually (0.620 and 0.621, respectively). However, in the combination of Sokal + EUTOS, Sokal explained 84.1% of the variation while EUTOS explained 47.8%. Thus, for PFS, the predictive ability of Sokal is superior to EUTOS or Hasford. When analyzing dual combination scores, Sokal + EUTOS combined had the highest c-indices for OS, PFS and EFS (0.758, 0.705, 0.621) compared to EUTOS + Hasford and Sokal + Hasford. Linear contrast to rank Sokal + EUTOS in combination produced various valid paired orders, of which the order of SokalLow EUTOSLow, SokalIntermediate EUTOSLow, SokalIntermediate EUTOSHigh, SokalHigh EUTOSLow, SokalHigh EUTOSHighhad a hazard ratio of 4.47, 4.08, 2.26 for OS, PFS and EFS respectively (p-value<0.01 for all). Contrary to the ELN 2013 guidelines that no single score is superior, our data shows that Sokal is superior in predicting OS, PFS and EFS in CP-CML. Dual score combinations are capable of improving prognostic ability, with Sokal + EUTOS in combination being the best to predict survival outcomes. Table 1. Log likelihood ratios of dual combination scores versus individual scores. Survival Outcome Log Likelihood ratio (p-value) EUTOS + SOKAL EUTOS SOKAL OS 40.44 0.49 (<0.01) 38.66 (0.18) PFS 42.50 20.33 (<0.01) 35.76 (<0.01) EFS 74.66 11.32 (<0.01) 73.49 (0.28) SOKAL + HASFORD SOKAL HASFORD OS 31.78 31.31 (0.79) 11.81 (<0.01) PFS 34.05 33.08 (0.61) 12.32 (<0.01) EFS 57.94 55.85 (0.35) 32.24 (<0.01) EUTOS + HASFORD EUTOS HASFORD OS 21.37 0.92 (<0.01) 20.87 (0.48) PFS 32.07 23.65 (<0.01) 20.22 (<0.01) EFS 46.35 12.34 (<0.01) 44.17 (0.14) Disclosures Shih: Novartis: Research Funding. Chuah:Novartis: Honoraria; Children International: Honoraria; Bristol Meyers Squibb: Honoraria. Goh:Roche: Honoraria; Janssen: Honoraria, Research Funding; Gilead Sciences: Honoraria; Sanofi: Honoraria; Novartis: Honoraria, Research Funding; Bristol-Myers Squibb: Honoraria; Celgene: Honoraria.
6
BENEDICT, K. M., S. P. GOW, R. J. REID-SMITH, C. W. BOOKER, T. A. McALLISTER, and P. S. MORLEY. "Latent class comparison of test accuracy when evaluating antimicrobial susceptibility using disk diffusion and broth microdilution to testEscherichia coliandMannheimia haemolyticaisolates recovered from beef feedlot cattle." Epidemiology and Infection 142, no. 11 (January 24, 2014): 2314–25. http://dx.doi.org/10.1017/s0950268813003300.
Full textAbstract:
SUMMARYThe study objective was to use Bayesian latent class analysis to evaluate the accuracy of susceptibility test results obtained from disk diffusion and broth microdilution using bacteria recovered from beef feedlot cattle. Isolates ofEscherichia coliandMannheimia haemolyticawere tested for susceptibility to ampicillin, ceftiofur, streptomycin, sulfisoxazole, tetracycline, and trimethoprim-sulfamethoxazole. Results showed that neither testing method was always or even generally superior to the other. Specificity (ability to correctly classify non-resistant isolates) was extremely high for both testing methods, but sensitivity (ability to correctly classify resistant isolates) was lower, variable in the drugs evaluated, and variable between the two bacterial species. Predictive values estimated using Bayesian Markov chain Monte Carlo models showed that the ability to predict true susceptibility status was equivalent for test results obtained with the two testing methods for some drugs, but for others there were marked differences between results obtained from disk diffusion and broth microdilution tests.
7
Altarazi, Safwan, Rula Allaf, and Firas Alhindawi. "Machine Learning Models for Predicting and Classifying the Tensile Strength of Polymeric Films Fabricated via Different Production Processes." Materials 12, no. 9 (May 7, 2019): 1475. http://dx.doi.org/10.3390/ma12091475.
Full textAbstract:
In this study, machine learning algorithms (MLA) were employed to predict and classify the tensile strength of polymeric films of different compositions as a function of processing conditions. Two film production techniques were investigated, namely compression molding and extrusion-blow molding. Multi-factor experiments were designed with corresponding parameters. A tensile test was conducted on samples and the tensile strength was recorded. Predictive and classification models from nine MLA were developed. Performance analysis demonstrated the superior predictive ability of the support vector machine (SVM) algorithm, in which a coefficient of determination and mean absolute percentage error of 96% and 4%, respectively were obtained for the extrusion-blow molded films. The classification performance of the MLA was also evaluated, with several algorithms exhibiting excellent performance.
8
Senders, Joeky T., Patrick Staples, Alireza Mehrtash, David J. Cote, Martin J. B. Taphoorn, David A. Reardon, William B. Gormley, Timothy R. Smith, Marike L. Broekman, and Omar Arnaout. "An Online Calculator for the Prediction of Survival in Glioblastoma Patients Using Classical Statistics and Machine Learning." Neurosurgery 86, no. 2 (October 5, 2019): E184—E192. http://dx.doi.org/10.1093/neuros/nyz403.
Full textAbstract:
Abstract BACKGROUND Although survival statistics in patients with glioblastoma multiforme (GBM) are well-defined at the group level, predicting individual patient survival remains challenging because of significant variation within strata. OBJECTIVE To compare statistical and machine learning algorithms in their ability to predict survival in GBM patients and deploy the best performing model as an online survival calculator. METHODS Patients undergoing an operation for a histopathologically confirmed GBM were extracted from the Surveillance Epidemiology and End Results (SEER) database (2005-2015) and split into a training and hold-out test set in an 80/20 ratio. Fifteen statistical and machine learning algorithms were trained based on 13 demographic, socioeconomic, clinical, and radiographic features to predict overall survival, 1-yr survival status, and compute personalized survival curves. RESULTS In total, 20 821 patients met our inclusion criteria. The accelerated failure time model demonstrated superior performance in terms of discrimination (concordance index = 0.70), calibration, interpretability, predictive applicability, and computational efficiency compared to Cox proportional hazards regression and other machine learning algorithms. This model was deployed through a free, publicly available software interface (https://cnoc-bwh.shinyapps.io/gbmsurvivalpredictor/). CONCLUSION The development and deployment of survival prediction tools require a multimodal assessment rather than a single metric comparison. This study provides a framework for the development of prediction tools in cancer patients, as well as an online survival calculator for patients with GBM. Future efforts should improve the interpretability, predictive applicability, and computational efficiency of existing machine learning algorithms, increase the granularity of population-based registries, and externally validate the proposed prediction tool.
9
Goulden, Robert, Marie-Claire Hoyle, Jessie Monis, Darran Railton, Victoria Riley, Paul Martin, Reynaldo Martina, and Emmanuel Nsutebu. "qSOFA, SIRS and NEWS for predicting inhospital mortality and ICU admission in emergency admissions treated as sepsis." Emergency Medicine Journal 35, no. 6 (February 21, 2018): 345–49. http://dx.doi.org/10.1136/emermed-2017-207120.
Full textAbstract:
BackgroundThe third international consensus definition for sepsis recommended use of a new prognostic tool, the quick Sequential Organ Failure Assessment (qSOFA), based on its ability to predict inhospital mortality and prolonged intensive care unit (ICU) stay in patients with suspected infection. While several studies have compared the prognostic accuracy of qSOFA to the Systemic Inflammatory Response Syndrome (SIRS) criteria in suspected sepsis, few have compared qSOFA and SIRS to the widely used National Early Warning Score (NEWS).MethodsThis was a retrospective cohort study carried out in a UK tertiary centre. The study population comprised emergency admissions in whom sepsis was suspected and treated. The accuracy for predicting inhospital mortality and ICU admission was calculated and compared for qSOFA, SIRS and NEWS.ResultsAmong 1818 patients, 53 were admitted to ICU (3%) and 265 died in hospital (15%). For predicting inhospital mortality, the area under the receiver operating characteristics curve for NEWS (0.65, 95% CI 0.61 to 0.68) was similar to qSOFA (0.62, 95% CI 0.59 to 0.66) (test for difference, P=0.18) and superior to SIRS (P<0.001), which was not predictive. The sensitivity of NEWS≥5 (74%, 95% CI 68% to 79%) was similar to SIRS≥2 (80%, 95% CI 74% to 84%) and higher than qSOFA≥2 (37%, 95% CI 31% to 43%). The specificity of NEWS≥5 (43%, 95% CI 41% to 46%) was higher than SIRS≥2 (21%, 95% CI 19% to 23%) and lower than qSOFA≥2 (79%, 95% CI 77% to 81%). The negative predictive value was 88% (86%–90%) for qSOFA, 86% (82%–89%) for SIRS and 91% (88%–93%) for NEWS. Results were similar for the secondary outcome of ICU admission.ConclusionNEWS has equivalent or superior value for most test characteristics relative to SIRS and qSOFA, calling into question the rationale of adopting qSOFA in institutions where NEWS is already in use.
10
van Niftrik, Christiaan H. B., Frank van der Wouden, Victor E. Staartjes, Jorn Fierstra, Martin N. Stienen, Kevin Akeret, Martina Sebök, et al. "Machine Learning Algorithm Identifies Patients at High Risk for Early Complications After Intracranial Tumor Surgery: Registry-Based Cohort Study." Neurosurgery 85, no. 4 (May 31, 2019): E756—E764. http://dx.doi.org/10.1093/neuros/nyz145.
Full textAbstract:
Abstract INTRODUCTION Reliable preoperative identification of patients at high risk for early postoperative complications occurring within 24 h (EPC) of intracranial tumor surgery can improve patient safety and postoperative management. Statistical analysis using machine learning algorithms may generate models that predict EPC better than conventional statistical methods. OBJECTIVE To train such a model and to assess its predictive ability. METHODS This cohort study included patients from an ongoing prospective patient registry at a single tertiary care center with an intracranial tumor that underwent elective neurosurgery between June 2015 and May 2017. EPC were categorized based on the Clavien-Dindo classification score. Conventional statistical methods and different machine learning algorithms were used to predict EPC using preoperatively available patient, clinical, and surgery-related variables. The performance of each model was derived from examining classification performance metrics on an out-of-sample test dataset. RESULTS EPC occurred in 174 (26%) of 668 patients included in the analysis. Gradient boosting machine learning algorithms provided the model best predicting the probability of an EPC. The model scored an accuracy of 0.70 (confidence interval [CI] 0.59-0.79) with an area under the curve (AUC) of 0.73 and a sensitivity and specificity of 0.80 (CI 0.58-0.91) and 0.67 (CI 0.53-0.77) on the test set. The conventional statistical model showed inferior predictive power (test set: accuracy: 0.59 (CI 0.47-0.71); AUC: 0.64; sensitivity: 0.76 (CI 0.64-0.85); specificity: 0.53 (CI 0.41-0.64)). CONCLUSION Using gradient boosting machine learning algorithms, it was possible to create a prediction model superior to conventional statistical methods. While conventional statistical methods favor patients’ characteristics, we found the pathology and surgery-related (histology, anatomical localization, surgical access) variables to be better predictors of EPC.
11
Brion, G. M., and S. Lingireddy. "Artificial neural network modelling: a summary of successful applications relative to microbial water quality." Water Science and Technology 47, no. 3 (February 1, 2003): 235–40. http://dx.doi.org/10.2166/wst.2003.0201.
Full textAbstract:
Artificial neural networks (ANN) are modelling tools that can be of great utility in studies of microbial water quality. The ability of ANNs to work with complex, inter-related multiparameter databases and provide superior predictive power in non-linear relationships suits their application to microbial water quality studies. To date ANNs have been successfully applied (a) for the prediction of peak microbial concentrations, (b) to sort land use associated faecal pollution sources and relative ages of runoff and (c) towards the selection and study of surrogate parameters. Predictions of peak microbial contamination or faecal pollution sources have been greater than 90% accurate. The importance of a subgroup of organisms that are isolated by the total coliform membrane filter test on m-Endo media in defining faecal sources was revealed through parameter selection exercises. The result is the definition of a new bacterial ratio that can be directly related to the age of faecal contamination in animal impacted runoff.
12
Watson, Jessica, Hayley E. Jones, Jonathan Banks, Penny Whiting, Chris Salisbury, and Willie Hamilton. "Use of multiple inflammatory marker tests in primary care: using Clinical Practice Research Datalink to evaluate accuracy." British Journal of General Practice 69, no. 684 (June 17, 2019): e462-e469. http://dx.doi.org/10.3399/bjgp19x704309.
Full textAbstract:
BackgroundResearch comparing C-reactive protein (CRP), erythrocyte sedimentation rate (ESR), and plasma viscosity (PV) in primary care is lacking. Clinicians often test multiple inflammatory markers, leading to concerns about overuse.AimTo compare the diagnostic accuracies of CRP, ESR, and PV, and to evaluate whether measuring two inflammatory markers increases accuracy.Design and settingProspective cohort study in UK primary care using the Clinical Practice Research Datalink.MethodThe authors compared diagnostic test performance of inflammatory markers, singly and paired, for relevant disease, defined as any infections, autoimmune conditions, or cancers. For each of the three tests (CRP, ESR, and PV), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under receiver operator curve (AUC) were calculated.ResultsParticipants comprised 136 961 patients with inflammatory marker testing in 2014; 83 761 (61.2%) had a single inflammatory marker at the index date, and 53 200 (38.8%) had multiple inflammatory markers. For ‘any relevant disease’, small differences were seen between the three tests; AUC ranged from 0.659 to 0.682. CRP had the highest overall AUC, largely because of marginally superior performance in infection (AUC CRP 0.617, versus ESR 0.589, P<0.001). Adding a second test gave limited improvement in the AUC for relevant disease (CRP 0.682, versus CRP plus ESR 0.688, P<0.001); this is of debatable clinical significance. The NPV for any single inflammatory marker was 94% compared with 94.1% for multiple negative tests.ConclusionTesting multiple inflammatory markers simultaneously does not increase ability to rule out disease and should generally be avoided. CRP has marginally superior diagnostic accuracy for infections, and is equivalent for autoimmune conditions and cancers, so should generally be the first-line test.
13
Anirudh, Rushil, Jayaraman J. Thiagarajan, Peer-Timo Bremer, and Brian K. Spears. "Improved surrogates in inertial confinement fusion with manifold and cycle consistencies." Proceedings of the National Academy of Sciences 117, no. 18 (April 20, 2020): 9741–46. http://dx.doi.org/10.1073/pnas.1916634117.
Full textAbstract:
Neural networks have become the method of choice in surrogate modeling because of their ability to characterize arbitrary, high-dimensional functions in a data-driven fashion. This paper advocates for the training of surrogates that are 1) consistent with the physical manifold, resulting in physically meaningful predictions, and 2) cyclically consistent with a jointly trained inverse model; i.e., backmapping predictions through the inverse results in the original input parameters. We find that these two consistencies lead to surrogates that are superior in terms of predictive performance, are more resilient to sampling artifacts, and tend to be more data efficient. Using inertial confinement fusion (ICF) as a test-bed problem, we model a one-dimensional semianalytic numerical simulator and demonstrate the effectiveness of our approach.
14
McBeath, T. M., M. J. McLaughlin, R. D. Armstrong, M. Bell, M. D. A. Bolland, M. K. Conyers, R. E. Holloway, and S. D. Mason. "Predicting the response of wheat (Triticum aestivum L.) to liquid and granular phosphorus fertilisers in Australian soils." Soil Research 45, no. 6 (2007): 448. http://dx.doi.org/10.1071/sr07044.
Full textAbstract:
Liquid forms of phosphorus (P) have been shown to be more effective than granular P for promoting cereal growth in alkaline soils with high levels of free calcium carbonate on Eyre Peninsula, South Australia. However, the advantage of liquid over granular P forms of fertiliser has not been fully investigated across the wide range of soils used for grain production in Australia. A glasshouse pot experiment tested if liquid P fertilisers were more effective for growing spring wheat (Triticum aestivum L.) than granular P (monoammonium phosphate) in 28 soils from all over Australia with soil pH (H2O) ranging from 5.2 to 8.9. Application of liquid P resulted in greater shoot biomass, as measured after 4 weeks’ growth (mid to late tillering, Feeks growth stage 2–3), than granular P in 3 of the acidic to neutral soils and in 3 alkaline soils. Shoot dry matter responses of spring wheat to applied liquid or granular P were related to soil properties to determine if any of the properties predicted superior yield responses to liquid P. The calcium carbonate content of soil was the only soil property that significantly contributed to predicting when liquid P was more effective than granular P. Five soil P test procedures (Bray, Colwell, resin, isotopically exchangeable P, and diffusive gradients in thin films (DGT)) were assessed to determine their ability to measure soil test P on subsamples of soil collected before the experiment started. These soil test values were then related to the dry matter shoot yields to assess their ability to predict wheat yield responses to P applied as liquid or granular P. All 5 soil test procedures provided a reasonable prediction of dry matter responses to applied P as either liquid or granular P, with the resin P test having a slightly greater predictive capacity on the range of soils tested. The findings of this investigation suggest that liquid P fertilisers do have some potential applications in non-calcareous soils and confirm current recommendations for use of liquid P fertiliser to grow cereal crops in highly calcareous soils. Soil P testing procedures require local calibration for response to the P source that is going to be used to amend P deficiency.
15
Woźnicki, Piotr, Niklas Westhoff, Thomas Huber, Philipp Riffel, Matthias F. Froelich, Eva Gresser, Jost von Hardenberg, et al. "Multiparametric MRI for Prostate Cancer Characterization: Combined Use of Radiomics Model with PI-RADS and Clinical Parameters." Cancers 12, no. 7 (July 2, 2020): 1767. http://dx.doi.org/10.3390/cancers12071767.
Full textAbstract:
Radiomics is an emerging field of image analysis with potential applications in patient risk stratification. This study developed and evaluated machine learning models using quantitative radiomic features extracted from multiparametric magnetic resonance imaging (mpMRI) to detect and classify prostate cancer (PCa). In total, 191 patients that underwent prostatic mpMRI and combined targeted and systematic fusion biopsy were retrospectively included. Segmentations of the whole prostate glands and index lesions were performed manually in apparent diffusion coefficient (ADC) maps and T2-weighted MRI. Radiomic features were extracted from regions corresponding to the whole prostate gland and index lesion. The best performing combination of feature setup and classifier was selected to compare its predictive ability of the radiologist’s evaluation (PI-RADS), mean ADC, prostate specific antigen density (PSAD) and digital rectal examination (DRE) using receiver operating characteristic (ROC) analysis. Models were evaluated using repeated 5-fold cross-validation and a separate independent test cohort. In the test cohort, an ensemble model combining a radiomics model, with models for PI-RADS, PSAD and DRE achieved high predictive AUCs for the differentiation of (i) malignant from benign prostatic lesions (AUC = 0.889) and of (ii) clinically significant (csPCa) from clinically insignificant PCa (cisPCa) (AUC = 0.844). Our combined model was numerically superior to PI-RADS for cancer detection (AUC = 0.779; p = 0.054) as well as for clinical significance prediction (AUC = 0.688; p = 0.209) and showed a significantly better performance compared to mADC for csPCa prediction (AUC = 0.571; p = 0.022). In our study, radiomics accurately characterizes prostatic index lesions and shows performance comparable to radiologists for PCa characterization. Quantitative image data represent a potential biomarker, which, when combined with PI-RADS, PSAD and DRE, predicts csPCa more accurately than mADC. Prognostic machine learning models could assist in csPCa detection and patient selection for MRI-guided biopsy.
16
Almeida, Juliano Ribeiro de, Guilherme Ribeiro de Almeida, and Daniel Reed Bergmann. "O Efeito Halloween no Mercado Acionário Brasileiro." Brazilian Review of Finance 14, no. 4 (July 15, 2017): 597. http://dx.doi.org/10.12660/rbfin.v14n4.2016.49582.
Full textAbstract:
The Halloween effect relates to the notion that stock market returns tend to be higher in the period from November to April than from May to October. In this study, we analyze the robustness of this trading strategy taking into account the individual returns of stocks traded in the Brazilian stock market during the period from August 1994 to June 2014. Using standard dummy regression approach introduced by Bouman and Jacobsen (2002), our results suggest the existence of the Halloween effect in the Brazilian market, which has shown to be economically and statistically significant, with a positive sign and a slight drop trend over the past few years. In addition, when reassessing these results using the "Superior Predictive Ability Test" of Hansen (2005), we have found that an investment strategy based on the Halloween effect generates a statistically significant returns superior to a buy-and-hold strategy when the effects of data-snooping when data-snooping effects are not neglected in the stock returns series, as in Bouman and Jacobsen (2002).
17
Lamarre, Patrice, Denis Lebel, and Murray P. Ducharme. "A Population Pharmacokinetic Model for Vancomycin in Pediatric Patients and Its Predictive Value in a Naive Population." Antimicrobial Agents and Chemotherapy 44, no. 2 (February 1, 2000): 278–82. http://dx.doi.org/10.1128/aac.44.2.278-282.2000.
Full textAbstract:
ABSTRACT The objectives of this study were to (i) construct a population pharmacokinetic (PK) model able to describe vancomycin (VAN) concentrations in serum in pediatric patients, (ii) determine VAN PK parameters in this population, and (iii) validate the predictive ability of this model in a naive pediatric population. Data used in this study were obtained from 78 pediatric patients (under 18 years old). PK analyses were performed using compartmental methods. The most appropriate model was chosen based on the evaluation of pertinent graphics and calculation of the Akaike information criterion test. The population PK analysis was performed using an iterative two-stage method. A two-compartment PK model using age, sex, weight, and serum creatinine as covariates was determined to be the most appropriate one to describe serum VAN concentrations. The quality of fit was very good, and the distribution of weighted residuals was found to be homoscedastic (Wilcoxon signed rank test). Fitted population PK parameters (mean ± standard deviation) were as follows: central clearance (0.1 ± 0.05 liter/h/kg), central volume of distribution (0.27 ± 0.07 liter/kg), peripheral volume of distribution (0.16 ± 0.07 liter/kg), and distributional clearance (0.16 ± 0.07 liter/kg). The predictive ability of the developed model (including the above-mentioned covariates) was evaluated in a naive population of 19 pediatric patients. The predictability was very good. Precision (±95% confidence interval [CI]) (peak, 4.1 [±1.4], and trough, 2.2 [±0.7]) and bias (±95% CI) (peak, −0.58 [±2.2], and trough, 0.63 [±1.1] mg/liter) were significantly (P < 0.05) superior to those obtained using a conventional method (precision [±95% CI]: peak, 8.03 [±2.46], and trough, 2.7 [±0.74]; bias: peak, −7.1 [±2.9], and trough, −1.35 [±1.2] mg/liter). We propose the use of this population PK model to optimize VAN clinical therapies in our institution and others with similar patient population characteristics.
18
Bozzato, Alessandro, Johannes Zenk, Holger Greess, Joachim Hornung, Frank Gottwald, Christina Rabe, and Heinrich Iro. "Potential of ultrasound diagnosis for parotid tumors: Analysis of qualitative and quantitative parameters." Otolaryngology–Head and Neck Surgery 137, no. 4 (October 2007): 642–46. http://dx.doi.org/10.1016/j.otohns.2007.05.062.
Full textAbstract:
Objective Histology of parotid tumors determines the extent of surgery. The aim was to test ultrasound (US) contrast enhancer-kinetics to identify histologic entities, possibly being superior to qualitative morphological parameters. Study Design In a cross-sectional assessment of ultrasound diagnosis, the subjective US-classification was compared with contrast analysis with histology as gold standard. Subjects and Methods A total of 64 male and 61 female patients with a mean age of 54 years were included, with 13 malignant tumors. These were classified with US morphology, then time-dependent contrast medium analysis. Results A total of 92.8% of tumors were classified correctly as malignant or benign. The sensitivity, specificity, positive- and negative-predictive values were 66.7%, 86.3%, 60.6%, and 89.1% for differentiating Warthin tumors, but only 46.2%, 98.2%, 75%, and 94% for malignant lesions. Contrast parameters yielded significant parameters for benign tumors, not for malignant entities. Conclusion Although contrast medium analysis provided statistical criteria, these, however, do not possess the ability to improve the diagnostic prediction of tumor histology. Neither the morphologic classification nor contrast medium analysis was able to identify a malignant lesion sufficiently.
19
Di Staso, Silvio, Luca Agnifili, Federico Di Staso, Hilary Climastone, Marco Ciancaglini, and Gian Luca Scuderi. "Diagnostic capability of optic nerve head rim width and retinal nerve fiber thickness in open-angle glaucoma." European Journal of Ophthalmology 28, no. 4 (March 19, 2018): 459–64. http://dx.doi.org/10.1177/1120672117750057.
Full textAbstract:
Purpose: This study was performed to test the diagnostic capability of the minimum rim width compared to peripapillary retinal nerve fiber layer thickness in patients with glaucoma. Methods: A case control, observer masked study, was conducted. Minimum rim width and retinal nerve fiber layer thickness were assessed using the patient-specific axis traced between fovea-to-Bruch’s membrane opening center axis. For both minimum rim width and retinal nerve fiber layer thickness, the regionalization in six sectors (nasal, superior-nasal, superior-temporal, temporal, inferior-temporal, and inferior-nasal) was analyzed. Eyes with at least one sector with value below the 5% or 1% normative limit of the optical coherence tomography normative database were classified as glaucomatous. The area under the receiver operator characteristic curve, the accuracy, sensitivity, specificity, and predictive positive and negative values were calculated for both minimum rim width and retinal nerve fiber layer thickness. Results: A total of 118 eyes of 118 Caucasian subjects (80 eyes with open-angle glaucoma and 38 control eyes) were enrolled in the study. Accuracy, sensitivity, and specificity were 79.7%, 77.5%, and 84.2%, respectively, for minimum rim width and 84.7%, 82.5%, and 89.5% for retinal nerve fiber layer thickness. The positive predictive values were 0.91% and 0.94% for minimum rim width and retinal nerve fiber layer thickness, respectively, whereas the negative predictive values were 0.64% and 0.70%. The area under the receiver operator characteristic curve was 0.892 for minimum rim width and 0.938 for retinal nerve fiber layer thickness. Conclusion: Our results indicated that the sector analysis based on Bruch’s membrane opening and fovea to disk alignment is able to detect glaucomatous defects, and that Bruch’s membrane opening minimum rim width and retinal nerve fiber layer thickness showed equivalent diagnostic ability.
20
Yang, Hui, Wuritu Yang, Fu-Ying Dao, Hao Lv, Hui Ding, Wei Chen, and Hao Lin. "A comparison and assessment of computational method for identifying recombination hotspots in Saccharomyces cerevisiae." Briefings in Bioinformatics 21, no. 5 (October 21, 2019): 1568–80. http://dx.doi.org/10.1093/bib/bbz123.
Full textAbstract:
Abstract Meiotic recombination is one of the most important driving forces of biological evolution, which is initiated by double-strand DNA breaks. Recombination has important roles in genome diversity and evolution. This review firstly provides a comprehensive survey of the 15 computational methods developed for identifying recombination hotspots in Saccharomyces cerevisiae. These computational methods were discussed and compared in terms of underlying algorithms, extracted features, predictive capability and practical utility. Subsequently, a more objective benchmark data set was constructed to develop a new predictor iRSpot-Pse6NC2.0 (http://lin-group.cn/server/iRSpot-Pse6NC2.0). To further demonstrate the generalization ability of these methods, we compared iRSpot-Pse6NC2.0 with existing methods on the chromosome XVI of S. cerevisiae. The results of the independent data set test demonstrated that the new predictor is superior to existing tools in the identification of recombination hotspots. The iRSpot-Pse6NC2.0 will become an important tool for identifying recombination hotspot.
21
Tung, Chi-Hua, Yi-Sheng Chang, Kai-Po Chang, and Yen-Wei Chu. "NIgPred: Class-Specific Antibody Prediction for Linear B-Cell Epitopes Based on Heterogeneous Features and Machine-Learning Approaches." Viruses 13, no. 8 (August 3, 2021): 1531. http://dx.doi.org/10.3390/v13081531.
Full textAbstract:
Upon invasion by foreign pathogens, specific antibodies can identify specific foreign antigens and disable them. As a result of this ability, antibodies can help with vaccine production and food allergen detection in patients. Many studies have focused on predicting linear B-cell epitopes, but only two prediction tools are currently available to predict the sub-type of an epitope. NIgPred was developed as a prediction tool for IgA, IgE, and IgG. NIgPred integrates various heterologous features with machine-learning approaches. Differently from previous studies, our study considered peptide-characteristic correlation and autocorrelation features. Sixty kinds of classifier were applied to construct the best prediction model. Furthermore, the genetic algorithm and hill-climbing algorithm were used to select the most suitable features for improving the accuracy and reducing the time complexity of the training model. NIgPred was found to be superior to the currently available tools for predicting IgE epitopes and IgG epitopes on independent test sets. Moreover, NIgPred achieved a prediction accuracy of 100% for the IgG epitopes of a coronavirus data set. NIgPred is publicly available at our website.
22
Rowe, Anna L., Thomas N. Meyer, Todd M. Miller, and Kurt Steuck. "Assessing Knowledge Structures: Don't Always Call an Expert." Proceedings of the Human Factors and Ergonomics Society Annual Meeting 41, no. 2 (October 1997): 1203–7. http://dx.doi.org/10.1177/1071181397041002107.
Full textAbstract:
Measures of knowledge structures can be used to access and evaluate conceptual understanding for assessment and training purposes. Typically, the quality of an individual's knowledge structure is determined by comparing it to a standard knowledge structure that is an aggregate of the structures of several experts. Recent research suggests that this approach may not be appropriate for all domains. This study investigated different approaches for forming a standard knowledge structure for two knowledge structure measures: relatedness ratings and a diagramming task. Three approaches to developing knowledge standards were compared: a standard derived from expert data, a standard based on high-performing students, and a rational standard developed through an analysis of instructional materials. The knowledge standards were compared in their ability to predict performance on a multiple-choice test. The results showed that comparison of students' structures with a standard constructed by aggregating high-performing student structures produced scores that were independently predictive of performance for both measures, whereas the expert standard resulted in independently predictive knowledge scores for only the diagramming task. For both measures, the high-performer standard and the aggregate expert standard were superior to the rational standard. These results offer support for using standards other than the expert-consensus standard typically used when assessing the quality of knowledge structures.
23
Park, Cheol Ho. "The Profitability of Technical Trading Rules in the KOSPI200 Futures Market." Journal of Derivatives and Quantitative Studies 15, no. 2 (November 30, 2007): 85–119. http://dx.doi.org/10.1108/jdqs-02-2007-b0004.
Full textAbstract:
This article investigates the profitability of technical trading rules in the KOSPI200 futures market from 1997 through 2006 after accounting for transaction costs, risk. and data-snooping problems. To effectively mitigate data - snooping problems resulted from survivorship bias, we largely expand the full set of technical trading rules handled in the previous literature and measure statistical significance of technical trading performance using White’s (2000) Bootstrap Reality Check (BRC) methodology and Hansen’s (2005) Superior Predictive Ability (SPA) test that can take account of interdependency across individual technical trading rules. The results indicate that under the net return criterion the best trading rule generates the highest mean net return of about 32% per annum during the sample period but the trading return is statistically insignificant when the effect of data-snooping is considered. Similar results are found under the Sharpe ratio criterion. These findings suggest that substantial technical trading profits may be obtained due to chance rather than the Inherent predictability of technical trading rules.
24
Mahajan, Arvind. "Information content of web-based stock ratings: the case of Motley fool CAPS data." Journal of Advances in Management Research 15, no. 3 (August 6, 2018): 393–410. http://dx.doi.org/10.1108/jamr-02-2018-0025.
Full textAbstract:
Purpose The purpose of this paper is to answer a fundamental question – are individual stock picks by a particular internet investment community informative enough to beat the market? The author observes that the stock picks by the CAPS community are reflective of existing information and portfolios based upon CAPS community stock rankings do not generate abnormal returns. The CAPS community is good at tracking existing performance but, it lacks predictive ability. Design/methodology/approach The study uses a unique data set of stock ratings from Motley Fools CAPS community to determine the information content embedded in these ratings. Observing predictive ability of this web-based stock ratings forum will raise questions about the efficiency of the financial markets. The author forms stock portfolios based on stocks’ star ratings, and star rating changes, and test if the long-short portfolio strategy generates significant α after controlling for single, and multi-factor asset pricing models, such as Fama-French three-factor model and Carhart four-factor model. Findings The paper finds no evidence that the CAPS community ratings contain “information content,” which can be exploited to generate abnormal returns. CAPS community ratings are good at tracking existing stock performance, but cannot be used to make superior forecasts to generate abnormal returns. The findings are consistent with the efficient market hypothesis. Furthermore, the author provides evidence that CAPS community ratings are themselves determined by stock performance rather than the other way around. Originality/value The study employs a unique data set capturing the stock ratings of a very popular web-based investment community to evaluate its ability to make better than random forecasts. Besides applying well-accepted asset pricing models to generate α, the study conducts causality tests to discern a causal relation between stock ratings and stock performance.
25
Krips, Ram, and Miriam Furst. "Prediction of Human's Ability in Sound Localization Based on the Statistical Properties of Spike Trains along the Brainstem Auditory Pathway." Computational Intelligence and Neuroscience 2014 (2014): 1–11. http://dx.doi.org/10.1155/2014/575716.
Full textAbstract:
The minimum audible angle test which is commonly used for evaluating human localization ability depends on interaural time delay, interaural level differences, and spectral information about the acoustic stimulus. These physical properties are estimated at different stages along the brainstem auditory pathway. The interaural time delay is ambiguous at certain frequencies, thus confusion arises as to the source of these frequencies. It is assumed that in a typical minimum audible angle experiment, the brain acts as an unbiased optimal estimator and thus the human performance can be obtained by deriving optimal lower bounds. Two types of lower bounds are tested: the Cramer-Rao and the Barankin. The Cramer-Rao bound only takes into account the approximation of the true direction of the stimulus; the Barankin bound considers other possible directions that arise from the ambiguous phase information. These lower bounds are derived at the output of the auditory nerve and of the superior olivary complex where binaural cues are estimated. An agreement between human experimental data was obtained only when the superior olivary complex was considered and the Barankin lower bound was used. This result suggests that sound localization is estimated by the auditory nuclei using ambiguous binaural information.
26
Marani, Afshin, Armin Jamali, and Moncef L. Nehdi. "Predicting Ultra-High-Performance Concrete Compressive Strength Using Tabular Generative Adversarial Networks." Materials 13, no. 21 (October 24, 2020): 4757. http://dx.doi.org/10.3390/ma13214757.
Full textAbstract:
There have been abundant experimental studies exploring ultra-high-performance concrete (UHPC) in recent years. However, the relationships between the engineering properties of UHPC and its mixture composition are highly nonlinear and difficult to delineate using traditional statistical methods. There is a need for robust and advanced methods that can streamline the diverse pertinent experimental data available to create predictive tools with superior accuracy and provide insight into its nonlinear materials science aspects. Machine learning is a powerful tool that can unravel underlying patterns in complex data. Accordingly, this study endeavors to employ state-of-the-art machine learning techniques to predict the compressive strength of UHPC using a comprehensive experimental database retrieved from the open literature consisting of 810 test observations and 15 input features. A novel approach based on tabular generative adversarial networks was used to generate 6513 plausible synthetic data for training robust machine learning models, including random forest, extra trees, and gradient boosting regression. While the models were trained using the synthetic data, their ability to generalize their predictions was tested on the 810 experimental data thus far unknown and never presented to the models. The results indicate that the developed models achieved outstanding predictive performance. Parametric studies using the models were able to provide insight into the strength development mechanisms of UHPC and the significance of the various influential parameters.
27
VerMilyea, M., J. M. M. Hall, S. M. Diakiw, A. Johnston, T. Nguyen, D. Perugini, A. Miller, A. Picou, A. P. Murphy, and M. Perugini. "Development of an artificial intelligence-based assessment model for prediction of embryo viability using static images captured by optical light microscopy during IVF." Human Reproduction 35, no. 4 (April 2020): 770–84. http://dx.doi.org/10.1093/humrep/deaa013.
Full textAbstract:
Abstract STUDY QUESTION Can an artificial intelligence (AI)-based model predict human embryo viability using images captured by optical light microscopy? SUMMARY ANSWER We have combined computer vision image processing methods and deep learning techniques to create the non-invasive Life Whisperer AI model for robust prediction of embryo viability, as measured by clinical pregnancy outcome, using single static images of Day 5 blastocysts obtained from standard optical light microscope systems. WHAT IS KNOWN ALREADY Embryo selection following IVF is a critical factor in determining the success of ensuing pregnancy. Traditional morphokinetic grading by trained embryologists can be subjective and variable, and other complementary techniques, such as time-lapse imaging, require costly equipment and have not reliably demonstrated predictive ability for the endpoint of clinical pregnancy. AI methods are being investigated as a promising means for improving embryo selection and predicting implantation and pregnancy outcomes. STUDY DESIGN, SIZE, DURATION These studies involved analysis of retrospectively collected data including standard optical light microscope images and clinical outcomes of 8886 embryos from 11 different IVF clinics, across three different countries, between 2011 and 2018. PARTICIPANTS/MATERIALS, SETTING, METHODS The AI-based model was trained using static two-dimensional optical light microscope images with known clinical pregnancy outcome as measured by fetal heartbeat to provide a confidence score for prediction of pregnancy. Predictive accuracy was determined by evaluating sensitivity, specificity and overall weighted accuracy, and was visualized using histograms of the distributions of predictions. Comparison to embryologists’ predictive accuracy was performed using a binary classification approach and a 5-band ranking comparison. MAIN RESULTS AND THE ROLE OF CHANCE The Life Whisperer AI model showed a sensitivity of 70.1% for viable embryos while maintaining a specificity of 60.5% for non-viable embryos across three independent blind test sets from different clinics. The weighted overall accuracy in each blind test set was >63%, with a combined accuracy of 64.3% across both viable and non-viable embryos, demonstrating model robustness and generalizability beyond the result expected from chance. Distributions of predictions showed clear separation of correctly and incorrectly classified embryos. Binary comparison of viable/non-viable embryo classification demonstrated an improvement of 24.7% over embryologists’ accuracy (P = 0.047, n = 2, Student’s t test), and 5-band ranking comparison demonstrated an improvement of 42.0% over embryologists (P = 0.028, n = 2, Student’s t test). LIMITATIONS, REASONS FOR CAUTION The AI model developed here is limited to analysis of Day 5 embryos; therefore, further evaluation or modification of the model is needed to incorporate information from different time points. The endpoint described is clinical pregnancy as measured by fetal heartbeat, and this does not indicate the probability of live birth. The current investigation was performed with retrospectively collected data, and hence it will be of importance to collect data prospectively to assess real-world use of the AI model. WIDER IMPLICATIONS OF THE FINDINGS These studies demonstrated an improved predictive ability for evaluation of embryo viability when compared with embryologists’ traditional morphokinetic grading methods. The superior accuracy of the Life Whisperer AI model could lead to improved pregnancy success rates in IVF when used in a clinical setting. It could also potentially assist in standardization of embryo selection methods across multiple clinical environments, while eliminating the need for complex time-lapse imaging equipment. Finally, the cloud-based software application used to apply the Life Whisperer AI model in clinical practice makes it broadly applicable and globally scalable to IVF clinics worldwide. STUDY FUNDING/COMPETING INTEREST(S) Life Whisperer Diagnostics, Pty Ltd is a wholly owned subsidiary of the parent company, Presagen Pty Ltd. Funding for the study was provided by Presagen with grant funding received from the South Australian Government: Research, Commercialisation and Startup Fund (RCSF). ‘In kind’ support and embryology expertise to guide algorithm development were provided by Ovation Fertility. J.M.M.H., D.P. and M.P. are co-owners of Life Whisperer and Presagen. Presagen has filed a provisional patent for the technology described in this manuscript (52985P pending). A.P.M. owns stock in Life Whisperer, and S.M.D., A.J., T.N. and A.P.M. are employees of Life Whisperer.
28
Stein, Anthony Selwyn, Drew Watson, Shweta Kapoor, Kunal Ghosh Ghosh Roy, Aftab Alam, Diwyanshu Sahu, Kabya Basu, et al. "Superior therapy response predictions for patients with myelodysplastic syndrome (MDS) using Cellworks Singula: MyCare-009-02." Journal of Clinical Oncology 38, no. 15_suppl (May 20, 2020): e19528-e19528. http://dx.doi.org/10.1200/jco.2020.38.15_suppl.e19528.
Full textAbstract:
e19528 Background: Despite using cytogenetic and molecular-risk stratification and precision medicine, the current overall outcome of MDS patients remains relatively poor. Therapy selection is often based on information considering only cytogenetics and single molecular aberrations and ignoring other patient-specific omics data that could potentially enable more effective treatments. The Cellworks Singula™ report predicts response for physician prescribed therapies (PPT) using the novel Cellworks Omics Biology Model (CBM) to simulate downstream molecular effects of cell signaling, drugs, and radiation on patient-specific in silico diseased cells. We test the hypothesis that Singula is a more accurate predictor of patient-specific therapy response than PPT. Methods: Singula’s ability to predict response was evaluated in an independent, randomly selected, retrospective cohort of 146 MDS patients aged 28 to 89 years (median 69) treated with PPT. Patient omics data was available from PubMed and TCGA. The accuracy of Singula was compared to that of PPT using McNemar’s test to account for the correlation between Singula and PPT. Multivariate logistic regression modeled complete response (CR) as a function of patient age, PPT, and Singula against any non-response (NR). Likelihood ratio tests were performed to further validate if Singula provides predictive information beyond PPT or patient age. Similar analyses were performed for overall survival (OS) using proportional hazards regression. Results: Singula was a better predictor for CR than PPT (McNemar’s χ2 = 42.0, p-value < 0.0001), with an overall accuracy of 73.3% (Exact 95% CI: 65.3%, 80.2%) compared to 37.7% (95% CI: 30.0%, 46.1%) for PPT. Singula exhibited a sensitivity and specificity of 90.9% (95% CI: 80.0%, 97.0%) and 62.6% (95% CI: 51.8%, 72.6%), respectively. In multivariate regression analysis, Singula (p < 0.0001) remained an independent predictor for CR after adjusting for patient age (p = 0.0759) and PPT (p = 0.0496). Singula provided alternative therapy selections for 17 of 53 true negative detected by Cellworks. Conclusions: Singula is a superior independent predictor for CR compared to PPT in MDS patients. The Singula report can also validate therapy selection, correctly identify non-responders to PPT and further provide alternative therapy selections.
29
Abubakar, Ibrahim, Ajit Lalvani, Jo Southern, Alice Sitch, Charlotte Jackson, Oluchukwu Onyimadu, Marc Lipman, et al. "Two interferon gamma release assays for predicting active tuberculosis: the UK PREDICT TB prognostic test study." Health Technology Assessment 22, no. 56 (October 2018): 1–96. http://dx.doi.org/10.3310/hta22560.
Full textAbstract:
Background Despite a recent decline in the annual incidence of tuberculosis (TB) in the UK, rates remain higher than in most Western European countries. The detection and treatment of latent TB infection (LTBI) is an essential component of the UK TB control programme. Objectives To assess the prognostic value and cost-effectiveness of the current two interferon gamma release assays (IGRAs) compared with the standard tuberculin skin test (TST) for predicting active TB among untreated individuals at increased risk of TB: (1) contacts of active TB cases and (2) new entrants to the UK from high-TB-burden countries. Design A prospective cohort study and economic analysis. Participants and setting Participants were recruited in TB clinics, general practices and community settings. Contacts of active TB cases and migrants who were born in high-TB-burden countries arriving in the UK were eligible to take part if they were aged ≥ 16 years. Main outcome measures Outcomes include incidence rate ratios comparing the incidence of active TB in those participants with a positive test result and those with a negative test result for each assay, and combination of tests and the cost per quality-adjusted life-year (QALY) for each screening strategy. Results A total of 10,045 participants were recruited between May 2010 and July 2015. Among 9610 evaluable participants, 97 (1.0%) developed active TB. For the primary analysis, all test data were available for 6380 participants, with 77 participants developing active TB. A positive result for TSTa (positive if induration is ≥ 5 mm) was a significantly poorer predictor of progression to active TB than a positive result for any of the other tests. Compared with TSTb [positive if induration is ≥ 6 mm without prior bacillus Calmette–Guérin (BCG) alone, T-SPOT®.TB (Oxford Immunotec Ltd, Oxford, UK), TSTa + T-SPOT.TB, TSTa + IGRA and the three combination strategies including TSTb were significantly superior predictors of progression. Compared with the T-SPOT.TB test alone, TSTa + T-SPOT.TB, TSTb + QuantiFERON® TB Gold In-Tube (QFT-GIT; QIAGEN GmbH, Hilden, Germany) and TSTb + IGRA were significantly superior predictors of progression and, compared with QFT-GIT alone, T-SPOT.TB, TSTa + T-SPOT.TB, TSTa + QFT-GIT, TSTa + IGRA, TSTb + T-SPOT.TB, TSTb + QFT-GIT and TSTb + IGRA were significantly superior predictors of progression. When evaluating the negative predictive performance of tests and strategies, negative results for TSTa + QFT-GIT were significantly poorer predictors of non-progression than negative results for TSTa, T-SPOT.TB and TSTa + IGRA. The most cost-effective LTBI testing strategies are the dual-testing strategies. The cost and QALY differences between the LTBI testing strategies were small; in particular, QFT-GIT, TSTb + T-SPOT.TB and TSTb + QFT-GIT had very similar incremental net benefit estimates. Conclusion This study found modest differences between tests, or combinations of tests, in identifying individuals who would go on to develop active TB. However, a two-step approach that combined TSTb with an IGRA was the most cost-effective testing option. Implications for practice and future research The two-step TSTb strategy, which stratified the TST by prior BCG vaccination followed by an IGRA, was the most cost-effective approach. The limited ability of current tests to predict who will progress limits the clinical utility of tests. The implications of these results for the NHS England/Public Health England national TB screening programme for migrants should be investigated. Study registration This study is registered as NCT01162265. Funding The National Institute for Health Research Health Technology Assessment programme.
30
Marcucci, Guido, Drew Watson, Shweta Kapoor, Swaminathan Rajagopalan, Rajan Parashar, Aktar Alam, Diwyanshu Sahu, et al. "Superior therapy response predictions for patients with acute myeloid leukemia (AML) using Cellworks Singula: MyCare-009-01." Journal of Clinical Oncology 38, no. 15_suppl (May 20, 2020): e19502-e19502. http://dx.doi.org/10.1200/jco.2020.38.15_suppl.e19502.
Full textAbstract:
e19502 Background: Despite using cytogenetic and molecular-risk stratification and precision medicine, the current overall outcome of AML patients remains relatively poor. Therapy selection is often based on information considering only cytogenetics and single molecular aberrations and ignoring other patient-specific omics data that could potentially enable more effective treatments. The Cellworks Singula™ report predicts response for physician prescribed therapies (PPT) using the novel Cellworks Omics Biology Model (CBM) to simulate downstream molecular effects of cell signaling, drugs, and radiation on patient-specific in silico diseased cells. We test the hypothesis that Singula is a more accurate predictor of patient-specific therapy response than PPT. Methods: Singula’s ability to predict response was evaluated in an independent, randomly selected, retrospective cohort of 494 AML patients aged 2 to 85 years (median 54) treated with PPT. Patient omics data was available from PubMed. The accuracy of Singula was compared to that of PPT using McNemar’s test to account for the correlation between Singula and PPT. Multivariate logistic regression modeled complete response (CR) as a function of patient age, PPT, and Singula against any non-response (NR). Likelihood ratio tests were performed to further validate if Singula provides predictive information beyond PPT or patient age. Similar analyses were performed for overall survival (OS) using proportional hazards regression. Results: Singula was a better predictor for CR than PPT (McNemar’s χ2 = 72.0, p-value < 0.0001), with an overall accuracy of 88.5% (95% CI: 85.3%, 91.1%) compared to 70.2% (95% CI: 66.0%, 74.2%) for PPT. Singula exhibited a sensitivity and specificity of 97.1% and 68.0%, respectively. In multivariate regression analysis, Singula (p < 0.0001) remained an independent predictor for CR after adjusting for patient age (p = 0.0329) while PPT became not significant (p = 0.75). Singula was also an independent predictor for OS (p < 0.0001) after adjusting for patient age (p = 0.0018) and PPT (p = 0.0011). For all 100 true negatives, Singula generated alternative standard of care therapy selections with predicted clinical response. Conclusions: Singula is a superior independent predictor for CR and OS compared to PPT in AML patients. The Singula report can also validate therapy selection, correctly identify non-responders to PPT and further provide alternative therapy selections.
31
Wen, Patrick Y., Drew Watson, Shweta Kapoor, Aftab Alam, Aktar Alam, Deepak Anil Lala, Diwyanshu Sahu, et al. "Superior therapy response predictions for patients with glioblastoma (GBM) using Cellworks Singula: MyCare-009-03." Journal of Clinical Oncology 38, no. 15_suppl (May 20, 2020): 2519. http://dx.doi.org/10.1200/jco.2020.38.15_suppl.2519.
Full textAbstract:
2519 Background: Despite using cytogenetic and molecular-risk stratification and precision medicine, the current overall outcome of GBM patients remains relatively poor. Therapy selection is often based on information considering only a single aberration and ignoring other patient-specific omics data which could potentially enable more effective treatment selection. The Cellworks Singula™ report predicts response for physician prescribed therapies (PPT) using the novel Cellworks Omics Biology Model (CBM) to simulate downstream molecular effects of cell signaling, drugs, and radiation on patient-specific in silico diseased cells. We test the hypothesis that Singula is a superior predictor of progression-free survival (PFS) and overall survival (OS) compared to PPT. Methods: Singula’s ability to predict response was evaluated in an independent, randomly selected, retrospective cohort of 109 GBM patients aged 17 to 83 years treated with PPT. Patient omics data was available from TCGA. Singula uses PubMed to generate protein interaction network activated and inactivated disease pathways. We simulated PPT for each patient and calculated the quantitative drug effect on a composite GBM disease inhibition score based on specific phenotypes while blinded to clinical response. Univariate and multivariate proportional hazards (PH) regression analyses were performed to determine if Singula provides predictive information for PFS and OS, respectively, above and beyond age and PPT. Results: In univariate analyses, Singula was a significant predictor of both PFS (HR = 4.130, p < 0.000) and OS (HR = 2.418, p < 0.0001). In multivariate PH regression analyses, Singula (HR = 4.033, p < 0.0001) remained an independent predictor of PFS after adjustment for PPT (p = 0.1453) and patient age (p = 0.4273). Singula (HR = 1.852, p = 0.0070) was also a significant independent predictor of OS after adjustment for PPT (p = 0.4127) and patient age (p = 0.0003). Results indicate that Singula is a superior predictor of both PFS and OS compared to PPT. Singula provided alternative therapy selections for 29 of 52 disease progressors detected by Cellworks. Conclusions: Singula is a superior predictor of PFS and OS in GBM patients compared to PPT. Singula can identify non-responders to PPT and provide alternative therapy selections.
32
Jain, Prayut, and Shashi Jain. "Can Machine Learning-Based Portfolios Outperform Traditional Risk-Based Portfolios? The Need to Account for Covariance Misspecification." Risks 7, no. 3 (July 3, 2019): 74. http://dx.doi.org/10.3390/risks7030074.
Full textAbstract:
The Hierarchical risk parity (HRP) approach of portfolio allocation, introduced by Lopez de Prado (2016), applies graph theory and machine learning to build a diversified portfolio. Like the traditional risk-based allocation methods, HRP is also a function of the estimate of the covariance matrix, however, it does not require its invertibility. In this paper, we first study the impact of covariance misspecification on the performance of the different allocation methods. Next, we study under an appropriate covariance forecast model whether the machine learning based HRP outperforms the traditional risk-based portfolios. For our analysis, we use the test for superior predictive ability on out-of-sample portfolio performance, to determine whether the observed excess performance is significant or if it occurred by chance. We find that when the covariance estimates are crude, inverse volatility weighted portfolios are more robust, followed by the machine learning-based portfolios. Minimum variance and maximum diversification are most sensitive to covariance misspecification. HRP follows the middle ground; it is less sensitive to covariance misspecification when compared with minimum variance or maximum diversification portfolio, while it is not as robust as the inverse volatility weighed portfolio. We also study the impact of the different rebalancing horizon and how the portfolios compare against a market-capitalization weighted portfolio.
33
Fasano, Serena, Luciana Pierro, Alessia Borgia, Melania Alessia Coscia, Ranieri Formica, Laura Bucci, Antonella Riccardi, and Francesco Ciccia. "Biomarker panels may be superior over single molecules in prediction of renal flares in systemic lupus erythematosus: an exploratory study." Rheumatology 59, no. 11 (March 24, 2020): 3193–200. http://dx.doi.org/10.1093/rheumatology/keaa074.
Full textAbstract:
Abstract Objective Recent evidence suggests that some urinary biomarkers, namely Vascular Cell Adhesion Molecule-1 (VCAM-1), Intercellular Adhesion Molecule-1 (ICAM-1), Monocyte Chemoattractant Protein 1 (MCP-1), Neutrophil Gelatinase Associated Lipocalcin and Lipocalin-type Prostaglandin D-Synthetase (L-PGDS), might discriminate SLE patients with ongoing renal activity from those with stable disease. The objective of this study was to assess the role of these markers in predicting renal flares in comparison with conventional biomarkers and to derive a biomarker panel which may improve diagnostic accuracy. Methods Eligible participants were SLE patients prospectively followed at our clinic. Urinary biomarker levels were measured in urinary sample by ELISA assay and were compared by the unpaired Student’s t test or the Mann–Whitney U test as appropriate. Receiver operating characteristic analysis was used to calculate the area under the curve. Cox regression was used to identify independent factors associated with disease flares. Results Urine was collected from 61 patients. During 8 months’ follow-up, eight patients experienced a renal flare. Urinary L-PGDS, ICAM-1 and VCAM-1 levels were significantly increased in the patients who subsequently experienced a renal flare with respect to the remaining 53. At Cox regression analysis, L-PGDS, ICAM-1, VCAM-1, hypocomplementemia and anti-dsDNA antibodies were factors associated with renal flares. Based on receiver operating characteristic analysis, a combination of novel and conventional biomarkers demonstrated an excellent ability for accurately identifying a flare. Conclusion This study might suggest the usefulness of a novel biomarker panel in predicting a renal flare in SLE.
34
Winther, Simon, Louise Nissen, Jelmer Westra, Samuel Emil Schmidt, Nadia Bouteldja, Lars Lyhne Knudsen, Lene Helleskov Madsen, et al. "Pre-test probability prediction in patients with a low to intermediate probability of coronary artery disease: a prospective study with a fractional flow reserve endpoint." European Heart Journal - Cardiovascular Imaging 20, no. 11 (April 9, 2019): 1208–18. http://dx.doi.org/10.1093/ehjci/jez058.
Full textAbstract:
Abstract Aims European and North American guidelines currently recommend pre-test probability (PTP) stratification based on simple probability models in patients with suspected coronary artery disease (CAD). However, no unequivocal recommendation has yet been established. We aimed to compare the ability of risk factors and different PTP stratification models to predict haemodynamically obstructive CAD with fractional flow reserve (FFR) as reference in low to intermediate probability patients. Methods and results We prospectively included 1675 patients with low to intermediate risk who had been referred to coronary computed tomography angiography (CTA). Patients with coronary stenosis were subsequently investigated by invasive coronary angiography (ICA) with FFR measurement if indicated. Discrimination and calibration were assessed for four models: the updated Diamond–Forrester (UDF), the CAD Consortium Basic, the Clinical, and the Clinical + Coronary artery calcium score (CACS). At coronary CTA, 24% of patients were diagnosed with a suspected stenosis and 10% had haemodynamically obstructive CAD at the ICA. Calibration for all CAD Consortium models increased compared with the UDF score. However, all models overestimated the probability of haemodynamically obstructive CAD. Discrimination increased by area under the receiver operating curve from 67% to 86% for UDF vs. CAD Consortium Clinical + CACS. The proportion of low-probability patients (pre-test score < 15%) was for the UDF, CAD Consortium Basic, Clinical, and Clinical + CACS: 14%, 58%, 51%, and 66%, respectively. The corresponding negative predictive values were 97%, 94%, 95%, and 98%, respectively. Conclusion CAD Consortium models improve PTP stratification compared with the UDF score, mainly due to superior calibration in low to intermediate probability patients. Adding the coronary calcium score to the models substantially increases discrimination. Clinical Trials. gov identifier NCT02264717.
35
Someren, Ken Van, and Garry S. Palmer. "Prediction of 200-m Sprint Kayaking Performance." Canadian Journal of Applied Physiology 28, no. 4 (August 1, 2003): 505–17. http://dx.doi.org/10.1139/h03-039.
Full textAbstract:
The aim of this study was to determine the anthropometric and physiological profile of 200-m sprint kayakers and to examine relationships with 200-m race performance. Twenty-six male kayakers who were categorised in two ability groups, international (Int) and national (Nat) level, underwent a battery of anthropometric and physiological tests and a 200-m race. Race time was significantly lower in Int than Nat (39.9 ± 0.8 s and 42.6 ± 0.9 s, respectively). Int demonstrated significantly greater measures of mesomorphy, biepycondylar humeral breadth, circumferences of the upper arm, forearm and chest, peak power and total work in a modified Wingate test, total work in a 2-min ergometry test, peak isokinetic power, and peak isometric force. Significant relationships were found between 200-m time and a number of anthropometric variables and anaerobic and dynamometric parameters. Stepwise multiple regression revealed that total work in the modified Wingate alone predicted 200-m race time (R2 = 0.53, SEE = 1.11 s) for all 26 subjects, while biepycondylar humeral breadth alone predicted race time (R2 = 0.54, SEE = 0.52 s) in Int. These results demonstrate that superior upper body dimensions and anaerobic capacities distinguish international-level kayakers from national-level athletes and may be used to predict 200-m performance. Key words: kayak, laboratory assessment, anthropometry, aerobic, anaerobic
36
Ahluwalia, Manmeet Singh, Drew Watson, Shweta Kapoor, Rajan Parashar, Kunal Ghosh Ghosh Roy, Aftab Alam, Swaminathan Rajagopalan, et al. "Superior therapy response predictions for patients with low-grade glioma (LGG) using Cellworks Singula: MyCare-009-04." Journal of Clinical Oncology 38, no. 15_suppl (May 20, 2020): 2569. http://dx.doi.org/10.1200/jco.2020.38.15_suppl.2569.
Full textAbstract:
2569 Background: Despite using cytogenetic and molecular-risk stratification and precision medicine, the current overall outcome of LGG patients remains relatively poor. Therapy selection is often based on information considering only a single aberration and ignoring other patient-specific omics data which could potentially enable more effective treatments. The Cellworks Singula report predicts response for physician prescribed therapies (PPT) using the novel Cellworks Omics Biology Model (CBM) to simulate downstream molecular effects of cell signaling, drugs, and radiation on patient-specific in silico diseased cells. We test the hypothesis that Singula is a superior predictor of progression-free survival (PFS) and overall survival (OS) compared to PPT. Methods: Singula’s ability to predict response was evaluated in an independent, randomly selected, retrospective cohort of 137 LGG patients aged 14 to 73 years treated with PPT. Patient omics data was available from TCGA. Singula uses PubMed to generate protein interaction network activated and inactivated disease pathways. We simulated the PPT for each patient and calculated the quantitative drug effect on a composite LGG disease inhibition score based on specific phenotypes while blinded to clinical response. Univariate and multivariate proportional hazards (PH) regression analyses were performed to determine if Singula provides predictive information for PFS and OS, respectively, above and beyond age and PPT. Results: In univariate analyses, Singula was a significant predictor of both PFS (HR = 3.587, p < 0.0001) and OS (HR = 3.044, p = 0.0007). In multivariate PH regression analyses, Singula (HR = 3.707, p < 0.0001) remained an independent predictor of PFS after adjustment for PPT (p = 0.3821) and patient age (p = 0.0020). Singula (HR = 2.970, p = 0.0013) was also a significant independent predictor of OS after adjustment for PPT (p = 0.0540) and patient age (p < 0.0001). Results indicate that Singula is a superior predictor of both PFS and OS compared to PPT. Singula provided alternative standard of care therapy selections for all 34 disease progressors. Conclusions: Singula is a superior predictor of PFS and OS in LGG patients compared to PPT. Singula can correctly identify non-responders to PPT and provide alternative therapy selections.
37
Gao, Pu, Jiageng Ruan, Yongchang Du, Paul D. Walker, and Nong Zhang. "The prediction of braking noise in regenerative braking system using closed-loop coupling disk brake model." Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 233, no. 14 (March 1, 2019): 3721–35. http://dx.doi.org/10.1177/0954407019832766.
Full textAbstract:
Aiming at improving regenerative braking ability in electric vehicles without compromising any safety, two different regenerative braking strategies are proposed in this study. The impact of continuously varying braking force distributions between front/rear wheel and electric/friction corresponding in two different strategies on braking noise are investigated. Based on the closed-loop coupling disk brake model, the relationship between the contact coupling stiffness and the braking force is established by considering the stationary modal test, the nonlinear optimization, and the relationship between brake-line pressure and braking force. The continuously varying braking force is initially transformed to continuously varying contact coupling stiffness, then, the brake noise tendency at each frequency band is calculated in closed-loop coupled model. The predicted result shows good consistency with the result recorded in bench test, verifying the reliability and effectivity of the presented method. The comparison of the two different electric braking strategies shows that the second braking strategy is superior to the first braking strategy in terms of suppressing the brake noise tendency.
38
Lang, Erhard W., Magdalena Kasprowicz, Peter Smielewski, Edgar Santos, John Pickard, and Marek Czosnyka. "Short pressure reactivity index versus long pressure reactivity index in the management of traumatic brain injury." Journal of Neurosurgery 122, no. 3 (March 2015): 588–94. http://dx.doi.org/10.3171/2014.10.jns14602.
Full textAbstract:
OBJECT The pressure reactivity index (PRx) correlates with outcome after traumatic brain injury (TBI) and is used to calculate optimal cerebral perfusion pressure (CPPopt). The PRx is a correlation coefficient between slow, spontaneous changes (0.003–0.05 Hz) in intracranial pressure (ICP) and arterial blood pressure (ABP). A novel index—the so-called long PRx (L-PRx)—that considers ABP and ICP changes (0.0008–0.008 Hz) was proposed. METHODS The authors compared PRx and L-PRx for 6-month outcome prediction and CPPopt calculation in 307 patients with TBI. The PRx- and L-PRx–based CPPopt were determined and the predictive power and discriminant abilities were compared. RESULTS The PRx and L-PRx correlation was good (R = 0.7, p < 0.00001; Spearman test). The PRx, age, CPP, and Glasgow Coma Scale score but not L-PRx were significant fatal outcome predictors (death and persistent vegetative state). There was a significant difference between the areas under the receiver operating characteristic curves calculated for PRx and L-PRx (0.61 ± 0.04 vs 0.51 ± 0.04; z-statistic = −3.26, p = 0.011), which indicates a better ability by PRx than L-PRx to predict fatal outcome. The CPPopt was higher for L-PRx than for PRx, without a statistical difference (median CPPopt for L-PRx: 76.9 mm Hg, interquartile range [IQR] ± 10.1 mm Hg; median CPPopt for PRx: 74.7 mm Hg, IQR ± 8.2 mm Hg). Death was associated with CPP below CPPopt for PRx (χ2 = 30.6, p < 0.00001), and severe disability was associated with CPP above CPPopt for PRx (χ2 = 7.8, p = 0.005). These relationships were not statistically significant for CPPopt for L-PRx. CONCLUSIONS The PRx is superior to the L-PRx for TBI outcome prediction. Individual CPPopt for L-PRx and PRx are not statistically different. Deviations between CPP and CPPopt for PRx are relevant for outcome prediction; those between CPP and CPPopt for L-PRx are not. The PRx uses the entire B-wave spectrum for index calculation, whereas the L-PRX covers only one-third of it. This may explain the performance discrepancy.
39
Apolo, Andrea Borghese, George Philips, Irina Ostrovnaya, Jonathan E. Rosenberg, Matthew I. Milowsky, Eric Jay Small, Dean F. Bajorin, and Susan Halabi. "External validation of prognostic models for overall survival (OS) in patients (pts) with advanced cancer (UC) treated with cisplatin-based chemotherapy." Journal of Clinical Oncology 30, no. 15_suppl (May 20, 2012): 4592. http://dx.doi.org/10.1200/jco.2012.30.15_suppl.4592.
Full textAbstract:
4592 Background: The most commonly used model predicting OS for UC pts treated with cisplatin-based chemotherapy is based on 2-variables (visceral metastases and performance status), developed at MSKCC in 1999, and validated in a phase III study (DeSantis JCO 2011). A prognostic model of OS for advanced UC pts based on 4 variables (visceral metastases, albumin, performance status, and hemoglobin) was developed using 308 pts from MSKCC (ASCO 2007 abstr 5055). We report the discriminative ability of the 4- and 2- variable models for advanced UC pts using an independent dataset from CALGB 90102. Methods: The analysis was performed using an external multi-institutional dataset from CALGB 90102. The primary measurement of predictive discrimination was Harrell’s c-index which was computed with 95% confidence interval (CI). To assess whether there was a statistically significant difference in discrimination between the two models, the U statistic was used to test whether the predictions of the 4-variable model in all possible pairs were more concordant with actual observations than the 2-variable model in the same pairs. Results: CALGB 90102 included 74 UC pts (58 males, 16 females), median age 64 years, treated with cisplatin, gemcitabine and gefitinib, enrolled from 7/02 to 4/05 with a median follow-up of 72.5 months. Visceral metastases were present in 64% (bone, 18%, liver, 31%, lung, 43%), median KPS 90%. The MSKCC 2-variable risk group distribution was 30% =0, 65%= 1 and 5%=2. The median OS =12.7 months (95% CI=10.4-20.5) with 68 deaths observed. When applied to the CALGB cohort, the predictive accuracy for the 4- and 2-variable models were 0.63 (95 CI= 0.56- 0.69) and 0.58 (95% CI= 0.52-0.65), respectively. There was a statistically significant difference in discrimination between the two models (p =0.019), with superiority of the 4-variable model compared to the 2-variable model. Conclusions: A 4-variable prognostic nomogram for survival in pts with advanced UC was superior to a 2-variable risk-group model. The 4-variable prognostic model may replace the widely used 2-variable model and can be used in the design and conduct of future phase II and III trials in advanced UC.
40
Prasetiono, Beni Agus, and Maharani Fatimah Gandasari. "Model Rangkaian Tes Keterampilan Tenis Lapangan pada Pemain Putra Kelompok Usia 12-14 Tahun." Jurnal SPORTIF : Jurnal Penelitian Pembelajaran 4, no. 2 (November 14, 2018): 220. http://dx.doi.org/10.29407/js_unpgri.v4i2.12498.
Full textAbstract:
This study aims to produce a series of field tennis skills tests for good male players aged 12-14 years. This study uses a quantitative approach. Independent variables in this study were 7 skills, namely service, straightforward target forehand groundstroke, crossed forehand target groundstroke, straight target backhand groundstroke, crossed backhand groundstroke, forehand / backhand volleyball, tennis rally ability. The sample used in this study was a tennis court athlete aged 12 to 14 years in Landak Regency and was a superior athlete. The sampling technique in this study uses two methods, namely random sampling or random sampling techniques and nonrandom sampling techniques. At the time of the instrument testing using a random sample technique, namely by stratified random sampling and determination of the titreion selector using non-random sampling technique, namely by sampling judgment. Data analysis techniques using the analysis method "Wherry Dolittle" with the help of SPSS and Microsoft Office Exel. From the description above it is concluded to get a good athlete the need for the selection process as early as possible related to the field of tennis and then follow a good training process as well. Field tennis talent test instruments have not been used in the selection of talented athletes. For this reason, there is a need to test the tennis court talent. The test instrument has also not known its accuracy in terms of predicting the ability or talent of athletes. Study and research are needed beforehand to produce a field tennis talent test instrument
41
Kwon, Young Suk, and Moon Seong Baek. "Development and Validation of a Quick Sepsis-Related Organ Failure Assessment-Based Machine-Learning Model for Mortality Prediction in Patients with Suspected Infection in the Emergency Department." Journal of Clinical Medicine 9, no. 3 (March 23, 2020): 875. http://dx.doi.org/10.3390/jcm9030875.
Full textAbstract:
The quick sepsis-related organ failure assessment (qSOFA) score has been introduced to predict the likelihood of organ dysfunction in patients with suspected infection. We hypothesized that machine-learning models using qSOFA variables for predicting three-day mortality would provide better accuracy than the qSOFA score in the emergency department (ED). Between January 2016 and December 2018, the medical records of patients aged over 18 years with suspected infection were retrospectively obtained from four EDs in Korea. Data from three hospitals (n = 19,353) were used as training-validation datasets and data from one (n = 4234) as the test dataset. Machine-learning algorithms including extreme gradient boosting, light gradient boosting machine, and random forest were used. We assessed the prediction ability of machine-learning models using the area under the receiver operating characteristic (AUROC) curve, and DeLong’s test was used to compare AUROCs between the qSOFA scores and qSOFA-based machine-learning models. A total of 447,926 patients visited EDs during the study period. We analyzed 23,587 patients with suspected infection who were admitted to the EDs. The median age of the patients was 63 years (interquartile range: 43–78 years) and in-hospital mortality was 4.0% (n = 941). For predicting three-day mortality among patients with suspected infection in the ED, the AUROC of the qSOFA-based machine-learning model (0.86 [95% CI 0.85–0.87]) for three -day mortality was higher than that of the qSOFA scores (0.78 [95% CI 0.77–0.79], p < 0.001). For predicting three-day mortality in patients with suspected infection in the ED, the qSOFA-based machine-learning model was found to be superior to the conventional qSOFA scores.
42
Fahey-Gilmour, J., J. Heasman, B. Rogalski, B. Dawson, and P. Peeling. "Can Elite Australian Football Player’s Game Performance Be Predicted?" International Journal of Computer Science in Sport 20, no. 1 (January 1, 2021): 55–78. http://dx.doi.org/10.2478/ijcss-2021-0004.
Full textAbstract:
Abstract In elite Australian football (AF) many studies have investigated individual player performance using a variety of outcomes (e.g. team selection, game running, game rating etc.), however, none have attempted to predict a player’s performance using combinations of pre-game factors. Therefore, our aim was to investigate the ability of commonly reported individual player and team characteristics to predict individual Australian Football League (AFL) player performance, as measured through the official AFL player rating (AFLPR) (Champion Data). A total of 158 variables were derived for players (n = 64) from one AFL team using data collected during the 2014-2019 AFL seasons. Various machine learning models were trained (cross-validation) on the 2014-2018 seasons, with the 2019 season used as an independent test set. Model performance, assessed using root mean square error (RMSE), varied (4.69-5.03 test set RMSE) but was generally poor when compared to a singular variable prediction (AFLPR pre-game rating: 4.72 test set RMSE). Variation in model performance (range RMSE: 0.14 excusing worst model) was low, indicating different approaches produced similar results, however, glmnet models were marginally superior (4.69 RMSE test set). This research highlights the limited utility of currently collected pre-game variables to predict week-to-week game performance more accurately than simple singular variable baseline models.
43
Söderlund, Neil, Alastair Gray, Ruairidh Milne, and James Raftery. "Case Mix Measurement in English Hospitals: An Evaluation of Five Methods for Predicting Resource Use." Journal of Health Services Research & Policy 1, no. 1 (January 1996): 10–19. http://dx.doi.org/10.1177/135581969600100104.
Full textAbstract:
Objectives: The introduction of an internal market in the British National Health Service (NHS) has highlighted the importance of developing appropriate, valid and timely measures of hospital activity, both for the purposes of specifying and monitoring contracts and for evaluating the success of the NHS reforms in general. This paper compares the validity of five case mix methods (Diagnosis Related Groups (DRGs); Healthcare Resource Groups (HRGs) versions 1 and 2; specialty classification; a simple age categorization) in predicting resource use. Methods: Two data sets were used to compare different case mix methods. A 3% random sample (n ≃ 300 000) of the 1992/3 Hospital Episodes Statistics was used to test their ability to predict variation in length of stay, and a second set of individually costed patient episodes from two hospitals (n ≃ 40 000) was used to test their ability to explain cost variation. Analysis of variance models were used to assess the fit of each of the case mix systems to test data and a simple significance test of differences in mean squared error between models was applied. Results: All case mix methods performed poorly on untrimmed data. When lengths of stay greater than 29 days were excluded, version 2 of HRGs explained 31% of total variance in length of stay and 25% of cost variation. DRGs explained less variance but performed better than HRGs version 1. For a typical hospital patient population consisting of a range of specialties, the difference in explanatory power between HRGs V2 and DRGs was statistically significant at the 5% level for sample sizes of approximately 2000 or greater. For individual specialties, the minimum sample size required for the difference between the groupers to be significant ranged from around 300 to over 2000. Conclusions: The locally developed HRGs version 2 system appears to offer superior performance in terms of resource homogeneity to other currently available approaches. It is also more adaptable and cheaper than imported alternatives and has been formally endorsed by the UK medical Royal Colleges.
44
Solomon, B., V. Gregorc, F. Taguchi, K. Kasahara, M. Nishio, H. Roder, F. R. Hirsch, M. W. Duncan, P. A. Bunn, and D. P. Carbone. "Prediction of clinical outcome in non-small cell lung cancer (NSCLC) patients treated with gefitinib using Matrix-Assisted Laser Desorption/Ionization-Time of Flight Mass Spectrometry (MALDI-TOF MS) of serum." Journal of Clinical Oncology 24, no. 18_suppl (June 20, 2006): 7004. http://dx.doi.org/10.1200/jco.2006.24.18_suppl.7004.
Full textAbstract:
7004 Background: Assessment of epidermal growth factor receptor (EGFR) gene copy number, mutational status, and protein levels may predict response and possibly survival following treatment with EGFR tyrosine kinase inhibitors, but all these methods require tumor tissue, highlighting the need for a non-invasive predictive test. We evaluated the ability of MALDI-TOF MS profiling of serum to predict which patients (Pts) with NSCLC were likely to benefit from gefitinib treatment. Methods: Serum from Pts with NSCLC, collected prior to treatment with gefitinib, was subjected to MALDI-TOF MS using Voyager DE-STR or DE-PRO instruments. Replicate mass spectra obtained at two institutions were submitted to a third party for processing (background subtraction, noise estimation, normalization, spectral alignment and peak identification) and selection of discriminating mass/charge (m/z) values from a training cohort of 70 Caucasian Pts. The predictive capability of the profile was then assessed in independent cohorts of NSCLC Pts. Results: Intra- and inter- laboratory reproducibility of MALDI spectra were excellent. A set of 11 m/z values (mass range 5 - 12.5 kDa) predictive of clinical benefit were identified in the training cohort and confirmed by leave-one-out cross validation. Spectra from 19/70 Pts in the training cohort were unclassifiable. For the remaining 51 Pts the algorithm discriminated groups more or less likely to benefit with respect to time to progression (median 3.0 vs. 1.5 mo., p = 0.0325) and overall survival (median 14.6 vs. 2.3 mo., p = 0.0128). Validation was performed in an independent cohort consisting of serum from 69 Japanese Pts. Spectra from 13/69 Pts were unclassifiable. For the remaining 56 Pts it was possible to identify a group with superior time to progression (median 14.8 vs. 2.1 mo., p = 0.0012) and overall survival (median 19.1 vs. 7.9 mo., p = 0.0102). Conclusions: MALDI-TOF MS of pretreatment serum may aid with the identification of subsets of NSCLC Pts that will benefit from treatment with gefitinib. This algorithm is currently being evaluated in an expanded cohort of Pts receiving gefitinib treatment and in Pts treated with erlotinib. [Table: see text]
45
Sahasrabudhe, Kieran, Melanie Rebechi, Ying Huang, Gregory Behbehani, Bhavana Bhatnagar, James Stewart Blachly, Bradley Wayne Blaser, et al. "Effect of induction intensity on survival in patients with acute myeloid leukemia." Journal of Clinical Oncology 39, no. 15_suppl (May 20, 2021): e19004-e19004. http://dx.doi.org/10.1200/jco.2021.39.15_suppl.e19004.
Full textAbstract:
e19004 Background: Acute Myeloid Leukemia (AML) has traditionally been treated frontline with intensive induction chemotherapy in patients fit enough for this treatment. The FDA has approved several oral targeted therapies for AML in recent years. The survival impact of these agents vs induction chemotherapy is unknown. Methods: In this single-center, retrospective study, patients diagnosed with AML from 2015-2020 were included if they received treatment with either high intensity chemotherapy (HiC) or lower intensity targeted therapy (LITT). HiC was defined as a regimen containing cytarabine + anthracycline given on a “7+3” based schedule. Patients treated with liposomal cytarabine-daunorubicin were excluded. LITT was defined as venetoclax, gilteritinib, enasidenib, or ivosidenib alone or in combination with a hypomethylating agent. Patients fell into four groups: HiC only, LITT only, HiC followed by LITT, and LITT followed by HiC with assignment censored at transplant. Overall survival (OS) was estimated using Kaplan-Meier method and patients receiving any HiC vs LITT only were compared using log-rank test. Results: A total of 332 patients were included: 177 received HiC only, 116 LITT only, 32 HiC before LITT, and 7 LITT before HiC. Baseline characteristics and OS data are outlined in the table. The any HiC group had a lower median age and more patients with WBC >10 K/µL at diagnosis, as well as more patients receiving allogeneic hematopoietic cell transplant (HCT). OS was superior in the any HiC group vs LITT only group. Receipt of any HiC remained predictive of OS after adjusting for age (HR 0.65, 95% CI 0.44-0.96, p = 0.03); however, was no longer predictive of OS after adjusting for age and receipt of HCT. Conclusions: While HiC was associated with superior OS compared to LITT only treatment in univariable analysis, the survival benefit was no longer apparent after adjusting for age and receipt of HCT. The results suggest that intensity of AML treatment is less impactful on prognosis than ability to receive HCT. Differences in age were likely confounded by clinical trial eligibility and prescribing information specifically affecting patients receiving LITT. In the era of LITT, prospective randomized studies of intensity of AML therapy, particularly in non-favorable risk disease, are imperative to striking a balance between toxicity and cure for patients of all ages.[Table: see text]
46
Carmona, Ruben, Kaveh Zakeri, Garrett Green, Lindsay Hwang, Sachin Gulaya, Beibei Xu, Rohan Verma, et al. "Improved Method to Stratify Elderly Patients With Cancer at Risk for Competing Events." Journal of Clinical Oncology 34, no. 11 (April 10, 2016): 1270–77. http://dx.doi.org/10.1200/jco.2015.65.0739.
Full textAbstract:
Purpose To compare a novel generalized competing event (GCE) model versus the standard Cox proportional hazards regression model for stratifying elderly patients with cancer who are at risk for competing events. Methods We identified 84,319 patients with nonmetastatic prostate, head and neck, and breast cancers from the SEER-Medicare database. Using demographic, tumor, and clinical characteristics, we trained risk scores on the basis of GCE versus Cox models for cancer-specific mortality and all-cause mortality. In test sets, we examined the predictive ability of the risk scores on the different causes of death, including second cancer mortality, noncancer mortality, and cause-specific mortality, using Fine-Gray regression and area under the curve. We compared how well models stratified subpopulations according to the ratio of the cumulative cause-specific hazard for cancer mortality to the cumulative hazard for overall mortality (ω) using the Akaike Information Criterion. Results In each sample, increasing GCE risk scores were associated with increased cancer-specific mortality and decreased competing mortality, whereas risk scores from Cox models were associated with both increased cancer-specific mortality and competing mortality. GCE models created greater separation in the area under the curve for cancer-specific mortality versus noncancer mortality (P < .001), indicating better discriminatory ability between these events. Comparing the GCE model to Cox models of cause-specific mortality or all-cause mortality, the respective Akaike Information Criterion scores were superior (lower) in each sample: prostate cancer, 28.6 versus 35.5 versus 39.4; head and neck cancer, 21.1 versus 29.4 versus 40.2; and breast cancer, 24.6 versus 32.3 versus 50.8. Conclusion Compared with standard modeling approaches, GCE models improve stratification of elderly patients with cancer according to their risk of dying from cancer relative to overall mortality.
47
Hong, Tae Hee, Hongui Cha, Joon Ho Shim, Boram Lee, Jongsuk Chung, Chung Lee, Nayoung K. D. Kim, et al. "Clinical advantage of targeted sequencing for unbiased tumor mutational burden estimation in samples with low tumor purity." Journal for ImmunoTherapy of Cancer 8, no. 2 (October 2020): e001199. http://dx.doi.org/10.1136/jitc-2020-001199.
Full textAbstract:
BackgroundTumor mutational burden (TMB) measurement is limited by low tumor purity of samples, which can influence prediction of the immunotherapy response, particularly when using whole-exome sequencing-based TMB (wTMB). This issue could be overcome by targeted panel sequencing-based TMB (pTMB) with higher depth of coverage, which remains unexplored.MethodsWe comprehensively reanalyzed four public datasets of immune checkpoint inhibitor (ICI)-treated cohorts (adopting pTMB or wTMB) to test each biomarker’s predictive ability for low purity samples (cut-off: 30%). For validation, paired genomic profiling with the same tumor specimens was performed to directly compare wTMB and pTMB in patients with breast cancer (paired-BRCA, n=165) and ICI-treated patients with advanced non-small-cell lung cancer (paired-NSCLC, n=156).ResultsLow tumor purity was common (range 30%–45%) in real-world samples from ICI-treated patients. In the survival analyzes of public cohorts, wTMB could not predict the clinical benefit of immunotherapy when tumor purity was low (log-rank p=0.874), whereas pTMB could effectively stratify the survival outcome (log-rank p=0.020). In the paired-BRCA and paired-NSCLC cohorts, pTMB was less affected by tumor purity, with significantly more somatic variants identified at low allele frequency (p<0.001). We found that wTMB was significantly underestimated in low purity samples with a large proportion of clonal variants undetected by whole-exome sequencing. Interestingly, pTMB more accurately predicted progression-free survival (PFS) after immunotherapy than wTMB owing to its superior performance in the low tumor purity subgroup (p=0.054 vs p=0.358). Multivariate analysis revealed pTMB (p=0.016), but not wTMB (p=0.32), as an independent predictor of PFS even in low-purity samples. The net reclassification index using pTMB was 21.7% in the low-purity subgroup (p=0.016).ConclusionsOur data suggest that TMB characterization with targeted deep sequencing might have potential strength in predicting ICI responsiveness due to its enhanced sensitivity for hard-to-detect variants at low-allele fraction. Therefore, pTMB could act as an invaluable biomarker in the setting of both clinical trials and practice outside of trials based on its reliable performance in mitigating the purity-related bias.
48
Sharma, Prateek, and Vipul _. "Forecasting stock index volatility with GARCH models: international evidence." Studies in Economics and Finance 32, no. 4 (October 5, 2015): 445–63. http://dx.doi.org/10.1108/sef-11-2014-0212.
Full textAbstract:
Purpose – The purpose of this paper is to compare the daily conditional variance forecasts of seven GARCH-family models. This paper investigates whether the advanced GARCH models outperform the standard GARCH model in forecasting the variance of stock indices. Design/methodology/approach – Using the daily price observations of 21 stock indices of the world, this paper forecasts one-step-ahead conditional variance with each forecasting model, for the period 1 January 2000 to 30 November 2013. The forecasts are then compared using multiple statistical tests. Findings – It is found that the standard GARCH model outperforms the more advanced GARCH models, and provides the best one-step-ahead forecasts of the daily conditional variance. The results are robust to the choice of performance evaluation criteria, different market conditions and the data-snooping bias. Originality/value – This study addresses the data-snooping problem by using an extensive cross-sectional data set and the superior predictive ability test (Hansen, 2005). Moreover, it covers a sample period of 13 years, which is relatively long for the volatility forecasting studies. It is one of the earliest attempts to examine the impact of market conditions on the forecasting performance of GARCH models. This study allows for a rich choice of parameterization in the GARCH models, and it uses a wide range of performance evaluation criteria, including statistical loss functions and the Mince-Zarnowitz regressions (Mincer and Zarnowitz 1969). Therefore, the results are more robust and widely applicable as compared to the earlier studies.
49
Mehta, Tapan, Hui-Ju Young, Byron Lai, Fuchenchu Wang, Yumi Kim, Mohan Thirumalai, Tracy Tracy, Robert Motl, and James Rimmer. "Comparing the Convergent and Concurrent Validity of the Dynamic Gait Index with the Berg Balance Scale in People with Multiple Sclerosis." Healthcare 7, no. 1 (February 15, 2019): 27. http://dx.doi.org/10.3390/healthcare7010027.
Full textAbstract:
Background: Recent clinical guidelines for adults with neurological disabilities suggest the need to assess measures of static and dynamic balance using the Berg Balance Scale (BBS) and Dynamic Gait Index (DGI) as core outcome measures. Given that the BBS measures both static and dynamic balance, it was unclear as to whether either of these instruments was superior in terms of its convergent and concurrent validity, and whether there was value in complementing the BBS with the DGI. Objective: The objective was to evaluate the concurrent and convergent validity of the BBS and DGI by comparing the performance of these two functional balance tests in people with multiple sclerosis (MS). Methods: Baseline cross-sectional data on 75 people with MS were collected for use in this study from 14 physical therapy clinics participating in a large pragmatic cluster-randomized trial. Convergent validity estimates between the DGI and BBS were examined by comparing the partial Spearman correlations of each test to objective lower extremity functional measures (Timed Up and Go (TUG), Six-Minute Walk Test (6MWT), Timed 25-Foot Walk (T25FW) test) and the self-reported outcomes of physical functioning and general health using the 36-Item Short Form Health Survey (SF-36). Concurrent validity was assessed by applying logistic regression with gait disability as the binary outcome (Patient Determined Disease Steps (PDDS) as the criterion measure). The predictive ability of two models, a reduced/parsimonious model including the BBS only and a second model including both the BBS and DGI, were compared using the adjusted coefficient of determinations. Results: Both the DGI and BBS were strongly correlated with lower extremity measures overall as well as across the two PDSS strata with correlations. In PDDS ≤ 2, the difference in the convergence of BBS with TUG and DGI with TUG was −0.123 (95% CI: −0.280, −0.012). While this finding was statistically significant at a type 1 error rate of 0.05, it was not significant (Hommel’s adjusted p-value = 0.465) after accounting for multiple testing corrections to control for the family-wise error rate. The BBS–SF-36 physical functioning correlation was at least moderate and significant overall and across both PDDS strata. However, the DGI–physical functioning score did not have a statistically significant correlation within PDDS ≤ 2. None of the differences in convergent and concurrent validity between the BBS and DGI were significant. The additional variation in 6MWT explained by the DGI when added to a model with the BBS was 7.78% (95% CI: 0.6%, 15%). Conclusions: These exploratory analyses on data collected in pragmatic real-world settings suggest that neither of these measures of balance is profoundly superior to the other in terms of its concurrent and convergent validity. The DGI may not have any utility for people with PDDS ≤ 2, especially if the focus is on mobility, but may be useful if the goal is to provide insight on lower extremity endurance. Further research leveraging longitudinal data from pragmatic trials and quasi-experimental designs may provide more information about the clinical usefulness of the DGI in terms of its predictive validity when compared to the BBS.
50
Hill, Brian T., Angela M. B. Collie, Tomas Radivoyevitch, Eric D. Hsi, and John Sweetenham. "Cell of Origin Determination in Diffuse Large B-Cell Lymphoma: Performance of Immunohistochemical (IHC) Algorithms and Ability to Predict Outcome." Blood 118, no. 21 (November 18, 2011): 950. http://dx.doi.org/10.1182/blood.v118.21.950.950.
Full textAbstract:
Abstract Abstract 950 INTRODUCTION: Diffuse large B-cell lymphoma (DLBCL) can be categorized by its cell of origin (CoO) as either being derived from a germinal center B-cell (GCB) or activated B-cell (ABC). Primary mediastinal DLBCL represents a third, distinct entity. This classification was initially defined by gene expression profiling (GEP), which remains the gold standard for such determination. Determination of CoO will likely become the basis for patient selection for clinical trials of targeted therapies. Several algorithms and methods have been developed that use immunohistochemistry (IHC) to differentiate GCB-DLBCL from non-GCB DLBCL. These include the Hans algorithm (utilizes staining for CD10, Bcl-6 and Mum1), the Choi algorithm (utilizes additional staining for GCET1 and FoxP1) as well as the Tally method (does not use Bcl-6 and utilizes LMO2 as a tie-breaker stain for otherwise equivocal cases). Recently, it has been recognized that IHC approaches to assign CoO may not be reproducible even at highly experienced laboratories. We sought to determine the performance of these IHC assays in our laboratory as a necessary step in developing trials based on CoO stratification. METHODS: We reviewed 108 adult (age ≥18) cases of de novo DLBCL, the majority of which were treated with chemoimmunotherapy (R-CHOP or R-CVP) at the Cleveland Clinic from 2000–2010. Diagnostic biopsies were available for all cases. IHC staining was performed on tissue microarrays (TMAs), and published algorithms (Hans, Choi and Tally) were applied to categorize cases as GCB or non-GCB. In addition, gene expression profiling was completed in a subset of these cases, for which frozen tissue was available. A linear predictor score for gene expression profiling (GEP) was used to assign cases in 31 of 33 cases with 2 technical failures at the array stage (overall success rate 84.8%). Clinical details including age, sex, International Prognostic Index (IPI) stage at diagnosis, treatment, progression free survival (PFS) and overall survival (OS) were captured for 69 of the 108 patients. Actuarial survival analysis was performed according to the Kaplan and Meier method, and the curves compared by the log-rank test. RESULTS: For the 69 patients with adequate clinical follow-up, the median age was 64 years old (range 18–88). There were 49% males and 51% females. The distribution of patients with stage I, II, III, and IV disease at the time of diagnosis was 20%, 14%, 20%, and 32% (14% had unknown stage). The 5-year overall survival of patients was 88%. Results of the Hans algorithm, Choi algorithm and Tally method were interpretable in 98 (90.7%), 95 (87.9%) and 88 (81.5%) of 108 cases, respectively. Inability to assign subtypes was due to suboptimal staining of the TMA (tissue loss or poor staining of an individual core). Using GEP to assign CoO, 42% of cases were classified as GCB, 42% as ABC and 14% were unclassifiable. The sensitivities of the Hans, Choi and Tally approaches to identify the CoO predicted by GEP were 0.83, 0.83, and 0.58 for correctly identifying GCB cases, respectively, and were 0.70, 0.70 and 0.80 for identifying non-GCB cases, respectively. The positive predictive values of the Hans, Choi and Tally approaches were 0.83, 0.83, and 1.0 for GCB and 0.78, 0.78, and 0.89 for non-GCB. As shown in the figure, 5-year overall survival was significantly superior for GCB relative to ABC cases using GEP (100% vs. 58.9%, P < 0.001) and for GCB vs. non-GCB cases for the algorithms of Hans (100% vs. 82.3%, P = 0.0197) and Choi (95.6% vs. 78.0%, P = 0.0482). The Tally method was not predictive of outcome, possibly due to insufficient power (5-year OS 94.4% for GCB vs. 80.7% for non-GCB, P = 0.1725). Similar findings were observed for progression-free survival. CONCLUSIONS: The Hans and Choi algorithms are reasonable methods for identifying PFS and OS differences based on CoO for de novo DLBCL treated with chemoimmunotherapy. The positive predictive value is universally high for all algorithms tested, but the sensitivity of IHC for identifying CoO was fair, particularly for the Tally method. IHC represents a valid biomarker to identify non-GCB cases. Clinical trials of DLBCL that stratify patients by IHC are feasible provided the performance characteristics of the algorithms are taken into consideration during study design. Disclosures: No relevant conflicts of interest to declare.