Статті в журналах з теми "4611 Machine learning"

The increase in the prevalence of cardiovascular diseases (CVDs) specifies the importance of their prediction, the need for accurate risk stratification, preventive and treatment interventions. Large medical databases and technologies for their processing in the form of machine learning algorithms that have appeared in recent years have the potential to improve predictive accuracy and personalize treatment approaches to CVDs. The review examines the application of machine learning in predicting and identifying cardiovascular events. The role of this technology both in the calculation of total cardiovascular risk and in the prediction of individual diseases and events is discussed. We compared the predictive accuracy of current risk scores and various machine learning algorithms. The conditions for using machine learning and developing personalized tactics for managing patients with CVDs are analyzed.

Background: The objectives of this study were to classify patients with serum magnesium derangement on hospital admission into clusters using unsupervised machine learning approach and to evaluate the mortality risks among these distinct clusters. Methods: Consensus cluster analysis was performed based on demographic information, principal diagnoses, comorbidities, and laboratory data in hypomagnesemia (serum magnesium ≤ 1.6 mg/dL) and hypermagnesemia cohorts (serum magnesium ≥ 2.4 mg/dL). Each cluster’s key features were determined using the standardized mean difference. The associations of the clusters with hospital mortality and one-year mortality were assessed. Results: In hypomagnesemia cohort (n = 13,320), consensus cluster analysis identified three clusters. Cluster 1 patients had the highest comorbidity burden and lowest serum magnesium. Cluster 2 patients had the youngest age, lowest comorbidity burden, and highest kidney function. Cluster 3 patients had the oldest age and lowest kidney function. Cluster 1 and cluster 3 were associated with higher hospital and one-year mortality compared to cluster 2. In hypermagnesemia cohort (n = 4671), the analysis identified two clusters. Compared to cluster 1, the key features of cluster 2 included older age, higher comorbidity burden, more hospital admissions primarily due to kidney disease, more acute kidney injury, and lower kidney function. Compared to cluster 1, cluster 2 was associated with higher hospital mortality and one-year mortality. Conclusion: Our cluster analysis identified clinically distinct phenotypes with differing mortality risks in hospitalized patients with dysmagnesemia. Future studies are required to assess the application of this ML consensus clustering approach to care for hospitalized patients with dysmagnesemia.

Abstract BACKGROUND Urine steroid profiles are used in clinical practice for the diagnosis and monitoring of disorders of steroidogenesis and adrenal pathologies. Machine learning (ML) algorithms are powerful computational tools used extensively for the recognition of patterns in large data sets. Here, we investigated the utility of various ML algorithms for the automated biochemical interpretation of urine steroid profiles to support current clinical practices. METHODS Data from 4619 urine steroid profiles processed between June 2012 and October 2016 were retrospectively collected. Of these, 1314 profiles were used to train and test various ML classifiers' abilities to differentiate between “No significant abnormality” and “?Abnormal” profiles. Further classifiers were trained and tested for their ability to predict the specific biochemical interpretation of the profiles. RESULTS The best performing binary classifier could predict the interpretation of No significant abnormality and ?Abnormal profiles with a mean area under the ROC curve of 0.955 (95% CI, 0.949–0.961). In addition, the best performing multiclass classifier could predict the individual abnormal profile interpretation with a mean balanced accuracy of 0.873 (0.865–0.880). CONCLUSIONS Here we have described the application of ML algorithms to the automated interpretation of urine steroid profiles. This provides a proof-of-concept application of ML algorithms to complex clinical laboratory data that has the potential to improve laboratory efficiency in a setting of limited staff resources.

Suicide is a leading cause of death that defies prediction and challenges prevention efforts worldwide. Artificial intelligence (AI) and machine learning (ML) have emerged as a means of investigating large datasets to enhance risk detection. A systematic review of ML investigations evaluating suicidal behaviors was conducted using PubMed/MEDLINE, PsychInfo, Web-of-Science, and EMBASE, employing search strings and MeSH terms relevant to suicide and AI. Databases were supplemented by hand-search techniques and Google Scholar. Inclusion criteria: (1) journal article, available in English, (2) original investigation, (3) employment of AI/ML, (4) evaluation of a suicide risk outcome. N = 594 records were identified based on abstract search, and 25 hand-searched reports. N = 461 reports remained after duplicates were removed, n = 316 were excluded after abstract screening. Of n = 149 full-text articles assessed for eligibility, n = 87 were included for quantitative synthesis, grouped according to suicide behavior outcome. Reports varied widely in methodology and outcomes. Results suggest high levels of risk classification accuracy (>90%) and Area Under the Curve (AUC) in the prediction of suicidal behaviors. We report key findings and central limitations in the use of AI/ML frameworks to guide additional research, which hold the potential to impact suicide on broad scale.

Introduction: Knee injury and Osteoarthritis Outcome Score (KOOS) is a widely used patient-reported outcome measurement to track recovery after ACL surgery. This study focuses on the function of daily living subscale (KOOS ADL), which is calculated based on 17 questions. By employing machine learning to predict KOOS ADL scores, we sought to better understand the relative importance of the survey questions and thereby identify its most critical components as well as questions that do not adequately predict outcomes. Methods: Pre- and post-operative patient reported KOOS ADL survey responses and outcomes scores following ACL surgery were obtained from the Surgical Outcome System data registry(SOS), an international patient-reported outcomes database sponsored and maintained by Arthrex. Patients with missing KOOS ADL survey responses were excluded from the study. Machine learning (ML) algorithms such as Random Forest and Gradient Boosting were used to identify the most critical survey questions that predict KOOS ADL scores with high accuracy. These decision tree-based algorithms predict patient outcomes using several decision rules and thereby determining the relative value of individual questions at predicting patient deficits (e.g., if patients have “Severe” difficulty in ascending stairs, they are more likely to have globally worse scores than those with difficulty with other tasks). Results: 4996 patients were initially identified. Based on compliance with the survey, 2407, 2407, 1817 and 1193 patients records for pre-surgery, 3 month, 6 month and 1 year post-surgery responses respectively underwent further analysis. The dataset consisted of 53.9% males and 46.1% females. Mean age was 29 (range 11 to 70 years). Results from the ML models indicated that by 6 key questions, over 80% of the variance in KOOS ADL scores could be explained instead of standard 17 survey questions (Table 1). Interestingly, the analysis provided similar accuracy at both 6 months and 1 year. Discussion and Conclusion: Most patients have similar functional deficits that can be captured using a simplified version of the KOOS ADL survey. The abbreviated survey would result in a better patient reporting experience while still obtaining quality data. Additional work on predicting post-surgery scores using ML from pre-surgery responses and other patient information would provide valuable insights; however, predicting outcome scores with high accuracy remains challenging. We advocate for novel methods to identify and measure meaningful data to assist with understanding patient outcomes and thereby proving the true value of orthopaedic interventions on functional status. [Table: see text]

ABSTRACT The existing open-cluster membership determination algorithms are either prior dependent on some known parameters of clusters or are not automatable to large samples of clusters. In this paper, we present ml-moc, a new machine-learning-based approach to identify likely members of open clusters using the Gaia DR2 data and no a priori information about cluster parameters. We use the k-nearest neighbour (kNN) algorithm and the Gaussian mixture model (GMM) on high-precision proper motions and parallax measurements from the Gaia DR2 data to determine the membership probabilities of individual sources down to G ∼ 20 mag. To validate the developed method, we apply it to 15 open clusters: M67, NGC 2099, NGC 2141, NGC 2243, NGC 2539, NGC 6253, NGC 6405, NGC 6791, NGC 7044, NGC 7142, NGC 752, Blanco 1, Berkeley 18, IC 4651, and Hyades. These clusters differ in terms of their ages, distances, metallicities, and extinctions and cover a wide parameter space in proper motions and parallaxes with respect to the field population. The extracted members produce clean colour–magnitude diagrams and our astrometric parameters of the clusters are in good agreement with the values derived in previous work. The estimated degree of contamination in the extracted members ranges between 2 ${{\ \rm per\ cent}}$ and 12 ${{\ \rm per\ cent}}$. The results show that ml-moc is a reliable approach to segregate open-cluster members from field stars.

Insights and analysis are only as good as the available data. Data cleaning is one of the most important steps to create quality data decision making. Machine learning (ML) helps deal with data quickly, and to create error-free or limited-error datasets. One of the quality standards for cleaning the data includes handling the missing data, also known as data imputation. This research focuses on the use of machine learning methods to deal with missing data. In particular, we propose a generative adversarial network (GAN) based model called DEGAIN to estimate the missing values in the dataset. We evaluate the performance of the presented method and compare the results with some of the existing methods on publicly available Letter Recognition and SPAM datasets. The Letter dataset consists of 20,000 samples and 16 input features and the SPAM dataset consists of 4601 samples and 57 input features. The results show that the proposed DEGAIN outperforms the existing ones in terms of root mean square error and Frechet inception distance metrics.

Objectives Federated learning (FL) allows multiple institutions to collaboratively develop a machine learning algorithm without sharing their data. Organizations instead share model parameters only, allowing them to benefit from a model built with a larger dataset while maintaining the privacy of their own data. We conducted a systematic review to evaluate the current state of FL in healthcare and discuss the limitations and promise of this technology. Methods We conducted a literature search using PRISMA guidelines. At least two reviewers assessed each study for eligibility and extracted a predetermined set of data. The quality of each study was determined using the TRIPOD guideline and PROBAST tool. Results 13 studies were included in the full systematic review. Most were in the field of oncology (6 of 13; 46.1%), followed by radiology (5 of 13; 38.5%). The majority evaluated imaging results, performed a binary classification prediction task via offline learning (n = 12; 92.3%), and used a centralized topology, aggregation server workflow (n = 10; 76.9%). Most studies were compliant with the major reporting requirements of the TRIPOD guidelines. In all, 6 of 13 (46.2%) of studies were judged at high risk of bias using the PROBAST tool and only 5 studies used publicly available data. Conclusion Federated learning is a growing field in machine learning with many promising uses in healthcare. Few studies have been published to date. Our evaluation found that investigators can do more to address the risk of bias and increase transparency by adding steps for data homogeneity or sharing required metadata and code.

Unilateral corneal indices and topography maps are routinely used in practice, however, although there is consensus that fellow-eye asymmetry can be clinically significant, symmetry studies are limited to local curvature and single-point thickness or elevation measures. To improve our current practices, there is a need to devise algorithms for generating symmetry colormaps, study and categorize their patterns, and develop reference ranges for new global discriminative indices for identifying abnormal corneas. In this work, we test the feasibility of using the fellow eye as the reference surface for studying elevation symmetry throughout the entire corneal surface using 9230 raw Pentacam files from a population-based cohort of 4613 middle-aged adults. The 140 × 140 matrix of anterior elevation data in these files were handled with Python to subtract matrices, create color-coded maps, and engineer features for machine learning. The most common pattern was a monochrome circle (“flat”) denoting excellent mirror symmetry. Other discernible patterns were named “tilt”, “cone”, and “four-leaf”. Clustering was done with different combinations of features and various algorithms using Waikato Environment for Knowledge Analysis (WEKA). Our proposed approach can identify cases that may appear normal in each eye individually but need further testing. This work will be enhanced by including data of posterior elevation, thickness, and common diagnostic indices.

Abstract. Water resources management in Latin America and the Caribbean is particularly threatened by climatic, economic, and political pressures. To assess the region's ability to manage water resources, we conducted an unprecedented literature review of over 20 000 multilingual research articles using machine learning and an understanding of the socio-hydrologic landscape. Results reveal that the region's vulnerability to water-related stresses, and drivers such as climate change, is compounded by research blind spots in niche topics (reservoirs and risk assessment) and subregions (Caribbean nations), as well as by its reliance on an individual country (Brazil). A regional bright spot, Brazil, produces well-rounded water-related research, but its regional dominance suggests that funding cuts there would impede scientifically informed water management in the entire region.

Background In contrast to all other areas of medicine, psychiatry is still nearly entirely reliant on subjective assessments such as patient self-report and clinical observation. The lack of objective information on which to base clinical decisions can contribute to reduced quality of care. Behavioral health clinicians need objective and reliable patient data to support effective targeted interventions. Objective We aimed to investigate whether reliable inferences—psychiatric signs, symptoms, and diagnoses—can be extracted from audiovisual patterns in recorded evaluation interviews of participants with schizophrenia spectrum disorders and bipolar disorder. Methods We obtained audiovisual data from 89 participants (mean age 25.3 years; male: 48/89, 53.9%; female: 41/89, 46.1%): individuals with schizophrenia spectrum disorders (n=41), individuals with bipolar disorder (n=21), and healthy volunteers (n=27). We developed machine learning models based on acoustic and facial movement features extracted from participant interviews to predict diagnoses and detect clinician-coded neuropsychiatric symptoms, and we assessed model performance using area under the receiver operating characteristic curve (AUROC) in 5-fold cross-validation. Results The model successfully differentiated between schizophrenia spectrum disorders and bipolar disorder (AUROC 0.73) when aggregating face and voice features. Facial action units including cheek-raising muscle (AUROC 0.64) and chin-raising muscle (AUROC 0.74) provided the strongest signal for men. Vocal features, such as energy in the frequency band 1 to 4 kHz (AUROC 0.80) and spectral harmonicity (AUROC 0.78), provided the strongest signal for women. Lip corner–pulling muscle signal discriminated between diagnoses for both men (AUROC 0.61) and women (AUROC 0.62). Several psychiatric signs and symptoms were successfully inferred: blunted affect (AUROC 0.81), avolition (AUROC 0.72), lack of vocal inflection (AUROC 0.71), asociality (AUROC 0.63), and worthlessness (AUROC 0.61). Conclusions This study represents advancement in efforts to capitalize on digital data to improve diagnostic assessment and supports the development of a new generation of innovative clinical tools by employing acoustic and facial data analysis.

Bu məqalə biznesin proqnozlaşdırılması prosesi üçün Süni İntellekt tərəfindən dəstəklənən qərar dəstək sistemi (DSS) metodunu təqdim edir. Neyron şəbəkə modeli ilə biznes məlumatlarının proqnozlaşdırılmasının effektivliyində ən yaxşı təlim yanaşması müəyyən edilir. Bu tədqiqat neyron şəbəkələrə və öyrənmə yanaşmalarına əsaslanan birgə proqnozlaşdırma prosesi yaradır. Əlaqə öyrənmə modeli müəyyən edilmiş irəli gizli təbəqə şəbəkəsində istifadə olunur, logistik funksiya isə müvafiq olaraq çıxış və gizli təbəqə ötürmə funksiyası kimi istifadə olunur. Bu model DSS məhsulu­nun istehsalçısı üçün şərti məlumatlar üzərində işləyir. Verilənlər bazasından istifadə etməklə, qrafiklər və hesabatlar əldə etməklə və təhlil aparmaqla proqnoz menecerlərinə kömək edən istifadəçi dostu bir modeldir. Açar sözlər: Qərarlara Dəstək Sistemləri, biznes zəkası, maşın öyrənmə Natig Elkhan Huseynov Supported by artificial intelligence intellectual decision systems Summary This article introduces the Decision Support System (DSS) method supported by Artificial Intelligence for the business forecasting process. The neural network model identifies the best training approach to the effectiveness of business data forecasting. This research creates a collaborative prediction process based on neural networks and learning approaches. The communi­ca­tion learning model is used in a defined forward secret layer network, and the logistics function is used as an output and hidden layer transfer function, respectively. This model works on the conditional data for the manufacturer of the DSS product. It is a user-friendly model that helps forecast managers use databases, obtain graphs and reports, and analyze. Key words: Decision Support Systems, business intelligence, machine learning

Background A small proportion of high-need patients persistently use the bulk of health care services and incur disproportionate costs. Population health management (PHM) programs often refer to these patients as persistent high utilizers (PHUs). Accurate PHU prediction enables PHM programs to better align scarce health care resources with high-need PHUs while generally improving outcomes. While prior research in PHU prediction has shown promise, traditional regression methods used in these studies have yielded limited accuracy. Objective We are seeking to improve PHU predictions with an ensemble approach in a retrospective observational study design using insurance claim records. Methods We defined a PHU as a patient with health care costs in the top 20% of all patients for 4 consecutive 6-month periods. We used 2013 claims data to predict PHU status in next 24 months. Our study population included 165,595 patients in the Johns Hopkins Health Care plan, with 8359 (5.1%) patients identified as PHUs in 2014 and 2015. We assessed the performance of several standalone machine learning methods and then an ensemble approach combining multiple models. Results The candidate ensemble with complement naïve Bayes and random forest layers produced increased sensitivity and positive predictive value (PPV; 49.0% and 50.3%, respectively) compared to logistic regression (46.8% and 46.1%, respectively). Conclusions Our results suggest that ensemble machine learning can improve prediction of care management needs. Improved PPV implies reduced incorrect referral of low-risk patients. With the improved sensitivity/PPV balance of this approach, resources may be directed more efficiently to patients needing them most.

Aspirin resistance (AR) is a pressing problem in current ischemic stroke care. Although the role of genetic variations is widely considered, the data still remain controversial. Our aim was to investigate the contribution of genetic features to laboratory AR measured through platelet aggregation with arachidonic acid (AA) and adenosine diphosphate (ADP) in ischemic stroke patients. A total of 461 patients were enrolled. Platelet aggregation was measured via light transmission aggregometry. Eighteen single-nucleotide polymorphisms (SNPs) in ITGB3, GPIBA, TBXA2R, ITGA2, PLA2G7, HMOX1, PTGS1, PTGS2, ADRA2A, ABCB1 and PEAR1 genes and the intergenic 9p21.3 region were determined using low-density biochips. We found an association of rs1330344 in the PTGS1 gene with AR and AA-induced platelet aggregation. Rs4311994 in ADRA2A gene also affected AA-induced aggregation, and rs4523 in the TBXA2R gene and rs12041331 in the PEAR1 gene influenced ADP-induced aggregation. Furthermore, the effect of rs1062535 in the ITGA2 gene on NIHSS dynamics during 10 days of treatment was found. The best machine learning (ML) model for AR based on clinical and genetic factors was characterized by AUC = 0.665 and F1-score = 0.628. In conclusion, the association study showed that PTGS1, ADRA2A, TBXA2R and PEAR1 polymorphisms may affect laboratory AR. However, the ML model demonstrated the predominant influence of clinical features.

Early detection of patients vulnerable to infections acquired in the hospital environment is a challenge in current health systems given the impact that such infections have on patient mortality and healthcare costs. This work is focused on both the identification of risk factors and the prediction of healthcare-associated infections in intensive-care units by means of machine-learning methods. The aim is to support decision making addressed at reducing the incidence rate of infections. In this field, it is necessary to deal with the problem of building reliable classifiers from imbalanced datasets. We propose a clustering-based undersampling strategy to be used in combination with ensemble classifiers. A comparative study with data from 4616 patients was conducted in order to validate our proposal. We applied several single and ensemble classifiers both to the original dataset and to data preprocessed by means of different resampling methods. The results were analyzed by means of classic and recent metrics specifically designed for imbalanced data classification. They revealed that the proposal is more efficient in comparison with other approaches.

The COVID-19 pandemic shed light on the need for quick diagnosis tools in healthcare, leading to the development of several algorithmic models for disease detection. Though these models are relatively easy to build, their training requires a lot of data, storage, and resources, which may not be available for use by medical institutions or could be beyond the skillset of the people who most need these tools. This paper describes a data analysis and machine learning platform that takes advantage of high-performance computing infrastructure for medical diagnosis support applications. This platform is validated by re-training a previously published deep learning model (COVID-Net) on new data, where it is shown that the performance of the model is improved through large-scale hyperparameter optimisation that uncovered optimal training parameter combinations. The per-class accuracy of the model, especially for COVID-19 and pneumonia, is higher when using the tuned hyperparameters (healthy: 96.5%; pneumonia: 61.5%; COVID-19: 78.9%) as opposed to parameters chosen through traditional methods (healthy: 93.6%; pneumonia: 46.1%; COVID-19: 76.3%). Furthermore, training speed-up analysis shows a major decrease in training time as resources increase, from 207 min using 1 node to 54 min when distributed over 32 nodes, but highlights the presence of a cut-off point where the communication overhead begins to affect performance. The developed platform is intended to provide the medical field with a technical environment for developing novel portable artificial-intelligence-based tools for diagnosis support.

Models, methods and algorithms for cyber-social computing and machine learning implies the use of the metric of similarity – difference of unitary coded information for processing big data in order to generate adequate actuator signals for controlling cyber-social critical systems. A set-theoretic method of data search is being developed based on the similarity – difference of the frequency parameters of primitive elements, which makes it possible to determine the similarity of objects, the strategy of transforming one object into another, and also to identify the level of common interests, conflicts. Computational architectures of cyber-social computing and metric search for key data are being created. The definitions of the fundamental concepts in the field of computing are given on the basis of metric relations between interacting processes and phenomena. A software application is proposed for calculating the similarity-differences of objects based on the formation of vectors of frequencies of two sets of primitive data. A high level of correlation of the application results with the well-known system for determining plagiarism is shown. Key words: computing, cybersocial computing, decision making, unitary data codes, similarity – difference, data retrieval, plagiarism

In this study, efforts are created to develop a quantitative structure–activity relationship (QSAR)-based model, which are used for the prediction of toxicities to reduce testing in animals, time, and money in the early stages of drug development. An efficient machine learning model is developed to predict the toxicity of those drug molecules which binds to the androgen receptor (AR). Toxicity prediction is performed in terms of their activity, activity score, potency, and efficacy by using various physicochemical properties. A multilevel ensemble model is proposed, where its first level is performed ensemble-based classification of activity, and the second level is performed ensemble-based regression of activity score, potency, and efficacy of only those drug molecules which have been found active during the classification level. The AR dataset has 10,273 drug molecules where 461 are active, and 9812 are inactive, and each drug molecule has 1444 features. Therefore, our dataset is highly imbalanced having a very large number of features. Initially, we performed feature selection then the class imbalance problem is resolved. The [Formula: see text]-fold cross-validation is accomplished to measure the consistency of the model. Finally, our proposed multilevel ensemble model has been validated and compared with some existing models.

AbstractRecurrent neural networks (RNN) have been successfully applied to various sequential decision-making tasks, natural language processing applications, and time-series predictions. Such networks are usually trained through back-propagation through time (BPTT) which is prohibitively expensive, especially when the length of the time dependencies and the number of hidden neurons increase. To reduce the training time, extreme learning machines (ELMs) have been recently applied to RNN training, reaching a 99% speedup on some applications. Due to its non-iterative nature, ELM training, when parallelized, has the potential to reach higher speedups than BPTT.In this work, we present Opt-PR-ELM, an optimized parallel RNN training algorithm based on ELM that takes advantage of the GPU shared memory and of parallel QR factorization algorithms to efficiently reach optimal solutions. The theoretical analysis of the proposed algorithm is presented on six RNN architectures, including LSTM and GRU, and its performance is empirically tested on ten time-series prediction applications. Opt-PR-ELM is shown to reach up to 461 times speedup over its sequential counterpart and to require up to 20x less time to train than parallel BPTT. Such high speedups over new generation CPUs are extremely crucial in real-time applications and IoT environments.

162 Background: PARP inhibitors (PARPi) provide significant clinical benefit for men with aPC with BRCA 1 and BRCA 2 mutations. However, in clinical trials, pts with BRCA1 mutations appeared to derive less benefit than pts with BRCA2 (De Bono et al., 2020). Probabilistic Graphical Models (PGMs) are artificial intelligence (AI) algorithms that capture multivariate, multi-level dependencies in complex patterns in large datasets while retaining human interpretability. We hypothesize that PGMs can reveal variants in BRCA1 and 2 that co-segregate with other known pathogenic variants and may explain the difference in response to PARPi therapy. Methods: Multilevel gene interdependencies between BRCA1 or BRCA2 were assessed using a Bayesian Network (BN) machine learning approach and Fisher’s exact test. CGP was performed by a validated cfDNA NGS panel that sequenced 74 clinically relevant cancer genes (Guardant360, Redwood City, CA). Only variants of known significance and those of unknown significance with a pathogenic REVEL score were included in the analysis. Results: Of 4671 men with aPC undergoing cfDNA CGP, 1248 men with somatic mutations in BRCA1, BRCA2, ATM, or combinations of the three were included in the analysis. The Bayesian network analysis demonstrated positive interdependencies between pathogenic variants in BRCA1 and 7 other genes. A positive interdependency between BRCA2 and 2 genes was present (table). ATM displayed negative interdependency with both BRCA 1 and 2. Conclusions: Our results demonstrate a decreased association of BRCA2 versus BRCA1 with known or predicted pathogenic variants at other loci. This may explain increased sensitivity of aPC with BRCA2 mutations to PARPi due to fewer concurrent resistance pathways. For example, alteration of ERBB2, which segregates strongly with BRCA1, is known to induce tumor progression and invasion in aPC and is associated with castration-resistance. These hypothesis-generating data reveal differential genomic signatures associated with BRCA1 as compared to BRCA2 and may inform development of future combinatorial treatment regimens for these pts. [Table: see text]

Buruli ulcer (BU) is a disabling and stigmatising neglected tropical disease (NTD). Its distribution and burden are unknown because of underdiagnosis and underreporting. It is caused by Mycobacterium ulcerans, an environmental pathogen whose environmental niche and transmission routes are not fully understood. The main control strategy is active surveillance to promote early treatment and thus limit morbidity, but these activities are mostly restricted to well-known endemic areas. A better understanding of environmental suitability for the bacterium and disease could inform targeted surveillance, and advance understanding of the ecology and burden of BU. We used previously compiled point-level datasets of BU and M. ulcerans occurrence, evidence for BU occurrence within national and sub-national areas, and a suite of relevant environmental covariates in a distribution modelling framework. We fitted relationships between BU and M. ulcerans occurrence and environmental predictors by applying regression and machine learning based algorithms, combined in an ensemble model to characterise the optimal ecological niche for the disease and bacterium across Africa at a resolution of 5km x 5km. Proximity to waterbodies was the strongest predictor of suitability for BU, followed potential evapotranspiration. The strongest predictors of suitability for M. ulcerans were deforestation and potential evapotranspiration. We identified patchy foci of suitability throughout West and Central Africa, including areas with no previous evidence of the disease. Predicted suitability for M. ulcerans was wider but overlapping with that of BU. The estimated population living in areas predicted suitable for the bacterium and disease was 46.1 million. These maps could be used to inform burden estimations and case searches which would generate a more complete understanding of the spatial distribution of BU in Africa, and may guide control programmes to identify cases beyond the well-known endemic areas.

Abstract Background: Relapses after allo-HSCT remain an unsolved problem in Ph-positive acute lymphoblastic leukemia (ALL) patients, especially in patients with detectable BCR/ABL levels prior to allogeneic stem cell transplantation (allo-HSCT). Majority of centers make efforts to manage with it by preemptive or prophylactic administration of TKIs after allo-HSCT. However, the risk factors in this setting are yet to be determined. Moreover, persistence of minimal residual disease (MRD) after induction plays a critical role in relapse probability, but its fluctuation after transplant in the context of TKIs application is still a question. The aim of this study is to apply modern machine-learning approaches for building relapse predicting models and testing variable importance. Patients and methods: This study analyses the data in retrospective cohort of 74 Ph-positive ALL patients with posttransplant BCR/ABL expression levels available at different time intervals with median age of 30,5 years (range, 18-55), in whom allo-HSCT were performed between 2008 and 2021. Patient characteristics and features of the disease are presented in Table 1. For the analysis, all TKIs were divided into 2 groups TKIs1 - imatinib, TKIs2 - other TKIs, regardless of generation. Machine learning models were developed using R programming language and Caret package. The dependent variable was relapse after prediction moment, the following independent variable features were used: time intervals between allo-HSCT and prediction moment, BCR/ABL expression level at prediction moment, therapy after allo-HSCT (TKIs1 or TKIs2), the highest BCR/ABL expression level before prediction moment, chronic «graft-versus-host» disease (GvHD) before prediction for the patients, who reached D+100 after allo-HSCT. Results: At the time of analysis median follow-up was 26 months (range, 1-116). 5-year OS and EFS were 67,1% (95% CI 54,2 - 80) and 55,1% (95% CI 42,5 - 68,3), respectively, whereas 5-year cumulative incidence of relapse was 46,1% (95% CI 26,2 - 66) for MRD-positive prior to allo-HSCT patients, compared to 24,1% (95% CI 6,9-41,3) for MRD-negative patients (р=0,04). The resulting ROC-curve for 3 most effective classification models is given in figure 1A. As one can see Gradient Boosting Method (GBM) provided maximal AUC score (0.88). For this a decision-making threshold may be adjusted for obtaining Specificity = 0.75, Sensitivity = 0.88. Variable importance plot (figure 1B) showed that the highest BCR/ABL level, prediction moment, chronic GvHD and current BCR/ABL level have the strongest importance, while preceding therapy turned out to be less significant factor. In fact, exclusion of TKIs type almost did not affect the ROC curves. In GBM model AUC still demonstrated appropriate level of 0.87. When analyzing the model accuracy, false-negative rate (FNR) and false-positive rate (FPR) errors were estimated for the three ranges of prediction moments (figure 1C). It was shown that after D+100 both error rates don't exceed 22%, while before D+100 the model fails to make accurate prediction based on the independent variables used. Conclusions: Using independent factors, we built the model for both bone marrow and extramedullary relapses prediction after allo-HSCT with high sensitivity and reasonable specificity based on the relatively small group of patients. According to the predicting model, we confirm, that a high level of BCR/ABL at any time point after allo-HSCT is the most significant predictor of relapse, which may indicate the presence of subclones of cells that cause resistance to chemotherapy or TKIs. The BCR/ABL MRD levels before D+100 have low predictive ability for early relapses, which may develop rapidly without MRD phase. At the same time, BCR/ABL levels relatively accurate predict relapses after D+100 with ongoing TKI prophylaxis. The absence of chronic GvHD is an important independent factor influencing the risk of relapse. This means that for high-risk patients, approaches to induce a «graft-versus-leukemia» effect should be considered. In addition, prophylactic use of monoclonal antibodies in combination with TKIs may be considered to prevent relapse in the absence of chronic GvHD in high-risk patients. In summary, we believe that verification of this model on a multicenter group of patients is required to facilitate its clinical application. Figure 1 Figure 1. Disclosures Kulagin: Pfizer: Speakers Bureau; Johnson & Johnson: Speakers Bureau; Alexion: Research Funding; Roche: Speakers Bureau; Novartis: Speakers Bureau; Generium: Speakers Bureau; Sanofi: Speakers Bureau; Apellis: Research Funding; Biocad: Research Funding; X4 Pharmaceuticals: Research Funding.

Abstract Background: Metastatic breast cancer (MBC) clinical outcome is associated with heterogeneity in site, time of recurrence, treatment response, and disease outcome that is partially subtype dependent. The enumeration of CTCs can independently stratify Stage IV disease. We previously showed the feasibility of predicting CTCs stratification (pred_CTCs) through machine learning. The MONARCH 2 study (M2) showed the efficacy of abemaciclib (Abema), a cyclin dependent kinase 4 & 6 inhibitor (CDK4/6i), and fulvestrant in hormone-receptor positive, HER2 negative (luminal-like) MBC. The aim of this analysis was to assess the potential utility of CTCs stratification in luminal-like MBC treated with CDK4/6i utilizing a dataset from a randomized phase 3 study. Methods: Pred_CTCs were computed in the M2 (NCT02107703) randomized, phase 3 trial through a K nearest neighbor (KNN) algorithm trained on a 2,436 MBC patients pooled dataset from EPAC (European Pooled Analysis of CTCs) and the MD Anderson Cancer Center to identify patients likely to have CTCs ≥ 5/7.5ml blood (pred_Stage IVaggressive vs pred_Stage IVindolent) (Cristofanilli et al. 2019). The association of Pred_CTCs with progression-free survival (PFS) and overall survival (OS) in the M2 trial was explored using a univariate analysis and then a stepwise Cox regression to evaluate its value in the presence of prognostic factors previously identified in the MONARCH2 and 3 cohorts (i.e., ECOG performance status (PS), tumor grade, progesterone receptor status, liver and bone only involvement) (Di Leo A et al. 2018). The differential impact of Abema on OS was then explored through analysis of subgroups. Results: M2 enrolled 669 women with endocrine resistant luminal-like MBC, 644 were eligible for the KNN model. Patients classified as pred_Stage IVaggressive and pred_Stage IVindolent were 183 (28%) and 461 (72%), respectively. After univariable analysis, the prognostic impact of pred_CTCs was observed for both PFS and OS (HR=1.39 95%CI 1.14 - 1.69, P = 0.001 and HR=1.67, 95%CI 1.33 - 2.10 P < 0.001, respectively). Median OS was 48 and 32 months for pred_Stage IVindolent and pred_Stage IVaggressive, respectively. After stepwise Cox regression, variables associated with PFS were pred_CTCs, ECOG PS, liver and bone only disease (see Table 1). Features associated with OS were pred_CTCs, ECOG PS, and bone only disease. Subgroup analysis of Abema treatment effect on OS showed HR=0.68 (95%CI 0.52 - 0.89) and HR=0.89 (95%CI 0.60 - 1.35) in the pred_Stage IVindolent and pred_Stage IVaggressive subgroups, respectively Conclusions: This study represents the first analysis of clinical outcome using predicted modeling of CTCs for stage IV disease stratification. These hypothesis-generating results illustrate the need to expand resistance biomarkers evaluation in combination with CTCs stratification for improved biomarker-driven drug development. PFSHR95%CIP valuepred_CTCStage IVindolent1Stage IVaggressive1.321.02 - 1.710.034ECOG PS0111.441.17 - 1.770.001Bone onlyNo1Yes0.710.54 - 0.930.014LiverNo1Yes1.371.04 - 1.790.024OSpred_CTCStage IVindolent1Stage IVaggressive1.671.2 - 2.18< 0.001ECOG PS0111.781.39 - 2.30< 0.001Bone onlyNo1Yes0.590.43 - 0.800.001 Citation Format: Lorenzo Gerratana, Masha Kocherginsky, Andrew A Davis, Paolo D’Amico, Carolina Reduzzi, Qiang Zhang, Fabio Puglisi, Massimo Cristofanilli. Stage IV stratification using circulating tumor cells (CTCs) enumeration modeling: A retrospective analysis of the MONARCH 2 study [abstract]. In: Proceedings of the 2021 San Antonio Breast Cancer Symposium; 2021 Dec 7-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2022;82(4 Suppl):Abstract nr P2-02-01.

e4912046This scoping exploratory review was aimed at analyzing the challenges that the so-called post-truth world represents for teaching in Ibero-Latin American higher education. With the increased access to online information media and social networks, netizens are increasingly exposed and may be more vulnerable to false or misleading information that seeks to generate action from emotions rather than reason (GOSWAMI, 2017, Chronicle of Higher Education). The reference search was carried out in the databases of SciELO and La Referencia, from which 26 titles out of 196 were selected. Combinations of terms such as social media, post-truth, fake news, fact-checking, education, higher education, university, teaching, critical thinking, and freedom of expression were used, with the Boolean “Y” connector. The analysis of the references resulted in six thematic categories: main concepts; realms of fake news; news verification initiatives and methods; theoretical analysis and its relationship with education; studies on the factors, perception and credibility of fake news; and addressing misinformation in higher education. The discussion presents the draft of a proposed pedagogical model to be used in higher education and to address misinformation. Includes: critical thinking habits, democratic dialogue, intellectual skepticism, research skills, use of reliable sources of information, and analysis from multiple perspectives.ResumoEsta revisão exploratória de escopo teve como objetivo analisar os desafios que o chamado mundo pós-verdade representa para o ensino na educação superior ibero-americana. Com o aumento do acesso às mídias de informação online e redes sociais, os internautas estão cada vez mais expostos e podem ficar mais vulneráveis a informações falsas ou enganosas que buscam gerar ações a partir de emoções ao invés da razão (GOSWAMI, 2017, Chronicle of Higher Education). A busca das referências foi realizada nas bases de dados SciELO e La Referencia, das quais foram selecionados 26 títulos em 196. Combinações de termos como mídia social, pós-verdade, notícias falsas, checagem de fatos, educação, ensino superior, universidade, ensino, pensamento crítico e liberdade de expressão foram usadas, com o conector booleano “Y”. A análise das referências resultou em seis categorias temáticas: conceitos principais; escopos de notícias falsas; iniciativas e métodos de verificação de notícias; análise teórica e sua relação com a educação; estudos sobre os fatores, percepção e credibilidade das notícias falsas; e aproximação a desinformação no ensino superior. A discussão apresenta o esboço de uma proposta de modelo pedagógico para ser usado no ensino superior e para lidar com a desinformação. Inclui: hábitos de pensamento crítico, diálogo democrático, ceticismo intelectual, habilidades de pesquisa, uso de fontes confiáveis de informação e análise de múltiplas perspectivas.ResumenEsta revisión exploratoria de alcance tuvo como fin analizar los desafíos que para la enseñanza en la educación superior iberoamericana representa lo que se denomina el mundo posfactual (post-truth). Con el incrementado acceso a medios de información en línea y las redes sociales, los cibernautas están cada vez más expuestos y pueden ser más vulnerables a información falsa o engañosa que busca generar acción a partir de las emociones antes que la razón (GOSWAMI, 2017, Chronicle of Higher Education). La búsqueda de referencias se efectuó en las bases de datos de SciELO y La Referencia, de la cual se seleccionaron 26 títulos de 196. Se usaron combinaciones de términos como redes sociales, posverdad, noticias falsas, verificación de hechos, educación, educación superior, universidad, enseñanza, pensamiento crítico y libertad de expresión, con el conector booleano “Y”. El análisis de las referencias dio como resultado seis categorías temáticas: conceptos principales; ámbitos de las noticias falsas; iniciativas y métodos de verificación de noticias; análisis teóricos y su relación con la educación; estudios sobre factores, percepción y credibilidad de las noticias falsas; y abordaje de la desinformación en la educación superior. En la discusión se presenta el borrador de un modelo pedagógico propuesto para ser utilizado en la educación superior y abordar la desinformación. Incluye: hábitos de pensamiento crítico, diálogo democrático, escepticismo intelectual, habilidades de investigación, uso de fuentes confiables de información y análisis de múltiples perspectivas.Palavras-chave: Ensino Superior, Modelo Pedagógico, Mundo Pós-Factual.Keywords: Higher Education, Pedagogical Model, Postfactual World.Palabras clave: Educación Superior, Modelo Pedagógico, Mundo Posfactual.ReferencesAGUIRRE, Juan Carlos; JARAMILLO, Luis Guillermo. La ciencia entre el objetivismo y el construccionismo. Cinta Moebio, v. 38, 2010, 72-90.AGUADO LÓPEZ, Eduardo; ROGEL SALAZAR, Rosario; GARDUÑO OROPEZA, Gustavo; et.al. Redalyc: una alternativa a las asimetrías en la distribución del conocimiento científico. Ciencia, Docencia y Tecnología, v. XIX n. 37, 2008, p. 11-30.ALPERÍN, Juan Pablo; BABINI, Dominique; FISCHMAN, Gustavo (editores). Open access indicators and scholarly communications in Latin America. Buenos Aires: CLACSO, UNESCO, FLACSO Brasil, PKP, SciELO, RedALyC, 2014. Disponível em: http://microblogging.infodocs.eu/wp-content/uploads/2015/08/alperin2014.pdf. Acesso em: 4 de outubro de 2020.ALTBACH, Philip G.; DE WIT, Hans. Nacionalismo: ¿El fin de la internacionalización de la educación? Nexos. 8 mar 2017. Disponível em: https://educacion.nexos.com.mx/?p=480. Acesso em: 6 de outubro de 2020.ÁLVAREZ RUFS, Manuel. Estado del arte: Posverdad y fakenews (tesis de maestría). Madrid: Universidad Nacional de Educación a Distancia (UNED), 2018. Disponível em: http://e-spacio.uned.es/fez/view/bibliuned:masterComEdred-Malvarez. Acesso em: 30 de setembro de 2020.AMARAL FILHO, Nemézio. Tecnologias e a crise da democracia: desafios à práctica e ao ensino do Jornalismo no Brasil. Correspondencias Análisis. n. 10, 2019. Disponível em: https://doi.org/10.24265/cian.2019.n10.02. Acesso em: 28 de setembro de 2020.ARENDT, Hannah. Los orígenes del totalitarismo. Madrid: Santillana, 1998.BACON, Chris C. Appropriated literacies: the paradox of critical literacies, policies, and methodologies in a post-truth era. Education Policy Analysis Archives, v. 26, n. 147, 18 nov. 2018. Disponível em: http://dx.doi.org/10.14507/epaa.26.3377. Acesso em: 10 de outubro de 2020.CARLSON, Scott. How real-world learning could help people compete with machines. The Chronicle of Higher Education, 20 nov. 2017. Disponível em: https://www-chronicle-com.pitt.idm.oclc.org/article/How-Real-World-Learning-Could/241811. Acesso em: 2 de outubro de 2020.CATALINA-GARCÍA, Beatriz; SOUSA, Jorge Pedro; SOUSA, Li-Chang Shuen Cristina Silva. Consumo de noticias y percepción de fake news entre estudiantes de Comunicación de Brasil, España y Portugal. Revista de Comunicación, v. 18, n. 2, 2019, p. 93-115. Disponível em: https://dx.doi.org/10.26441/rc18.2-2019-a5. Acesso em: 8 de outubro de 2020.DAVID, Helena Maria Scherlowski Leal; MARTÍNEZ-RIERA, José Ramón. Fake news and small truths: a reflection on the political competence of nurses. Texto Contexto - Enfermagem, v. 29, 2020, e20190224. Disponível em: https://dx.doi.org/10.1590/1980-265x-tce-2019-0224. Acesso em: 2 de outubro de 2020.DE WIT, Hans; JARAMILLO, Isabel Christina; GACEL-ÁVILA, Jocelyne; KNIGHT, Jane. Higher education in Latin America. The international dimension. Washington, DC: The World Bank, 2005.DELGADO, Jorge Enrique. Journal publication in Chile, Colombia, and Venezuela: University responses to global, regional, and national pressures and tensions (doctoral dissertation). Pittsburgh, PA: University of Pittsburgh, School of Education, Department of Administrative and Policy Studies, 2011. Disponível em: http://d-scholarship.pitt.edu/9049/. Acesso em: 4 de outubro de 2020.DELMAZO, Caroline; VALENTE, Jonas C. L. Fake news nas redes sociais online: propagação e reações à desinformação em busca de cliques. Media Jornalismo, v. 18, n. 32, 2018, p. 155-169. Disponível em: http://www.scielo.mec.pt/scielo.php?script=sci_arttextpid=S2183-54622018000100012lng=pttlng=pt. Acesso em: 26 de setembro de 2020.DOMINGUES, Vanessa dos Reis. Ensino da história do tempo presente na era das redes sociais (tesis de maestria). Porto Alegre: Universidade Federal do Rio Grande do Sul, 2018. Disponível em: http://hdl.handle.net/10183/197053. Acesso em: 20 de setembro de 2020 .DUFFY, Eric. Does college prepare students for the real world? Quora, 9 sep. 2017. Disponível em: https://www.forbes.com/sites/quora/2017/09/09/does-college-prepare-students-for-the-real-world/#7d1c40fb42df. Acesso em: 2 de outubro de 2020EDMANS, Alex. What to trust in a post-truth world (video). TEDxLondonBusinessSchool, may 2017. Disponível em: https://www.ted.com/talks/. Acesso em: 4 de outubro de 2020.FERNÁNDEZ-SÁNCHEZ, H.; KING, K.; ENRÍQUEZ-HERNÁNDEZ, C. B. Revisiones sistemáticas exploratorias como metodología para la síntesis del conocimiento científico. Enfermería Universitaria, v. 17, n. 1, 2020, p. 88-94. Disponível em: https://doi.org/10.22201/eneo.23958421e.2020.1.697. Acesso em: 4 de outubro de 2020.FERREIRA, Alexandre; CARVALHO, Tiago; ANDALÓ, Fernanda; ROCHA, Anderson. Counteracting the contemporaneous proliferation of digital forgeries and fake news. Anais de Academia Brasileira de Ciências, v. 91, suppl. 1, 2019, e20180149. Disponível em: https://doi.org/10.1590/0001-3765201820180149. Acesso em: 10 de outubro de 2020.GABRIEL, Deborah. Pedagogies of social justice and cultural democracy in media higher education. Media Education Research Journal, v. 8, n. 1, 2017, p. 35-48.GARMAN, Noreen B. Challenge in education and society coursework: walking the path of social justice and democracy through dialogue. A pedagogical trope. Pittsburgh, PA: University of Pittsburgh, jan 2007.GOMES, Sheila Freitas; PENNA, Juliana Coelho Braga de Oliveira. ARROIO, Agnaldo. Fake news científicas: percepção, persuasão e letramento. Ciência Educação (Bauru), v. 26, e20018, 2020. Disponível em: https://doi.org/10.1590/1516-731320200018. Acesso em: 12 de outubro de 2020.GOSWAMI, Ranjit. The role of universities in the post-truth era. The Chronicle of Higher Education, 31 mar. 2017. Disponível em: https://www.universityworldnews.com/post.php?story=20170327230152935. Acesso em: 28 de setembro de 2020.GUIRAO GORIS, Silamani J. Adolf. Utilidad y tipos de revisión de literatura. Ene Revista de Enfermería, v. 9, n. 2, 2015. Disponível em: https://dx.doi.org/10.4321/S1988-348X2015000200002. Acesso em: 2 de outubro de 2020.HAMEL, Rainer Enrique. La riqueza y la validez de las lenguas indígenas en el siglo XXI. En: CLACSO (editor). Celebrando las lenguas originarias de América. Buenos Aires: CLACSO, 2020. Disponível em: http://lenguasindigenas.clacso.org/Lenguas_Indigenas_PDF.pdf. Acesso em: 20 de outubro de 2020.HAN, Jialing; DELGADO, Jorge Enrique; XIANG, Xin; et.al. Education of migrant children: a portrait of seven countries with comparative analysis. In: HAN, Jialing (editor). A multi-country study on the education of migrant children. Beijing, China: 21st Century Education Research Institute, Qatar Foundation, nov. 2017, p. 1-5.Iniciativa de las Naciones Unidas para el Aprendizaje sobre el Cambio Climático (UN CC:LEARN). ¿Cómo las universidades pueden tomar en cuenta el cambio climático? Ginebra, Suiza: Instituto de las Naciones Unidas para Formación Profesional e Investigaciones (UNITAR), 14 sep. 2018. Disponível em: https://www.uncclearn.org/es/noticias/como-las-universidades-pueden-tomar-en-cuenta-el-cambio-climatico. Acesso em: 4 de outubro de 2020.IRETON, Cherilyn; POSETTI, Julie. Journalism, fake news disinformation: handbook for journalism education and training. Paris: UNESCO, 2018.JIMÉNEZ I HERNANDO, Albert. La prensa como generador de pensamiento crítico (tesis de maestría). Pamplona: Universidad Pública de Navarra, 2020.KOONCE, Glenn L. Are truly democratic classrooms possible? In: Glenn L. Koonce, Taking sides. Clashing vies on educational issues, 8th edition. McGraw-Hill: 2014, p. 79-91.LÓPEZ BORRULL, Alexandre; VIVES GRÀCIA, Josep; BADELL GUIJARRO, Joan Isidre. Fake news, ¿Amenaza u oportunidad para los profesionales de la información y la documentación? El Profesional de la Información, v. 27, n. 6, 2018, p. 1346-1356. Disponível em: https://doi.org/10.3145/epi.2018.nov.17. Acesso em: 4 de outubro de 2020.LOUREIRO, Robson; GONÇALVES, Emerson Campos. (Semi)formação no contexto das fake news e da pós-verdade na sociedade excitada - de Adorno a Türcke. Educação em Revista, v. 37, e225778, 2021. Disponível em: https://doi.org/10.1590/0102-4698225778. Acesso em: 2 de outubro de 2020.MARTÍNEZ-CARDAMA, Sara; ALGORA-CANCHO, Laura. Lucha contra la desinformación desde las bibliotecas universitarias. El Profesional de la Información, v. 28, n. 4, 2019, 3280412. Disponível em: https://doi.org/10.3145/epi.2019.jul.12. Acesso em: 26 de setembro de 2020.MARTÍNEZ HERNÁNDEZ, Diego; LÓPEZ, Beliji Lileth; MANCO VEGA, Alejandra; ALIAGA, Francisco M.; DELGADO, Jorge Henrique; TEJADA-GÓMEZ, María-Alejandra; ROMERO, Cristina. Acceso, uso y publicación en revistas científicas entre los investigadores en ciencias sociales de Latinoamérica. 2014. Disponível em: http://dx.doi.org/10.6084/m9.figshare.1041561. Acesso em: 20 de setembro de 2020.MCMURTRIE, Beth. Can the lecture be saved? The Chronicle of Higher Education, 3 oct. 2019. Disponível em: https://www-chronicle-com.pitt.idm.oclc.org/article/Can-the-Lecture-Be-Saved-/247268. Acesso em: 28 de setembro de 2020.MENDIGUREN, Terese; PÉREZ DASILVA, Jesús; MESO AYERDI, Koldobika. Actitud ante las Fake News: Estudio del caso de los estudiantes de la Universidad del País Vasco. Revista de Comunicación, v. 19, n. 1, 2020, p. 171-184. Disponível em: https://dx.doi.org/10.26441/rc19.1-2020-a10. Acesso em: 12 de outubro de 2020.MOLLIS, Marcela. Geopolítica del saber: biografías recientes de las universidades latinoamericanas. En: VESSURI, Hebe (editora). Universidad e investigación científica. Buenos Aires: CLACSO, nov. 2006.MORENO-FLEITAS, Olga Elizabeth. La divulgación de la información en la encrucijada de la crisis del COVID-19 en Paraguay. Reacciones y trasmisión de datos falsos y científicos a través de las redes sociales y los medios masivos. Revista de la Sociedad Científica del Paraguay, v. 25, n. 1, 2020, p. 58-85. Disponível em: https://dx.doi.org/10.32480/rscp.2020-25-1.58-85. Acesso em: 12 de outubro de 2020.MUÑOZ, Manuel Ramiro. Pertinencia y nuevos roles de la educación superior en la región. En: TÜNNERMANN BERNHEIM, Carlos (editor). La educación superior en América Latina y el Caribe: diez años después de la conferencia mundial de 1998. Cali, Colombia: IESALC-UNESCO, Pontificia Universidad Javeriana, 2008, p. 166-198.MURIEL-TORRADO, Enrique; PEREIRA, Danielle Borges. Correlations between the concepts of disinformation and Fogg’s Behavior Model. Transinformação, v. 32, 2020, e200026. Disponível em: https://doi.org/10.1590/2318-0889202032e200026. Acesso em: 14 de outubro de 2020.NOAIN SÁNCHEZ, A. Periodismo de confirmación vs. desinformación: Verificado18 y las elecciones mexicanas de 2018. Ámbitos. Revista Internacional de Comunicación. V. 43, n. 1, 2019, p. 95-114. Disponível em: https://dx.doi.org/10.12795/Ambitos.2019.i43.05. Acesso em: 2 de outubro de 2020.OJEDA COPA, Alex; PEREDO RODRÍGUEZ, Valeria. Convergencia entre desinformación política y social en el conflicto electoral de 2019 en Bolivia. Temas Sociales. N. 46, 2020, p. 98-126. Disponível em: http://www.scielo.org.bo/scielo.php?script=sci_arttextpid=S0040-29152020000100005lng=estlng=es. Acesso em: 3 de dezembro de 2020.ORELLANA BENADO, M. E. Fabricando "verdades", ocultando la historia y "haciendo" universidad. Atenea (Concepción), n. 522, 2020. p. 307-314. Disponível em: https://dx.doi.org/10.29393/at522-110fvmo10110. Acesso em: 3 de dezembro de 2020.OTERO, Vanessa. Media Bias Chart ® 5.1. Lafayette, CO: Ad Fontes Media, 2020. Disponível em: https://www.adfontesmedia.com/?v=402f03a963ba. Acesso em: 3 de dezembro de 2020.PANGRAZIO, Luci. What’s new about ‘fake news’? Critical digital literacies in an era of fake news, post-truth and clickbait. Páginas de Educación, v. 11, n. 1, 2018, p. 6-22. Disponível em: https://dx.doi.org/10.22235/pe.v11i1.1551. Acesso em: 28 de setembro de 2020.POWELL, Justin J. W.; FERNANDEZ, Frank; CRIST, John T.; et.al. Introduction: the worldwide triumph of the research university and globalizing science. En: POWELL, Justin J. W.; FERNANDEZ, Frank; BAKER, David P. (editors). The century of science: the global triumph of the research university. Bingley, UK: Emerald, 2017, p. 1-36.PROCON.ORG. Home (website). Santa Mónica, CA: ProCon.org, 2020. Disponível em: https://www.procon.org/. Acesso em: 3 de dezembro de 2020.Registry of Open Access Repository Mandates and Policies (ROARMAP). Home (internet). Southampton: University of Southampton, School of Electronics and Computer Science, 2020. Disponível em: http://roarmap.eprints.org/. Acesso em: 3 de dezembro de 2020.RIPOLL, Leonardo; CANTO, Fábio Lorensi do. Fake news going viral: legal responsibility on the dissemination of misinformation. Revista Brasileira de Biblioteconomia e Documentação, v. 15, 2019. Disponível em: https://rbbd.febab.org.br/rbbd/article/view/1364. Acesso em: 2 de outubro de 2020.RODRIGUES, Theófilo; FERREIRA, Daniel. Estratégias digitais dos populismos de esquerda e de direita: Brasil e Espanha em perspectiva comparada. Trabalhos em Linguística Aplicada, v. 59, n. 2, 2020, p. 1070-1086. Disponível em: https://dx.doi.org/10.1590/01031813715921620200520. Acesso em: 3 de dezembro de 2020.RODRÍGUEZ PÉREZ, Carlos. Una reflexión sobre la epistemología del fact-checking journalism: retos y dilemas. Revista de Comunicación, v. 19, n. 1, 2020, p. 243-258. Disponível em: https://dx.doi.org/10.26441/rc19.1-2020-a14. Acesso em: 3 de dezembro de 2020.SAFORCADA, Fernanda; ATAIRO, Daniela; TROTTA, Lucía; et.al. Tendencias de privatización y mercantilización de la universidad en América Latina. Los casos de Argentina, Chile, Perú y República Dominicana. Buenos Aires: Instituto de Estudios y Capacitación - CONADU, 2019.SANTOS, Gustavo Ferreira. Social media, disinformation, and regulation of the electoral process: a study based on 2018 Brazilian election experience. Revista de Investigações Constitucionais, v. 7, n. 2, 2020, p. 429-449. Disponível em: https://doi.org/10.5380/rinc.v7i2.71057. Acesso em: 5 de dezembro de 2020.SEKULLICH, Daniel. Science struggling against fake news and fact deniers. University World News, 19 jun. 2019. Disponível em: https://www.universityworldnews.com/post.php?story=20190619112503915. Acesso em: 28 de setembro de 2020.STEPHENSON, Grace Karram. Finding new paths to discover and tell the truth. University World News, 22 jun. 2019. Disponível em: https://www.universityworldnews.com/post.php?story=20190621075859877. Acesso em: 28 de setembro de 2020. SVETLIK, David. When the academic world and the real world meet. Thought Action (NEA), n. Fall, 2007, p. 47-55. Disponível em: http://www.nea.org/assets/img/PubThoughtAndAction/TAA_07_06.pdf. Acesso em: 26 de setembro de 2020.TORRES, Carlos Alberto; SCHUGURENSKY, Daniel. The political economy of Higher Education in the era of neoliberal globalization: Latin America in comparative perspective. Higher Education, v. 43, jun. 2002, p. 429-455. Disponível em: https://doi.org/10.1023/A:1015292413037. Acesso em: 26 de setembro de 2020.TRIVIÑO CABRERA, Laura; CHAVES GUERRERO, Elisa Isabel. Cuando la Postmodernidad es un metarrelato más, ¿en qué educación ciudadana formar al profesorado? REIDICS Revista de Investigación en Didáctica de las Ciencias Sociales, n.7, 2020. Disponível em: https://doi.org/10.17398/2531-0968.07.82. Acesso em: 4 de dezembro de 2020.VARGAS, Claudio H. La jornada Aguascalientes: Los años por venir/extravíos. La Jornada Aguascalientes, 30 sep. 2019. Disponível em: https://www.lja.mx/2019/09/la-jornada-aguascalientes-los-anos-por-venir-extravios/. Acesso em: 2 de outubro de 2020.VASCONCELLOS-SILVA, Paulo R., CASTIEL, Luis David. COVID-19, as fake news e o sono da razão comunicativa gerando monstros: a narrativa dos riscos e os riscos das narrativas. Cadernos de Saúde Pública, v. 36, n. 7, 2020. Disponível em: https://doi.org/10.1590/0102-311x00101920. Acesso em: 2 de dezembro de 2020.VESSURI, Hebe. La ciencia y la educación superior en el proceso de internacionalización. Elementos de un marco conceptual para América Latina. UNESCO Forum Occasional Paper Series, n. 13/S, 2003.VIZOSO GARCÍA, Ángel Antonio; VÁZQUEZ HERRERO, Jorge. Plataformas de fact-checking en español. Características, organización y método. Communication Society, v. 32v, n. 1, 2019, p. 127-144. Disponível em: https://doi.org/10.15581/003.32.1.127-144. Acesso em: 14 de outubro de 2020.WHITTEMORE, Robin; CHAO, Ariana; JANG, Myoungock; et.al. Methods for knowledge synthesis. Heart Lung, v. 43, 2014, p. 453-461. Disponível em: http://dx.doi.org/10.1016/j.hrtlng.2014.05.014. Acesso em: 3 de dezembro de 2020.WORLD BANK. Lifelong learning in the global knowledge economy: Challenges for developing countries. Washington, DC: The International Bank for Reconstruction and Development, 2003. Disponível em: http://siteresources.worldbank.org/INTLL/Resources/Lifelong-Learning-in-the-Global-Knowledge-Economy/lifelonglearning_GKE.pdf. Acesso em: 2 de outubro de 2020.

Purpose: To predict central serous chorioretinopathy (CSC) recurrence 3 and 6 months after laser treatment by using machine learning.Methods: Clinical and imaging features of 461 patients (480 eyes) with CSC were collected at Zhongshan Ophthalmic Center (ZOC) and Xiamen Eye Center (XEC). The ZOC data (416 eyes of 401 patients) were used as the training dataset and the internal test dataset, while the XEC data (64 eyes of 60 patients) were used as the external test dataset. Six different machine learning algorithms and an ensemble model were trained to predict recurrence in patients with CSC. After completing the initial detailed investigation, we designed a simplified model using only clinical data and OCT features.Results: The ensemble model exhibited the best performance among the six algorithms, with accuracies of 0.941 (internal test dataset) and 0.970 (external test dataset) at 3 months and 0.903 (internal test dataset) and 1.000 (external test dataset) at 6 months. The simplified model showed a comparable level of predictive power.Conclusion: Machine learning achieves high accuracies in predicting the recurrence of CSC patients. The application of an intelligent recurrence prediction model for patients with CSC can potentially facilitate recurrence factor identification and precise individualized interventions.

ObjectivesEarly detection is of crucial importance for prevention of type 2 diabetes and pre-diabetes. Diagnosis of these conditions relies on the oral glucose tolerance test and haemoglobin A1c estimation which are invasive and challenging for large-scale screening. We aimed to combine the non-invasive nature of ECG with the power of machine learning to detect diabetes and pre-diabetes.MethodsData for this study come from Diabetes in Sindhi Families in Nagpur study of ethnically endogenous Sindhi population from central India. Final dataset included clinical data from 1262 individuals and 10 461 time-aligned heartbeats recorded digitally. The dataset was split into a training set, a validation set and independent test set (8892, 523 and 1046 beats, respectively). The ECG recordings were processed with median filtering, band-pass filtering and standard scaling. Minority oversampling was undertaken to balance the training dataset before initiation of training. Extreme gradient boosting (XGBoost) was used to train the classifier that used the signal-processed ECG as input and predicted the membership to ‘no diabetes’, pre-diabetes or type 2 diabetes classes (defined according to American Diabetes Association criteria).ResultsPrevalence of type 2 diabetes and pre-diabetes was ~30% and ~14%, respectively. Training was smooth and quick (convergence achieved within 40 epochs). In the independent test set, the DiaBeats algorithm predicted the classes with 97.1% precision, 96.2% recall, 96.8% accuracy and 96.6% F1 score. The calibrated model had a low calibration error (0.06). The feature importance maps indicated that leads III, augmented Vector Left (aVL), V4, V5 and V6 were most contributory to the classification performance. The predictions matched the clinical expectations based on the biological mechanisms of cardiac involvement in diabetes.ConclusionsMachine-learning-based DiaBeats algorithm using ECG signal data accurately predicted diabetes-related classes. This algorithm can help in early detection of diabetes and pre-diabetes after robust validation in external datasets.

Abstract Aims We investigated whether the use of an atrial fibrillation (AF) risk prediction algorithm could improve AF detection compared with opportunistic screening in primary care and assessed the associated budget impact. Methods and results Eligible patients were registered with a general practice in UK, aged 65 years or older in 2018/19, and had complete data for weight, height, body mass index, and systolic and diastolic blood pressure recorded within 1 year. Three screening scenarios were assessed: (i) opportunistic screening and diagnosis (standard care); (ii) standard care replaced by the use of the algorithm; and (iii) combined use of standard care and the algorithm. The analysis considered a 3-year time horizon, and the budget impact for the National Health Service (NHS) costs alone or with personal social services (PSS) costs. Scenario 1 would identify 79 410 new AF cases (detection gap reduced by 22%). Scenario 2 would identify 70 916 (gap reduced by 19%) and Scenario 3 would identify 99 267 new cases (gap reduction 27%). These rates translate into 2639 strokes being prevented in Scenario 1, 2357 in Scenario 2, and 3299 in Scenario 3. The 3-year NHS budget impact of Scenario 1 would be £45.3 million, £3.6 million (difference ‒92.0%) with Scenario 2, and £46.3 million (difference 2.2%) in Scenario 3, but for NHS plus PSS would be ‒£48.8 million, ‒£80.4 million (64.8%), and ‒£71.3 million (46.1%), respectively. Conclusion Implementation of an AF risk prediction algorithm alongside standard opportunistic screening could close the AF detection gap and prevent strokes while substantially reducing NHS and PSS combined care costs.

Abstract Background Severe sepsis and septic shock are among the leading causes of death in the United States and sepsis remains one of the most expensive conditions to diagnose and treat. Accurate early diagnosis and treatment can reduce the risk of adverse patient outcomes, but the efficacy of traditional rule-based screening methods is limited. The purpose of this study was to develop and validate a machine learning algorithm (MLA) for severe sepsis prediction up to 48 h before onset using a diverse patient dataset. Methods Retrospective analysis was performed on datasets composed of de-identified electronic health records collected between 2001 and 2017, including 510,497 inpatient and emergency encounters from 461 health centers collected between 2001 and 2015, and 20,647 inpatient and emergency encounters collected in 2017 from a community hospital. MLA performance was compared to commonly used disease severity scoring systems and was evaluated at 0, 4, 6, 12, 24, and 48 h prior to severe sepsis onset. Results 270,438 patients were included in analysis. At time of onset, the MLA demonstrated an AUROC of 0.931 (95% CI 0.914, 0.948) and a diagnostic odds ratio (DOR) of 53.105 on a testing dataset, exceeding MEWS (0.725, P < .001; DOR 4.358), SOFA (0.716; P < .001; DOR 3.720), and SIRS (0.655; P < .001; DOR 3.290). For prediction 48 h prior to onset, the MLA achieved an AUROC of 0.827 (95% CI 0.806, 0.848) on a testing dataset. On an external validation dataset, the MLA achieved an AUROC of 0.948 (95% CI 0.942, 0.954) at the time of onset, and 0.752 at 48 h prior to onset. Conclusions The MLA accurately predicts severe sepsis onset up to 48 h in advance using only readily available vital signs extracted from the existing patient electronic health records. Relevant implications for clinical practice include improved patient outcomes from early severe sepsis detection and treatment.

Land-use control is local and highly varied. State agencies struggle to assess plan contents. Similarly, advocacy groups and planning researchers wrestle with the length of planning documents and ability to compare across plans. The goal of this research is to (1) introduce Natural Language Processing techniques that can automate qualitative coding in planning research and (2) provide policy-relevant exploratory findings. We assembled a database of 461 California city-level General Plans, extracted the text, and used topic modeling to identify areas of emphasis (clusters of co-occurring words). We find that California city general plans address more than sixty topics, including greenhouse gas mitigation and Climate Action Planning. Through spatializing results, we find that a quarter of the topics in plans are regionally specific. We also quantify the rift and convergence of planning topics. The topics focused on housing have very little overlap with other planning topics. This is likely a factor of state requirements to update and evolve the Housing Elements every five years, but not other aspects of General Plans. This finding has policy implications as housing topics evolve away from other emphasis areas such as transportation and economic development. Furthermore, the topic modeling approach reveals that many cities have had a focus on environmental justice through Health and Wellness Elements well before the state mandate in 2019. Our searchable state-level database of general plans is the first for California—and nationally. We provide a model for others that wish to comprehensively assess and compare plan contents using machine learning.

Abstract Background Depending on etiology, extent of disease progression, and comorbidities, patients with severe mitral regurgitation (MR) typically present with considerable heterogeneity. Purpose This study therefore sought to improve diagnostic and prognostic resolution in patients undergoing mitral valve transcatheter edge-to-edge repair (MV TEER) for severe MR by developing a man-machine interaction-based phenotyping approach. Methods All 609 patients from this single-center registry underwent MV TEER for severe MR between 2009 and 2020. Unsupervised agglomerative clustering was applied to preprocedural echocardiography data, and an artificial neural network (ANN) was subsequently trained for future patient-to-cluster assignment. Primary outcome measure was postprocedural 5-year survival Results Cluster analysis revealed four pathophysiologically and prognostically informative phenotypes: Cluster 1 was constituted by patients (n=188) presenting with preserved left ventricular ejection fraction (LVEF; 56.5±7.79%) and regular left ventricular end-systolic diameter (LVESD; 35.2±7.52 mm). 5-year survival in patients from cluster 1, hereinafter serving as a reference, was 60.9% (95% CI: 53.3–69.7%). Patients from cluster 2 (n=102) also presented with preserved LVEF (55.7±7.82%) and regular LVESD (34.9±7.68 mm), but showed the largest mitral valve effective regurgitant orifice area (0.623±0.360 cm2) and highest systolic pulmonary artery pressures (68.4±16.2 mmHg). Consequently, their 5-year survival ranged at 43.7% (95% CI: 33.2–57.6%; p-value: 0.032). Patients from cluster 3 (n=270) were predominantly characterized by impaired left ventricular systolic function (LVEF: 31.0±10.4%) and dilated left ventricular diameters (LVESD: 53.2±10.9 mm), and their 5-year survival was reduced to 38.3% (95% CI: 31.9–46.1%; p-value: &lt;0.001). Poorest 5-year survival (23.8% [95% CI: 12.8–44.3%]; p-value: &lt;0.001) was observed in patients from cluster 4 (n=49) with biatrial dilatation (left atrial volume: 312±113 mL; right atrial area: 46.0±8.83 cm2) although LVEF was only slightly reduced (51.5±11.0%). All patients from cluster 4 were diagnosed with atrial fibrillation. An ANN could precisely predict cluster assignment (accuracy: 85.2%), detecting patients from high-risk clusters 3 and 4 with excellent specificity (95.0% and 99.4%, respectively). Conclusion Assigning patients to clusters using a multiparametric phenotypic approach can facilitate risk stratification in future clinical practice. Our unsupervised machine learning-based classification system differs from previous approaches for risk stratification, because we do neither hypothesize a linear sequence of accumulated pathologies caused by severe MR (potentially ignoring the aggravating impact of comorbidities), nor do we stratify patients into low- and high-risk cohorts in accordance with a single variable's dichotomy (prone to oversimplification). Funding Acknowledgement Type of funding sources: None.

Abstract Background Review of scientific literature is a time consuming but fundamental step in any kind of scientific research. A consistent manual filtering of papers is always necessary in order to evaluate their relevance with respect to the topic of interest, as the sorting provided by most common research engines is rarely efficient in terms of matching with the desired contents. Purpose The aim of this study was to develop, and validate versus manual analysis, an automated tool for performing an efficient search through medical scientific literature, according to keywords relevant to the application of specific technologies in the field of cardiology. Methods Using this multiplatform tool implemented in Python, PyQt5 library, the user is required to insert a list of keywords, from which all the possible search strings were built by connecting them with logical operators. The algorithm automatically queries the on-line database PubMed (NCBI) and downloads all the resulting abstracts, with titles and keywords. Results related to the field of cardiology are identified counting the occurrences of “marker” words collected in a dedicated dictionary, developed on the base of the Unified Medical Language System (U.S. NLM). Then, a search-specific dictionary is automatically developed according to the statistical distribution of words in the texts of abstracts, titles and keywords and weighting them according to their relative frequency (ratio between occurrences and number of considered papers). Finally, for each paper the occurrences of these “marker” words are counted and a matching-probability score is assigned, providing a sorting of the results according to expected matching with the topic of interest, together with a threshold-based binary classification. In order to validate the algorithm, three different technologies with potential applications in cardiology were considered: smartphone applications (App), machine learning (ML) and virtual reality (VR). The related dictionaries were developed with the dedicated function embedded in the tool, while, for the validation of the results, a dataset of 461 manually-classified abstracts was considered, and algorithm thresholds were iteratively adjusted on the base of validation results. Results The algorithm applied to the validation dataset showed an overall accuracy (acc) of 88.5% (sensitivity (se) 85.78%, specificity (sp) 91.27%) in the identification of cardiology papers, while the results for the three inspected technologies were: App: acc 90.89% (se 92.16%, sp 90.53%) ML: acc 82.65% (se 94.06%, sp 79.44%) VR: acc 91.54% (se 96%, sp 90.3%) The algorithm can process 5000 abstracts in around 2 hours. Conclusions Results of the validation revealed that the proposed approach is highly valuable in speeding-up any search of medical literature focused on a specific technology or application, enabling a quick overview regarding its diffusion and maturity in a specific scientific domain. Algorithm schema Funding Acknowledgement Type of funding source: None