To see the other types of publications on this topic, follow the link: Cancer Treatment Data processing.
Journal articles on the topic 'Cancer Treatment Data processing'
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 'Cancer Treatment Data processing.'
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
P, Rajesh, Murugan A, Murugamantham B, and Ganesh Kumar S. "Lung Cancer Diagnosis and Treatment Using AI and Mobile Applications." International Journal of Interactive Mobile Technologies (iJIM) 14, no. 17 (2020): 189. http://dx.doi.org/10.3991/ijim.v14i17.16607.
Full textAbstract:
Cancer has become very common in this evolving world. Technology advancements, increased radiations have made cancer a common syndrome. Various types of cancers like Skin Cancer, Breast Cancer, Prostate Cancer, Blood Cancer, Colorectal cancer, Kidney Cancer and Lung Cancer exits. Among these various types of cancers, the mortality rate is high in lung cancer which is tough to diagnose and can be diagnosed only in advanced stages. Small cell lung cancer and non-small cell lung cancer are the two types in which non-small cell lung cancer (NSCLC) is the most common type which makes up to 80 to 85 percent of all cases [1]. Digital Image Processing and Artificial Intelligence advancements has helped a lot in medical image analysis and Computer Aided Diagnosis(CAD). Numerous research is carried out in this field to improve the detection and prediction of the cancerous tissues. In current methods, traditional image processing techniques is applied for image processing, noise removal and feature extraction. There are few good approaches that applies Artificial Intelligence and produce better results. However, no research has achieved 100% accuracy in nodule detection, early detection of cancerous nodules nor faster processing methods. Application of Artificial Intelligence techniques like Machine Learning, Deep Learning is very minimal and limited. In this paper [Figure 1], we have applied Artificial intelligence techniques to process CT (Computed Tomography) Scan image for data collection and data model training. The DICOM image data is saved as numpy file with all medical information extracted from the files for training. With the trained data we apply deep learning for noise removal and feature extraction. We can process huge volume of medical images for data collection, image processing, detection and prediction of nodules. The patient is made well aware of the disease and enabled with their health tracking using various mobile applications made available in the online stores for iOS and Android mobile devices.
2
Zeng, Jiaming, Imon Banerjee, A. Solomon Henry, et al. "Natural Language Processing to Identify Cancer Treatments With Electronic Medical Records." JCO Clinical Cancer Informatics, no. 5 (April 2021): 379–93. http://dx.doi.org/10.1200/cci.20.00173.
Full textAbstract:
PURPOSE Knowing the treatments administered to patients with cancer is important for treatment planning and correlating treatment patterns with outcomes for personalized medicine study. However, existing methods to identify treatments are often lacking. We develop a natural language processing approach with structured electronic medical records and unstructured clinical notes to identify the initial treatment administered to patients with cancer. METHODS We used a total number of 4,412 patients with 483,782 clinical notes from the Stanford Cancer Institute Research Database containing patients with nonmetastatic prostate, oropharynx, and esophagus cancer. We trained treatment identification models for each cancer type separately and compared performance of using only structured, only unstructured ( bag-of-words, doc2vec, fasttext), and combinations of both ( structured + bow, structured + doc2vec, structured + fasttext). We optimized the identification model among five machine learning methods (logistic regression, multilayer perceptrons, random forest, support vector machines, and stochastic gradient boosting). The treatment information recorded in the cancer registry is the gold standard and compares our methods to an identification baseline with billing codes. RESULTS For prostate cancer, we achieved an f1-score of 0.99 (95% CI, 0.97 to 1.00) for radiation and 1.00 (95% CI, 0.99 to 1.00) for surgery using structured + doc2vec. For oropharynx cancer, we achieved an f1-score of 0.78 (95% CI, 0.58 to 0.93) for chemoradiation and 0.83 (95% CI, 0.69 to 0.95) for surgery using doc2vec. For esophagus cancer, we achieved an f1-score of 1.0 (95% CI, 1.0 to 1.0) for both chemoradiation and surgery using all combinations of structured and unstructured data. We found that employing the free-text clinical notes outperforms using the billing codes or only structured data for all three cancer types. CONCLUSION Our results show that treatment identification using free-text clinical notes greatly improves upon the performance using billing codes and simple structured data. The approach can be used for treatment cohort identification and adapted for longitudinal cancer treatment identification.
3
Ma, Meng, Kyeryoung Lee, Yun Mai, et al. "Extracting longitudinal anticancer treatments at scale using deep natural language processing and temporal reasoning." Journal of Clinical Oncology 39, no. 15_suppl (2021): e18747-e18747. http://dx.doi.org/10.1200/jco.2021.39.15_suppl.e18747.
Full textAbstract:
e18747 Background: Accurate longitudinal cancer treatments are vital for establishing primary endpoints such as outcome as well as for the investigation of adverse events. However, many longitudinal therapeutic regimens are not well captured in structured electronic health records (EHRs). Thus, their recognition in unstructured data such as clinical notes is critical to gain an accurate description of the real-world patient treatment journey. Here, we demonstrate a scalable approach to extract high-quality longitudinal cancer treatments from lung cancer patients' clinical notes using a Bidirectional Long Short Term Memory (BiLSTM) and Conditional Random Fields (CRF) based natural language processing (NLP) pipeline. Methods: The lung cancer (LC) cohort of 4,698 patients was curated from the Mount Sinai Healthcare system (2003-2020). Two domain experts developed a structured framework of entities and semantics that captured treatment and its temporality. The framework included therapy type (chemotherapy, targeted therapy, immunotherapy, etc.), status (on, off, hold, planned, etc.) and temporal reasoning entities and relations (admin_date, duration, etc.) We pre-annotated 149 FDA-approved cancer drugs and longitudinal timelines of treatment on the training corpus. A NLP pipeline was implemented with BiLSTM-CRF-based deep learning models to train and then apply the resulting models to the clinical notes of LC cohort. A postprocessor was developed to subsequently post-coordinate and refine the output. We performed both cross-evaluation and independent evaluation to assess the pipeline performance. Results: We applied the NLP pipeline to the 853,755 clinical notes, and identified 1,155 distinct entities for 194 cancer generic drugs, including 74 chemotherapy drugs, 21 immunotherapy drugs, and 99 targeted therapy drugs. We identified chemotherapy, immunotherapy, or targeted therapy data for 3,509 patients in the LC cohort from the clinical notes. Compared to only 2,395 patients with cancer treatments in structured EHR, this pipeline identified cancer treatments from notes for additional 2,303 patients who did not have any available cancer treatment data in the structured EHR. Our evaluation schema indicates that the longitudinal cancer drug recognition pipeline delivers strong performance (named entity recognization for drugs and temporal: F1 = 95%; drug-temporal relation recognition: F1 = 90%). Conclusions: We developed a high-performance BiLSTM-CRF based NLP pipeline to recognize longitudinal cancer treatments. The pipeline recovers and encodes as twice as many patients with cancer treatments compared with structured EHR. Our study indicates deep NLP with temporal reasoning could substantially accelerate the extraction of treatment profiles at scale. The pipeline is adjustable and can be applied across different cancers.
4
Thottathyl, Hymavathi, Kanadam Karteeka Pavan, and Rajeev Priyatam Panchadula. "Microarray Breast Cancer Data Clustering Using Map Reduce Based K-Means Algorithm." Revue d'Intelligence Artificielle 34, no. 6 (2020): 763–69. http://dx.doi.org/10.18280/ria.340610.
Full textAbstract:
Breast cancer is one of the world's most advanced and most common cancers occurring in women. An early diagnosis of breast cancer offers treatment for it; therefore, several experiments are in development establishing approaches for the early detection of breast cancer. The great increase in research in the last decade in microarray data processing is a potent tool of diagnosing diseases. Based on genomic knowledge, micro-arrays have changed the way clinical pathology recognizes, identifies, and classifies the diseases of humans, particularly those of cancer. In this article, we examined microarray data for breast cancer with the k-means clustering algorithm, but it was hard to scale and process a large number of micro-array data alone. To this end, we use a chart to minimize the paradigm for evaluating microarray data on breast cancer. Moreover, the efficiency of the parallel k-means model is measured with the operating period, the scaling, and all runtime of the model.
5
Hernandez-Boussard, Tina, Panagiotis Kourdis, Rajendra Dulal, et al. "A natural language processing algorithm to measure quality prostate cancer care." Journal of Clinical Oncology 35, no. 8_suppl (2017): 232. http://dx.doi.org/10.1200/jco.2017.35.8_suppl.232.
Full textAbstract:
232 Background: Electronic health records (EHRs) are a widely adopted but underutilized source of data for systematic assessment of healthcare quality. Barriers for use of this data source include its vast complexity, lack of structure, and the lack of use of standardized vocabulary and terminology by clinicians. This project aims to develop generalizable algorithms to extract useful knowledge regarding prostate cancer quality metrics from EHRs. Methods: We used EHR ICD-9/10 codes to identify prostate cancer patients receiving care at our academic medical center. Patients were confirmed in the California Cancer Registry (CCR), which provided data on tumor characteristics, treatment data, treatment outcomes and survival. We focused on three potential pretreatment process quality measures, which included documentation within 6 months prior to initial treatment of prostate-specific antigen (PSA), digital rectal exam (DRE) performance, and Gleason score. Each quality metric was defined using target terms and concepts to extract from the EHRs. Terms were mapped to a standardized medical vocabulary or ontology, enabling us to represent the metric elements by a concept domain and its permissible values. The structured representation of the quality metric included rules that accounted for the temporal order of the metric components. Our algorithms used natural language processing for free text annotation and negation, to ensure terms such as ‘DRE deferred’ are appropriately categorized. Results: We identified 2,123 patients receiving prostate cancer treatment between 2008-2016, of whom 1413 (67%) were matched in the CCR. We compared accuracy of our data mining algorithm, a random sample of manual chart review, and the CCR. (See Table.) Conclusions: EHR systems can be used to assess and report quality metrics systematically, efficiently, and with high accuracy. The development of such systems can improve and reduce the burden of quality reporting and potentially reduce costs of measuring quality metrics through automation. [Table: see text]
6
Volchenboum, Samuel L., Suzanne M. Cox, Allison Heath, Adam Resnick, Susan L. Cohn, and Robert Grossman. "Data Commons to Support Pediatric Cancer Research." American Society of Clinical Oncology Educational Book, no. 37 (May 2017): 746–52. http://dx.doi.org/10.1200/edbk_175029.
Full textAbstract:
The falling costs and increasing fidelity of high-throughput biomedical research data have led to a renaissance in cancer surveillance and treatment. Yet, the amount, velocity, and complexity of these data have overcome the capacity of the increasing number of researchers collecting and analyzing this information. By centralizing the data, processing power, and tools, there is a valuable opportunity to share resources and thus increase the efficiency, power, and impact of research. Herein, we describe current data commons and how they operate in the oncology landscape, including an overview of the International Neuroblastoma Risk Group data commons as a paradigm case. We outline the practical steps and considerations in building data commons. Finally, we discuss the unique opportunities and benefits of creating a data commons within the context of pediatric cancer research, highlighting the particular advantages for clinical oncology and suggested next steps.
7
Devi, M. Shyamala, A. N. Sruthi, and P. Balamurugan. "Artificial neural network classification-based skin cancer detection." International Journal of Engineering & Technology 7, no. 1.1 (2017): 591. http://dx.doi.org/10.14419/ijet.v7i1.1.10364.
Full textAbstract:
At present, skin cancers are extremely the most severe and life-threatening kind of cancer. The majority of the pores and skin cancers are completely remediable at premature periods. Therefore, a premature recognition of pores and skin cancer can effectively protect the patients. Due to the progress of modern technology, premature recognition is very easy to identify. It is not extremely complicated to discover the affected pores and skin cancers with the exploitation of Artificial Neural Network (ANN). The treatment procedure exploits image processing strategies and Artificial Intelligence. It must be noted that, the dermoscopy photograph of pores and skin cancer is effectively determined and it is processed to several pre-processing for the purpose of noise eradication and enrichment in image quality. Subsequently, the photograph is distributed through image segmentation by means of thresholding. Few components distinctive for skin most cancers regions. These features are mined the practice of function extraction scheme - 2D Wavelet Transform scheme. These outcomes are provides to the Back-Propagation Neural (BPN) Network for effective classification. This completely categorizes the data set into either cancerous or non-cancerous.
8
Marszałł, Michał, Jerzy Krysiński, Wiktor Sroka, et al. "ANN as a prognostic tool after treatment of non-seminoma testicular cancer." Open Medicine 7, no. 5 (2012): 672–79. http://dx.doi.org/10.2478/s11536-012-0027-7.
Full textAbstract:
AbstractTesticular cancer is rare but is the most common cancer in males between 15 and 34 years of age. Two principal types of testicular cancer are distinguished: seminomas and non-seminomas. If detected early, the overall cure rate for testicular cancer exceeds 90%. In this study, artificial neural network (ANN) analysis as a prognostic tool was demonstrated regard to five year recurrence after the non-seminoma treatment. Data from 202 patients treated for non-seminoma were available for evaluation and comparison. A total of 32 variables were analysed using the ANN. The ANN approach, as an advanced multivariate data processing method, was demon-strated to provide objective prognostic data. Some of these prognostic factors are consistent or even imperceptible with previously evaluated by other statistical methods.
9
Alba, Patrick R., Julie Ann Lynch, Anthony Gao, et al. "Using natural language processing (NLP) tools to identify veterans with metastatic prostate cancer (mPCa)." Journal of Clinical Oncology 38, no. 6_suppl (2020): 60. http://dx.doi.org/10.1200/jco.2020.38.6_suppl.60.
Full textAbstract:
60 Background: Veterans may benefit from promising innovations in treatments for mPCa. The Veterans Affairs (VA) and Prostate Cancer Foundation (PCF) leadership issued a challenge to identify, in real time, the national census of Veterans receiving care for mPCa. Administrative diagnostic and procedural coding do not accurately identify the risk status or disease state of prostate cancer (PCa). This study reports the development and validation of NLP tools deployed on clinical notes to identify risk status or disease state. Methods: Using diagnosis and histology codes, we queried the VA Corporate Data Warehouse to identify Veterans with prostate cancer. We included structured laboratory tests, medications, procedures, and surgeries related to prostate cancer diagnosis or treatment in the analysis. Using structured data, we identified 1000 likely mPCa cases and controls. Medical records were reviewed to confirm status and to extract term dictionaries related to cancer, anatomy, metastasis, and other diagnostic concepts. We went through several iterations of testing to refine and validate the NLP tool on a limited set of known cases and controls. We deployed the tool on all cancer, urology, pathology, and radiation oncology notes. Results: The NLP system was able to identify the patients' history of metastatic disease with 0.975 precision and 0.828 recall. Among the 1,081,137 Veterans with prostate cancer, NLP identified 63,222 (5.8%) with mPCa. There are 16,282 Veterans alive with mPCa. Mean age of diagnosis was 67 and 8,847 (54.3%) were diagnosed in the VA. Demographics were: White 9,756 (60%), Black 4,466 (27%), and other 2,060 (13%). Conclusions: NLP is a reliable tool for identifying Veterans who may benefit from novel innovations in mPCa diagnosis and treatment.[Table: see text]
10
Ahles, Tim A., Andrew J. Saykin, Brenna C. McDonald, et al. "Longitudinal Assessment of Cognitive Changes Associated With Adjuvant Treatment for Breast Cancer: Impact of Age and Cognitive Reserve." Journal of Clinical Oncology 28, no. 29 (2010): 4434–40. http://dx.doi.org/10.1200/jco.2009.27.0827.
Full textAbstract:
Purpose To examine the impact of age and cognitive reserve on cognitive functioning in patients with breast cancer who are receiving adjuvant treatments. Patients and Methods Patients with breast cancer exposed to chemotherapy (n = 60; mean age, 51.7 years) were evaluated with a battery of neuropsychological and psychological tests before treatment and at 1, 6, and 18 months after treatment. Patients not exposed to chemotherapy (n = 72; mean age, 56.6 years) and healthy controls (n = 45; mean age, 52.9 years) were assessed at matched intervals. Results Mixed-effects modeling revealed significant effects for the Processing Speed and Verbal Ability domains. For Processing Speed, a three-way interaction among treatment group, age, and baseline cognitive reserve (P < .001) revealed that older patients with lower baseline cognitive reserve who were exposed to chemotherapy had lower performance on Processing Speed compared with patients not exposed to chemotherapy (P = .003) and controls (P < .001). A significant group by time interaction for Verbal Ability (P = .01) suggested that the healthy controls and no chemotherapy groups improved over time. The chemotherapy group failed to improve at 1 month after treatment but improved during the last two follow-up assessments. Exploratory analyses suggested a negative effect of tamoxifen on Processing Speed (P = .036) and Verbal Memory (P = .05) in the no-chemotherapy group. Conclusion These data demonstrated that age and pretreatment cognitive reserve were related to post-treatment decline in Processing Speed in women exposed to chemotherapy and that chemotherapy had a short-term impact on Verbal Ability. Exploratory analysis of the impact of tamoxifen suggests that this pattern of results may be due to a combination of chemotherapy and tamoxifen.
11
Banerjee, Imon, Kevin Li, Martin Seneviratne, et al. "Weakly supervised natural language processing for assessing patient-centered outcome following prostate cancer treatment." JAMIA Open 2, no. 1 (2019): 150–59. http://dx.doi.org/10.1093/jamiaopen/ooy057.
Full textAbstract:
Abstract Background The population-based assessment of patient-centered outcomes (PCOs) has been limited by the efficient and accurate collection of these data. Natural language processing (NLP) pipelines can determine whether a clinical note within an electronic medical record contains evidence on these data. We present and demonstrate the accuracy of an NLP pipeline that targets to assess the presence, absence, or risk discussion of two important PCOs following prostate cancer treatment: urinary incontinence (UI) and bowel dysfunction (BD). Methods We propose a weakly supervised NLP approach which annotates electronic medical record clinical notes without requiring manual chart review. A weighted function of neural word embedding was used to create a sentence-level vector representation of relevant expressions extracted from the clinical notes. Sentence vectors were used as input for a multinomial logistic model, with output being either presence, absence or risk discussion of UI/BD. The classifier was trained based on automated sentence annotation depending only on domain-specific dictionaries (weak supervision). Results The model achieved an average F1 score of 0.86 for the sentence-level, three-tier classification task (presence/absence/risk) in both UI and BD. The model also outperformed a pre-existing rule-based model for note-level annotation of UI with significant margin. Conclusions We demonstrate a machine learning method to categorize clinical notes based on important PCOs that trains a classifier on sentence vector representations labeled with a domain-specific dictionary, which eliminates the need for manual engineering of linguistic rules or manual chart review for extracting the PCOs. The weakly supervised NLP pipeline showed promising sensitivity and specificity for identifying important PCOs in unstructured clinical text notes compared to rule-based algorithms. Trial registration This is a chart review study and approved by Institutional Review Board (IRB).
12
Ling, Albee Y., Allison W. Kurian, Jennifer L. Caswell-Jin, George W. Sledge, Nigam H. Shah, and Suzanne R. Tamang. "Using natural language processing to construct a metastatic breast cancer cohort from linked cancer registry and electronic medical records data." JAMIA Open 2, no. 4 (2019): 528–37. http://dx.doi.org/10.1093/jamiaopen/ooz040.
Full textAbstract:
Abstract Objectives Most population-based cancer databases lack information on metastatic recurrence. Electronic medical records (EMR) and cancer registries contain complementary information on cancer diagnosis, treatment and outcome, yet are rarely used synergistically. To construct a cohort of metastatic breast cancer (MBC) patients, we applied natural language processing techniques within a semisupervised machine learning framework to linked EMR-California Cancer Registry (CCR) data. Materials and Methods We studied all female patients treated at Stanford Health Care with an incident breast cancer diagnosis from 2000 to 2014. Our database consisted of structured fields and unstructured free-text clinical notes from EMR, linked to CCR, a component of the Surveillance, Epidemiology and End Results Program (SEER). We identified de novo MBC patients from CCR and extracted information on distant recurrences from patient notes in EMR. Furthermore, we trained a regularized logistic regression model for recurrent MBC classification and evaluated its performance on a gold standard set of 146 patients. Results There were 11 459 breast cancer patients in total and the median follow-up time was 96.3 months. We identified 1886 MBC patients, 512 (27.1%) of whom were de novo MBC patients and 1374 (72.9%) were recurrent MBC patients. Our final MBC classifier achieved an area under the receiver operating characteristic curve (AUC) of 0.917, with sensitivity 0.861, specificity 0.878, and accuracy 0.870. Discussion and Conclusion To enable population-based research on MBC, we developed a framework for retrospective case detection combining EMR and CCR data. Our classifier achieved good AUC, sensitivity, and specificity without expert-labeled examples.
13
Movchan, O. M., V. S. Svintsitskіy, and O. I. Bublieva. "Testing methods for surgical treatment of endometrial cancer." Reports of Vinnytsia National Medical University 25, no. 2 (2021): 301–4. http://dx.doi.org/10.31393/reports-vnmedical-2021-25(2)-20.
Full textAbstract:
Annotation. The urgency of the study is due to an increase in the incidence (more than 50%) of newly diagnosed uterine endometrial cancer, especially among young people. The main method of treatment for stage I-II endometrial cancer remains surgery. The study aimed to identify possible cytological conversion during laparoscopic procedures. The main method of research was a non-randomized, prospective cohort study with subsequent observation of the duration of hospitalization and 30 days after discharge for the period from 2010 to 2019. The duration of hospitalization was estimated, while in the perioperative period and within 30 days after discharge – the presence of postoperative complications. A total of 812 patients with stage I-IV endometrial cancer were analyzed, with a mean age of 52±5 years (25 to 75 years). The first group included patients who underwent laparotomy, the second – laparoscopic surgery. The presence of metastases and recurrences was confirmed by morphological, radiological, echoscopic and clinical methods. Standard methods of descriptive statistics were used for data processing; in particular, the average values were calculated with their standard errors when using the standard Student’s t-test at p<0.05 using Microsoft Excel software packages. Conclusions were made about the volume and type of surgery, taking into account the histological type of tumor, lymphovascular invasion, clinical stage, presence or absence of obesity and other comorbidities that may affect metabolism, life history and the presence of surgery. The obtained data confirm the safety of laparoscopic hysterectomy for women with stage I endometrial cancer. However, there are no data on whether laparoscopy can lead to intra-abdominal dissemination of tumor cells.
14
Deprez, Sabine, Shelli R. Kesler, Andrew J. Saykin, Daniel H. S. Silverman, Michiel B. de Ruiter, and Brenna C. McDonald. "International Cognition and Cancer Task Force Recommendations for Neuroimaging Methods in the Study of Cognitive Impairment in Non-CNS Cancer Patients." JNCI: Journal of the National Cancer Institute 110, no. 3 (2018): 223–31. http://dx.doi.org/10.1093/jnci/djx285.
Full textAbstract:
Abstract Cancer- and treatment-related cognitive changes have been a focus of increasing research since the early 1980s, with meta-analyses demonstrating poorer performance in cancer patients in cognitive domains including executive functions, processing speed, and memory. To facilitate collaborative efforts, in 2011 the International Cognition and Cancer Task Force (ICCTF) published consensus recommendations for core neuropsychological tests for studies of cancer populations. Over the past decade, studies have used neuroimaging techniques, including structural and functional magnetic resonance imaging (fMRI) and positron emission tomography, to examine the underlying brain basis for cancer- and treatment-related cognitive declines. As yet, however, there have been no consensus recommendations to guide researchers new to this field or to promote the ability to combine data sets. We first discuss important methodological issues with regard to neuroimaging study design, scanner considerations, and sequence selection, focusing on concerns relevant to cancer populations. We propose a minimum recommended set of sequences, including a high-resolution T1-weighted volume and a resting state fMRI scan. Additional advanced imaging sequences are discussed for consideration when feasible, including task-based fMRI and diffusion tensor imaging. Important image data processing and analytic considerations are also reviewed. These recommendations are offered to facilitate increased use of neuroimaging in studies of cancer- and treatment-related cognitive dysfunction. They are not intended to discourage investigator-initiated efforts to develop cutting-edge techniques, which will be helpful in advancing the state of the knowledge. Use of common imaging protocols will facilitate multicenter and data-pooling initiatives, which are needed to address critical mechanistic research questions.
15
Vodermaier, Andrea. "Breast Cancer Treatment and Cognitive Function: The Current State of Evidence, Underlying Mechanisms and Potential Treatments." Women's Health 5, no. 5 (2009): 503–16. http://dx.doi.org/10.2217/whe.09.36.
Full textAbstract:
Within the last decade, several studies have investigated whether adjuvant treatment of breast cancer affects cognitive function. A number of prospective studies have demonstrated inconsistent results regarding whether chemotherapy affects cognitive function. Approximately half of the studies demonstrated subtle cognitive decline in a wide range of domains among some breast cancer patients following chemotherapy, and half did not. Concomitant changes in brain structure and function have been identified in neuroimaging and neurophysiologic studies. Estrogenic therapy has been specifically associated with deterioration in verbal memory and processing speed. However, evidence is mostly based on smaller studies with cross-sectional data. Breast cancer patients who underwent both chemotherapy and estrogenic therapy showed the most deterioration and the most persistant decline in cognitive function. Since cognitive impairment is subtle, if evident at all, discrepant findings are due to hormonal, physiological, psychological or temporal confounding variables and differences in study design. Neuropsychological training has been demonstrated to improve cognitive dysfunction experienced by breast cancer patients after chemotherapy. Future research may examine the unique impact of endocrine therapy on cognitive function with prospective, controlled trials, as well as the role of further confounding variables (e.g., menopausal status, cytokine deregulation, cortisol and concurrent medication).
16
Et. al., Er Charnpreet kaur,. "Artificial Intelligence Techniques for Cancer Detection in Medical Image Processing: A Review." Turkish Journal of Computer and Mathematics Education (TURCOMAT) 12, no. 2 (2021): 2667–73. http://dx.doi.org/10.17762/turcomat.v12i2.2286.
Full textAbstract:
Cancer is the uncontrolled growth of abnormal cells in any part of a body. Cancer is a broad term for a group of diseases caused when abnormal cells grows in different body parts. There are more than hundred types of Cancer such as Lung cancer, Breast cancer, Skin cancer, Oral cancer, Colon cancer and Prostate cancer. Delay in treatment can cause serious health issues, even cause loss of life. This paper gives the review on methods of detection of lung cancer and brain cancer and liver using image processing. The methods used for detection are Automated and computer-aided detection system (CAD) with artificial intelligence and these methods are good to process a large datasets to provide accurate and efficient results in the detection of cancer. However, these processing system have to face many challenges to implement on large scale including imageacquisition, pre-processing, segmentation, and data management and classification strategies to be compatible with AI. This paper reviews the various image acquisition and segmentation techniques. These techniques become the need of an hour to cater the growing patient population and for the improvement in the Healthcare system.
17
Blackledge, Matthew D., Mihaela Rata, Nina Tunariu, et al. "Visualizing whole-body treatment response heterogeneity using multi-parametric magnetic resonance imaging." Journal of Algorithms & Computational Technology 10, no. 4 (2016): 290–301. http://dx.doi.org/10.1177/1748301816668024.
Full textAbstract:
A novel post-processing methodology able to assess whole-body tumor heterogeneity in patients with metastatic disease is proposed. The method is demonstrated on paired pre- and post-treatment data sets obtained from an initial cohort of six patients with metastatic disease from primary prostate or ovarian cancers. Whole-body diffusion-weighted imaging and T1-weighted contrast-enhanced imaging data were acquired covering the chest, abdomen, and pelvis. Joint histograms of Apparent Diffusion Coefficient and Fractional Enhancement values were calculated within volumes of interest and were modeled as a Gaussian mixture of two classes. Probability maps and volumetric estimates of the magnetic resonance data-derived classes providing visualization of pre- and post-treatment data are shown in three patient examples. This technique provided spatially heterogeneous characterization of regions following treatment as defined by the combined analysis of apparent diffusion coefficient and fractional enhancement. A new whole-body magnetic resonance data analysis has been demonstrated enabling visualization of intra-patient response heterogeneity in patients with metastatic cancer. Changes in the parameters of each subpopulation derived from this technique (apparent diffusion coefficient and fractional enhancement) reflect changes in the tissue properties of each subpopulation following treatment. Furthermore, the volume change of each population can be quantified. Such techniques may be essential for personalized anti-cancer therapy where there is a need to detect early drug-resistance and monitor heterogeneous response.
18
Ma, Meng, Arielle Redfern, Xiang Zhou, et al. "Automated abstraction of real-world clinical outcome in lung cancer: A natural language processing and artificial intelligence approach from electronic health records." Journal of Clinical Oncology 38, no. 15_suppl (2020): e14062-e14062. http://dx.doi.org/10.1200/jco.2020.38.15_suppl.e14062.
Full textAbstract:
e14062 Background: Real world evidence generated from electronic health records (EHRs) is playing an increasing role in health care decisions. It has been recognized as an essential element to assess cancer outcomes in real-world settings. Automatically abstracting outcomes from notes is becoming a fundamental challenge in medical informatics. In this study, we aim to develop a system to automatically abstract outcomes (Progression, Response, Stable Disease) from notes in lung cancer. Methods: A lung cancer cohort (n = 5,003) was obtained from the Mount Sinai Data Warehouse. The progress, pathology and radiology notes of patients were used. We integrated various techniques of Natural Language Processing (NLP) and Artificial Intelligence (AI) and developed a system to automatically abstract outcomes. The corresponding images, biopsies and lines of treatments (LOTs) were abstracted as attributes of outcomes. This system includes four information models: 1. Customized NLP annotator model: preprocessor, section detector, sentence splitter, named entity recognition, relation detector; CRF and LSTM methods were applied to recognize entities and relations. 2. Clinical Outcome container model: biopsy evidence extractor, lines of treatment detector, image evidence extractor, clinical outcome event recognizer, date detector, and temporal reasoning; Domain-specific rules were crafted to automatically infer outcomes. 3. Document Summarizer; 4. Longitudinal Outcome Summarizer. Results: To evaluate the outcomes abstracted, we curated a subset (n = 792) from patient cohort for which LOTs were available. About 61% of the outcomes identified were supported by radiologic images (time window = ±14 days) or biopsy pathology results (time window = ±100 days). In 91% (720/792) of patients, Progression was abstracted within a time window of 90 days prior to first-line treatment. Also, 72% of the Progression events identified were accompanied by a downstream event (e.g., treatment change or death). We randomly selected 250 outcomes for manual curation, and 197 outcomes were assessed to be correct (precision = 79%). Moreover, our automated abstraction system improved human abstractor efficiency to curate outcomes, reducing curation time per patient by 90%. Conclusions: We have demonstrated the feasibility and effectiveness of NLP and AI approaches to abstract outcomes from lung cancer EHR data. It promises to automatically abstract outcomes and other clinical entities from notes across all cancers.
19
Chen, Jiajia, Daqing Zhang, Wenying Yan, Dongrong Yang, and Bairong Shen. "Translational Bioinformatics for Diagnostic and Prognostic Prediction of Prostate Cancer in the Next-Generation Sequencing Era." BioMed Research International 2013 (2013): 1–13. http://dx.doi.org/10.1155/2013/901578.
Full textAbstract:
The discovery of prostate cancer biomarkers has been boosted by the advent of next-generation sequencing (NGS) technologies. Nevertheless, many challenges still exist in exploiting the flood of sequence data and translating them into routine diagnostics and prognosis of prostate cancer. Here we review the recent developments in prostate cancer biomarkers by high throughput sequencing technologies. We highlight some fundamental issues of translational bioinformatics and the potential use of cloud computing in NGS data processing for the improvement of prostate cancer treatment.
20
Lee, Kyeryoung, Zongzhi Liu, Meng Ma, et al. "Analyzing treatment patterns and time to the next treatment in chronic lymphocytic leukemia real-world data using automated temporal phenotyping." Journal of Clinical Oncology 39, no. 15_suppl (2021): e19512-e19512. http://dx.doi.org/10.1200/jco.2021.39.15_suppl.e19512.
Full textAbstract:
e19512 Background: Targeted therapy is an important treatment for chronic lymphocytic leukemia (CLL). However, optimal strategies for deploying small molecule inhibitors or antibody therapies in the real world are not well understood, largely due to a lack of outcomes data. We implemented a novel temporal phenotyping algorithm pipeline to derive lines of therapy (LOT) and disease progression in CLL patients. Here, the CLL treatment pattern and time to the next treatment (TTNT) were analyzed in real-world data (RWD) using patient electronic health records. Methods: We identified a CLL cohort with LOT from the Mount Sinai Data Warehouse (2003-2020). Each LOT consisted of either a single agent or combinations defined by NCCN CLL guidelines. We developed a natural language processing (NLP)-based temporal phenotyping approach to automatically identify the number of lines and therapeutic regimens. The sequence of treatment and time interval for each patient were derived from the systematic treatment data. Time to event analysis and multivariate (i.e., age, gender, race, other treatment patterns) Cox proportional hazard (CoxPH) models were used to analyze the patterns and predictors of TTNT. Results: Four hundred eleven CLL patients received 1 to 7 LOTs. Ibrutinib was the predominant 1st LOT (40.8% of patients) followed by anti-CD20-based antibody therapies and chemotherapy in 30.6 and 19.2% of patients, respectively, followed by Acalabrutinib, Venetoclax, and Idelalisib in 3.4, 2.7, and 0.7% of patients, respectively (Table 1). The 2nd to 5th LOT showed the same or similar trends. We next analyzed the TTNT in the 1st line of each therapeutic class. Acalabrutinib resulted in a longer median TTNT than Ibrutinib. Both Acalabrutinib and Ibrutinib showed longer TTNT compared to Venetoclax (median TTNTs were 742 and 598 vs. 373 days: HR = 0.23, p=0.015 and HR = 0.48, p=0.03, respectively). In addition, patients with age equal to or older than 65 showed longer TNNT (HR=0.16, p=0.016). Conclusions: Our result shows the potential of RWD usage in clinical decision making as real-world evidence reported here is consistent with results derived from clinical trial data. Linking this study to genetic data and other covariates affecting treatment outcomes may provide additional insights into the optimal sequences of the targeted therapies in CLL. Table 1: Therapeutic class and patient numbers (%) in each line.[Table: see text]
21
Arko, Darja, and Iztok Takac. "Inquiry and computer program Onko-Online: 25 years of clinical registry for breast cancer at the University Medical Centre Maribor." Radiology and Oncology 53, no. 3 (2019): 348–56. http://dx.doi.org/10.2478/raon-2019-0043.
Full textAbstract:
Abstract Background High-quality routine care data collected in the clinical registry play a significant role in improving the management of cancer patients. Clinical cancer registries record important data in the course of cancer diagnosis, treatment, follow-up and survival. Analyses of such comprehensive data pool make it possible to improve the quality of patients care and compare with other health care providers. Methods The first inquiry at the Department of Gynaecologic and Breast Oncology of the then General Hospital Maribor to follow breast cancer patients has been introduced in 1994. Based on our experience and new approaches in breast cancer treatment, the context of inquiry has been changed and extended to the present form, which served as a model for developing a relevant computer programme named Onko-Online in 2014. Results During the 25-year period, we collected data from about 3,600 breast cancer patients. The computer program Onko-Online allowed for quick and reliable collection, processing and analysis of 167 different data of breast cancer patients including general information, medical history, diagnostics, treatment, and follow-up. Conclusions The clinical registry for breast cancer Onko-Online provides data that help us to improve diagnostics and treatment of breast cancer patients, organize the daily practice and to compare the results of our treatment to the national and international standards. A limitation of the registry is the potentially incomplete or incorrect data input by different healthcare providers, involved in the treatment of breast cancer patients.
22
Kehl, Kenneth L., Wenxin Xu, Eva Lepisto, et al. "Natural Language Processing to Ascertain Cancer Outcomes From Medical Oncologist Notes." JCO Clinical Cancer Informatics, no. 4 (September 2020): 680–90. http://dx.doi.org/10.1200/cci.20.00020.
Full textAbstract:
PURPOSE Cancer research using electronic health records and genomic data sets requires clinical outcomes data, which may be recorded only in unstructured text by treating oncologists. Natural language processing (NLP) could substantially accelerate extraction of this information. METHODS Patients with lung cancer who had tumor sequencing as part of a single-institution precision oncology study from 2013 to 2018 were identified. Medical oncologists’ progress notes for these patients were reviewed. For each note, curators recorded whether the assessment/plan indicated any cancer, progression/worsening of disease, and/or response to therapy or improving disease. Next, a recurrent neural network was trained using unlabeled notes to extract the assessment/plan from each note. Finally, convolutional neural networks were trained on labeled assessments/plans to predict the probability that each curated outcome was present. Model performance was evaluated using the area under the receiver operating characteristic curve (AUROC) among a held-out test set of 10% of patients. Associations between curated response or progression end points and overall survival were measured using Cox models among patients receiving palliative-intent systemic therapy. RESULTS Medical oncologist notes (n = 7,597) were manually curated for 919 patients. In the 10% test set, NLP models replicated human curation with AUROCs of 0.94 for the any-cancer outcome, 0.86 for the progression outcome, and 0.90 for the response outcome. Progression/worsening events identified using NLP models were associated with shortened survival (hazard ratio [HR] for mortality, 2.49; 95% CI, 2.00 to 3.09); response/improvement events were associated with improved survival (HR, 0.45; 95% CI, 0.30 to 0.67). CONCLUSION NLP models based on neural networks can extract meaningful outcomes from oncologist notes at scale. Such models may facilitate identification of clinical and genomic features associated with response to cancer treatment.
23
Qiu, Hongquan, Dongzhi Wang, and Haiyan Miao. "Analysis of the Effect of Robots in the Treatment of Pancreatic Cancer Based on Smart Medicine." Journal of Healthcare Engineering 2021 (September 18, 2021): 1–12. http://dx.doi.org/10.1155/2021/9734882.
Full textAbstract:
In order to study the effect of robots in the treatment of pancreatic cancer in the context of smart medical, this paper improves the robot recognition technology and data processing technology and improves the system kernel algorithm through the hash algorithm. Unlike the traditional sequencing method that directly uses the gray average value as a feature, the hash algorithm calculates the gray three-average value of each frame block and uses the difference of the three-average value of adjacent frame blocks to perform detection. Moreover, this paper proposes a detection and localization scheme based on hash local matching, which consists of two parts: coarse matching and fine matching. In addition, this paper designs a control experiment to analyze the effect of robots in the treatment of pancreatic cancer, counts multiple sets of data, and uses mathematical statistics to process and visually display the experimental data. The research shows that the robot has a good clinical effect in the treatment of pancreatic cancer.
24
Somashekhar, S. P., Martín-J. Sepúlveda, Andrew D. Norden, et al. "Early experience with IBM Watson for Oncology (WFO) cognitive computing system for lung and colorectal cancer treatment." Journal of Clinical Oncology 35, no. 15_suppl (2017): 8527. http://dx.doi.org/10.1200/jco.2017.35.15_suppl.8527.
Full textAbstract:
8527 Background: IBM Watson for Oncology is an artificial intelligence cognitive computing system that provides confidence-ranked, evidence-based treatment recommendations for cancer. In the present study, we examine the level of agreement for lung and colorectal cancer therapy between the multidisciplinary tumour board from Manipal Comprehensive Cancer Centre in Bangalore, India, and Watson for Oncology. Methods: Watson for Oncology is a Memorial Sloan Kettering Cancer Center (New York, USA) trained cognitive computing system that uses natural language processing and machine learning to provide treatment recommendations. It processes structured and unstructured data from medical literature, treatment guidelines, medical records, imaging, lab and pathology reports, and the expertise of Memorial Sloan Kettering experts to formulate therapeutic recommendations. Treatment recommendations are provided in three categories: recommended, for consideration and not recommended. In this report we provide the results of the independent and blinded evaluation by the multidisciplinary tumour board and Watson for Oncology of 362 total cancer cases comprised of 112 lung, 126 colon and 124 rectal cancers seen at the Centre within the last three years. The recommendations of the two agents were compared for agreement and considered concordant when the tumour board recommendation was included in the recommended or for consideration categories of the treatment advisor. Results: Overall, treatment recommendations were concordant in 96.4% of lung, 81.0% of colon and 92.7% of rectal cancer cases. By tumour stage, treatment recommendations were concordant in 88.9% of localized and 97.9% of metastatic lung cancer, 85.5% of localized and 76.6% of metastatic colon cancer, and 96.8% of localized and 80.6% of metastatic rectal cancer. Conclusions: Treatment recommendations made by the Manipal multidisciplinary tumour board and Watson for Oncology were highly concordant in the cancers examined. This cognitive computing technology holds much promise in helping oncologists make information intensive, evidence based treatment decisions.
25
Park, Keunchil, Hyun Ae Jung, Jong-Mu Sun, et al. "10-year patient journey of stage III non-small cell lung cancer patients: A single-center, observational, retrospective study in Korea real-time automatically updated data warehouse in health care (UNIVERSE - ROOT study)." Journal of Clinical Oncology 37, no. 15_suppl (2019): 8536. http://dx.doi.org/10.1200/jco.2019.37.15_suppl.8536.
Full textAbstract:
8536 Background: The current standard of care (SoC) for locally advanced stage III NSCLC is concurrent chemoradiotherapy (CCRT) but the outcomes are poor and unsatisfactory. The purpose of this study is to analyze the clinical features of patients with locally advanced lung cancer for 10 years in order to help develop future treatment strategy. Methods: This study through big data analysis retrospectively collected de-identified patient data from clinical data warehouse (CDW) using an unique algorithm with Standard Query Language (SQL). This new algorithm was developed by the close interactive collaboration between senior data scientists and medical oncologists. These algorithms include clinical natural language processing (NLP) systems that generate structured information from unstructured free text and structured data capture (SDC). We performed pre-processing work and data quality management (DQM) operation using over 700 clinical variables from 23,735 patients with NSCLC. Through data extraction, transformation, cleansing, and organization, we have developed a systematic and optimized program for lung cancer cohorts, including clinical features and molecular study and outcomes. It is also automatically updated every 24 hours in real time. Results: In the past 10 years, 23,735 patients were diagnosed with NSCLC and complete clinical data were available in 22,718 patients (95.7%). Out of total 22,718 patients 4,138 (18.2%) were diagnosed with stage III NSCLC. Among them, 2,676 patients (64.7%) received any type(s) of anti-cancer treatments or regular follow up at our institute. Of these 2,676 patients, 1,275 (47.6%) received curative surgery (+/- neo- and/or adjuvant CCRT); 685 (25.6%) patients definitive CCRT ; 220 (8.2%) patients palliative thoracic RT; 76 (2.8%) patients best supportive care. Median OS was 48.0 months for neoadjuvant CCRT followed by curative surgery, 51.8 months for curative surgery +/- adjuvant treatment, 29.4 months for unresected definitive CCRT (PFS 10.0 months (range: 9.1-10.9). Molecular profiles as well as updated clinical data will be presented. Conclusions: This unique in-house algorithm enables us to do a rapid and comprehensive analysis of the big data through CDW, which can be also automatically updated daily. This should provide clinically relevant information about real-world treatment outcomes and help implement or develop new treatment strategy in a timely manner.
26
Aggarwal, Sangeeta, Mingfeng Liu, Rishi Sharma, et al. "Voice of Cancer Patients: Analysis of patient concerns regarding cognitive deficits associated with treatment for breast cancer." Journal of Clinical Oncology 33, no. 28_suppl (2015): 82. http://dx.doi.org/10.1200/jco.2015.33.28_suppl.82.
Full textAbstract:
82 Background: Patients undergoing breast cancer treatment often report Symptoms of Cognitive Deficit (SCD). Many of them share their experiences on online forums, which contain millions of freely shared messages that can be used to analyze these SCD. Unfortunately, this data is unstructured, making it difficult to analyze. In this project we organize this data using methods from Big Data Science (BDS) and analyze it by creating a Decision Support System (DSS): an interface that can be used by patients and providers to understand how SCD are associated with specific types – hormonal only (HT), chemo only (CT), or both (CT/HT) – of breast cancer therapies. Methods: We collected 3.5 million unique messages from 20 unrestricted breast cancer forums that provide clinically relevant information. We next built custom ontologies for breast cancer treatments, SCD, and supportive therapies. Then, we created a DSS using methods from BDS, including topic modeling, information retrieval, and natural language processing to extract the relevant data from these messages. We also used token windows and co-occurrence-based algorithms to associate treatment with SCD and supportive therapies. To use this system, a user provides disease-related parameters and the treatment. The DSS then gives the percentage of messages discussing SCD for a similar cohort of patients and the percentage of messages that discuss supportive therapies for each of these SCD. Results: We found 15719 messages that had strong association of SCD with treatments. 3355 messages were from HT patients, 5740 messages were from CT patients, and 9095 messages were from CT/HT patients. Among HT, 28.18% patients taking aromatase inhibitors and 19.20% taking tamoxifen associated SCD to HT. Among CT, 35.26% patient receiving taxane containing chemo associated SCD to CT. SCD worsened during HT for CT/HT patients. Suggestive therapy: 80 messages found Vitamin B12 and B6 useful, 65 suggested Acetyle-L-Carnitine, and 50 suggested playing word games. Conclusions: Using methods from BDS, our DSS reliably associates SCD with HT, CT and CT/CT, and suggests supportive therapies. More research is needed to evaluate the role of supportive therapy for SCD.
27
Proença, Camila A., Tayane A. Freitas, Thaísa A. Baldo, et al. "Use of data processing for rapid detection of the prostate-specific antigen biomarker using immunomagnetic sandwich-type sensors." Beilstein Journal of Nanotechnology 10 (November 6, 2019): 2171–81. http://dx.doi.org/10.3762/bjnano.10.210.
Full textAbstract:
Diagnosis of cancer using electroanalytical methods can be achieved at low cost and in rapid assays, but this may require the combination with data treatment for determining biomarkers in real samples. In this paper, we report an immunomagnetic nanoparticle-based microfluidic sensor (INμ-SPCE) for the amperometric detection of the prostate-specific antigen (PSA) biomarker, the data of which were treated with information visualization methods. The INμ-SPCE consists of eight working electrodes, reference and counter electrodes. On the working electrodes, magnetic nanoparticles with secondary antibodies with the enzyme horseradish peroxidase were immobilized for the indirect detection of PSA in a sandwich-type procedure. Under optimal conditions, the immunosensor could operate within a wide range from 12.5 to 1111 fg·L−1, with a low detection limit of 0.062 fg·L−1. Multidimensional projections combined with feature selection allowed for the distinction of cell lysates with different levels of PSA, in agreement with results from the traditional enzyme-linked immunosorbent assay. The approaches for immunoassays and data processing are generic, and therefore the strategies described here may provide a simple platform for clinical diagnosis of cancers and other types of diseases.
28
Murali, Nikitha, Ahmet Kucukkaya, Alexandra Petukhova, John Onofrey, and Julius Chapiro. "Supervised Machine Learning in Oncology: A Clinician's Guide." Digestive Disease Interventions 04, no. 01 (2020): 073–81. http://dx.doi.org/10.1055/s-0040-1705097.
Full textAbstract:
AbstractThe widespread adoption of electronic health records has resulted in an abundance of imaging and clinical information. New data-processing technologies have the potential to revolutionize the practice of medicine by deriving clinically meaningful insights from large-volume data. Among those techniques is supervised machine learning, the study of computer algorithms that use self-improving models that learn from labeled data to solve problems. One clinical area of application for supervised machine learning is within oncology, where machine learning has been used for cancer diagnosis, staging, and prognostication. This review describes a framework to aid clinicians in understanding and critically evaluating studies applying supervised machine learning methods. Additionally, we describe current studies applying supervised machine learning techniques to the diagnosis, prognostication, and treatment of cancer, with a focus on gastroenterological cancers and other related pathologies.
29
Guan, Meijian, Samuel Cho, Robin Petro, Wei Zhang, Boris Pasche, and Umit Topaloglu. "Natural language processing and recurrent network models for identifying genomic mutation-associated cancer treatment change from patient progress notes." JAMIA Open 2, no. 1 (2019): 139–49. http://dx.doi.org/10.1093/jamiaopen/ooy061.
Full textAbstract:
Abstract Objectives Natural language processing (NLP) and machine learning approaches were used to build classifiers to identify genomic-related treatment changes in the free-text visit progress notes of cancer patients. Methods We obtained 5889 deidentified progress reports (2439 words on average) for 755 cancer patients who have undergone a clinical next generation sequencing (NGS) testing in Wake Forest Baptist Comprehensive Cancer Center for our data analyses. An NLP system was implemented to process the free-text data and extract NGS-related information. Three types of recurrent neural network (RNN) namely, gated recurrent unit, long short-term memory (LSTM), and bidirectional LSTM (LSTM_Bi) were applied to classify documents to the treatment-change and no-treatment-change groups. Further, we compared the performances of RNNs to 5 machine learning algorithms including Naive Bayes, K-nearest Neighbor, Support Vector Machine for classification, Random forest, and Logistic Regression. Results Our results suggested that, overall, RNNs outperformed traditional machine learning algorithms, and LSTM_Bi showed the best performance among the RNNs in terms of accuracy, precision, recall, and F1 score. In addition, pretrained word embedding can improve the accuracy of LSTM by 3.4% and reduce the training time by more than 60%. Discussion and Conclusion NLP and RNN-based text mining solutions have demonstrated advantages in information retrieval and document classification tasks for unstructured clinical progress notes.
30
Yakowec, Jing Jing Wang, Mark Pettengill, Sadiqa Mahmood, Belen Fraile, and Hakim Lakhani. "Building a novel near real-time multisource database to assess and improve infusion wait time at a comprehensive cancer center." Journal of Clinical Oncology 36, no. 30_suppl (2018): 4. http://dx.doi.org/10.1200/jco.2018.36.30_suppl.4.
Full textAbstract:
4 Background: Evidence has shown that long infusion wait time is one of the main contributors to oncology patient dissatisfaction. To identify bottlenecks and inefficient processing, a comprehensive understanding of the infusion workflow at Dana-Farber Cancer Institute was explored. The goal of the project is to leverage existing data sources to quantify time to process completion and to serve as the database for multiple wait time improvement projects. Methods: Infusion workflow from patient check-in or appointment time to first infusion medication administration (wait time) was mapped. Data from Epic and Real-Time Locating System (RTLS) were pulled into a single integrated source in Tableau and SAS for analysis. Using a custom SQL query, the following tables including crucial timestamps were pulled and pooled: encounters, pharmacy processing and dispense, treatment plan and protocol, RTLS events related to infusion chair occupancy, and medication administration records. Further programming was written to flag categories such as investigational versus non-investigational drugs, linked versus un-linked to exam appointments, and inclusion and exclusion criteria regarding date range, infusion floor, and encounter type. Results: The final clean infusion database includes data from September 1, 2017 through the day before current day via automatic data pull. Processing and wait times were analyzed at multiple levels by drug, encounter, department, staff, and protocol. To date, four known wait time improvement projects that aim to shorten processing time, such as early signing of orders by providers, have leveraged this near real-time dataset to monitor and evaluate the impact of the projects. The automation of data to pre-built visualizations in Tableau comparing baseline processing time to post-pilot impact and overall wait time trends has been extremely well received by all improvement stakeholders at the institute. Conclusions: A novel database merging Epic and RTLS data was successfully built to explore and improve infusion patient wait time. This technique can be applied at other institutions interested in reducing wait times and improving patient satisfaction.
31
Alba, Patrick R., Anthony Gao, Kyung Min Lee, et al. "Ascertainment of Veterans With Metastatic Prostate Cancer in Electronic Health Records: Demonstrating the Case for Natural Language Processing." JCO Clinical Cancer Informatics, no. 5 (September 2021): 1005–14. http://dx.doi.org/10.1200/cci.21.00030.
Full textAbstract:
PURPOSE Prostate cancer (PCa) is among the leading causes of cancer deaths. While localized PCa has a 5-year survival rate approaching 100%, this rate drops to 31% for metastatic prostate cancer (mPCa). Thus, timely identification of mPCa is a crucial step toward measuring and improving access to innovations that reduce PCa mortality. Yet, methods to identify patients diagnosed with mPCa remain elusive. Cancer registries provide detailed data at diagnosis but are not updated throughout treatment. This study reports on the development and validation of a natural language processing (NLP) algorithm deployed on oncology, urology, and radiology clinical notes to identify patients with a diagnosis or history of mPCa in the Department of Veterans Affairs. PATIENTS AND METHODS Using a broad set of diagnosis and histology codes, the Veterans Affairs Corporate Data Warehouse was queried to identify all Veterans with PCa. An NLP algorithm was developed to identify patients with any history or progression of mPCa. The NLP algorithm was prototyped and developed iteratively using patient notes, grouped into development, training, and validation subsets. RESULTS A total of 1,144,610 Veterans were diagnosed with PCa between January 2000 and October 2020, among which 76,082 (6.6%) were identified by NLP as having mPCa at some point during their care. The NLP system performed with a specificity of 0.979 and sensitivity of 0.919. CONCLUSION Clinical documentation of mPCa is highly reliable. NLP can be leveraged to improve PCa data. When compared to other methods, NLP identified a significantly greater number of patients. NLP can be used to augment cancer registry data, facilitate research inquiries, and identify patients who may benefit from innovations in mPCa treatment.
32
Lee, Jooyun, Hyeoun-Ae Park, Seul Ki Park, and Tae-Min Song. "Using Social Media Data to Understand Consumers' Information Needs and Emotions Regarding Cancer: Ontology-Based Data Analysis Study." Journal of Medical Internet Research 22, no. 12 (2020): e18767. http://dx.doi.org/10.2196/18767.
Full textAbstract:
Background Analysis of posts on social media is effective in investigating health information needs for disease management and identifying people’s emotional status related to disease. An ontology is needed for semantic analysis of social media data. Objective This study was performed to develop a cancer ontology with terminology containing consumer terms and to analyze social media data to identify health information needs and emotions related to cancer. Methods A cancer ontology was developed using social media data, collected with a crawler, from online communities and blogs between January 1, 2014 and June 30, 2017 in South Korea. The relative frequencies of posts containing ontology concepts were counted and compared by cancer type. Results The ontology had 9 superclasses, 213 class concepts, and 4061 synonyms. Ontology-driven natural language processing was performed on the text from 754,744 cancer-related posts. Colon, breast, stomach, cervical, lung, liver, pancreatic, and prostate cancer; brain tumors; and leukemia appeared most in these posts. At the superclass level, risk factor was the most frequent, followed by emotions, symptoms, treatments, and dealing with cancer. Conclusions Information needs and emotions differed according to cancer type. The observations of this study could be used to provide tailored information to consumers according to cancer type and care process. Attention should be paid to provision of cancer-related information to not only patients but also their families and the general public seeking information on cancer.
33
Dundr, Pavel, David Cibula, Kristýna Němejcová, Ivana Tichá, Michaela Bártů, and Radek Jakša. "Pathologic Protocols for Sentinel Lymph Nodes Ultrastaging in Cervical Cancer." Archives of Pathology & Laboratory Medicine 144, no. 8 (2019): 1011–20. http://dx.doi.org/10.5858/arpa.2019-0249-ra.
Full textAbstract:
Context.— Ultrastaging of sentinel lymph nodes (SLNs) is a crucial aspect in the approach to SLN processing. No consensual protocol for pathologic ultrastaging has been approved by international societies to date. Objective.— To provide a review of the ultrastaging protocol and all its aspects related to the processing of SLNs in patients with cervical cancer. Data Sources.— In total, 127 publications reporting data from 9085 cases were identified in the literature. In 24% of studies, the information about SLN processing is entirely missing. No ultrastaging protocol was used in 7% of publications. When described, the differences in all aspects of SLN processing among the studies and institutions are substantial. This includes grossing of the SLN, which is not completely sliced and processed in almost 20% of studies. The reported protocols varied in all aspects of SLN processing, including the thickness of slices (range, 1–5 mm), the number of levels (range, 0–cut out until no tissue left), distance between the levels (range, 40–1000 μm), and number of sections per level (range, 1–5). Conclusions.— We found substantial differences in protocols used for SLN pathologic ultrastaging, which can impact sensitivity for detection of micrometastases and even small macrometastases. Since the involvement of pelvic lymph nodes is the most important negative prognostic factor, such profound discrepancies influence the referral of patients to adjuvant radiotherapy and could potentially cause treatment failure. It is urgent that international societies agree on a consensual protocol before SLN biopsy without pelvic lymphadenectomy is introduced into routine clinical practice.
34
Kehl, Kenneth L., Stefan Groha, Eva M. Lepisto, et al. "Clinical Inflection Point Detection on the Basis of EHR Data to Identify Clinical Trial–Ready Patients With Cancer." JCO Clinical Cancer Informatics, no. 5 (June 2021): 622–30. http://dx.doi.org/10.1200/cci.20.00184.
Full textAbstract:
PURPOSE To inform precision oncology, methods are needed to use electronic health records (EHRs) to identify patients with cancer who are experiencing clinical inflection points, consistent with worsening prognosis or a high propensity to change treatment, at specific time points. Such patients might benefit from real-time screening for clinical trials. METHODS Using serial unstructured imaging reports for patients with solid tumors or lymphoma participating in a single-institution precision medicine study, we trained a deep neural network natural language processing (NLP) model to dynamically predict patients' prognoses and propensity to start new palliative-intent systemic therapy within 30 days. Model performance was evaluated using Harrell's c-index (for prognosis) and the area under the receiver operating characteristic curve (AUC; for new treatment and new clinical trial enrollment). Associations between model outputs and manual annotations of cancer progression were also evaluated using the AUC. RESULTS A deep NLP model was trained and evaluated using 302,688 imaging reports for 16,780 patients. In a held-out test set of 34,770 reports for 1,952 additional patients, the model predicted survival with a c-index of 0.76 and initiation of new treatment with an AUC of 0.77. Model-generated prognostic scores were associated with annotation of cancer progression on the basis of manual EHR review (n = 1,488 reports for 110 patients with lung or colorectal cancer) with an AUC of 0.78, and predictions of new treatment were associated with annotation of cancer progression on the basis of manual EHR review with an AUC of 0.84. CONCLUSION Training a deep NLP model to identify clinical inflection points among patients with cancer is feasible. This approach could identify patients who may benefit from real-time targeted clinical trial screening interventions at health system scale.
35
Ward, Ashley Vanessa, Shawna B. Matthews, and Carol A. Sartorius. "3300 Progesterone receptor alters lipid biology in luminal breast cancer." Journal of Clinical and Translational Science 3, s1 (2019): 19. http://dx.doi.org/10.1017/cts.2019.46.
Full textAbstract:
OBJECTIVES/SPECIFIC AIMS: These studies seek to evaluate hormonal regulation of luminal breast cancer lipid metabolism and to identify targetable progesterone-mediated changes in lipid biology that contribute to therapeutic resistance in breast cancer. METHODS/STUDY POPULATION: Established and patient-derived luminal breast cancer cell lines, which express ER and PR, were used for this study. RNA transcript and protein expression levels were evaluated by qRT-PCR and immunoblot, respectively. Broad scale lipidomics of progesterone-treated cells was conducted via ultra-high pressure liquid chromatography-mass spectrometry (UHPLC-MS) through the UCD Skaggs School of Pharmacy Mass Spectrometry Core. RESULTS/ANTICIPATED RESULTS: Data mining of previously published microarray data of CK5+ and CK5− syngeneic cancer sublines revealed that CK5+ cells have increased expression of lipid processing genes, including LPL and PPARG. As progestin treatment induces a subpopulation of cells to turn on CK5 expression in luminal breast cancers, UHPLC-MS-based lipidomics analysis will expose whether modulation of the lipid landscape occurs in all cells with progesterone treatment, or whether this phenomenon is heightened specifically in CK5+ cells. I also expect that ER+ breast cancers with progestin induced-altered lipid content, such as lipid droplet formation, will evade therapy-induced death. DISCUSSION/SIGNIFICANCE OF IMPACT: There are numerous approved and developmental therapeutics targeting lipid biology. By determining if progestins alter lipid metabolic genes specifically in CK5+ CSCs, which are endocrine resistant, strategies may be devised to target these resistant cells using combination therapy in conjunction with existing therapies to prevent tumor recurrence.
36
Huang, Xiaofu, Ming Chen, Peizhong Liu, and Yongzhao Du. "Texture Feature-Based Classification on Transrectal Ultrasound Image for Prostatic Cancer Detection." Computational and Mathematical Methods in Medicine 2020 (October 6, 2020): 1–9. http://dx.doi.org/10.1155/2020/7359375.
Full textAbstract:
Prostate cancer is one of the most common cancers in men. Early detection of prostate cancer is the key to successful treatment. Ultrasound imaging is one of the most suitable methods for the early detection of prostate cancer. Although ultrasound images can show cancer lesions, subjective interpretation is not accurate. Therefore, this paper proposes a transrectal ultrasound image analysis method, aiming at characterizing prostate tissue through image processing to evaluate the possibility of malignant tumours. Firstly, the input image is preprocessed by optical density conversion. Then, local binarization and Gaussian Markov random fields are used to extract texture features, and the linear combination is performed. Finally, the fused texture features are provided to SVM classifier for classification. The method has been applied to data set of 342 transrectal ultrasound images obtained from hospitals with an accuracy of 70.93%, sensitivity of 70.00%, and specificity of 71.74%. The experimental results show that it is possible to distinguish cancerous tissues from noncancerous tissues to some extent.
37
Mandelblatt, Jeanne S., Brent J. Small, Gheorghe Luta, et al. "Cancer-Related Cognitive Outcomes Among Older Breast Cancer Survivors in the Thinking and Living With Cancer Study." Journal of Clinical Oncology 36, no. 32 (2018): 3211–22. http://dx.doi.org/10.1200/jco.18.00140.
Full textAbstract:
Purpose To determine treatment and aging-related effects on longitudinal cognitive function in older breast cancer survivors. Methods Newly diagnosed nonmetastatic breast cancer survivors (n = 344) and matched controls without cancer (n = 347) 60 years of age and older without dementia or neurologic disease were recruited between August 2010 and December 2015. Data collection occurred during presystemic treatment/control enrollment and at 12 and 24 months through biospecimens; surveys; self-reported Functional Assessment of Cancer Therapy-Cognitive Function; and neuropsychological tests that measured attention, processing speed, and executive function (APE) and learning and memory (LM). Linear mixed-effects models tested two-way interactions of treatment group (control, chemotherapy with or without hormonal therapy, and hormonal therapy) and time and explored three-way interactions of ApoE (ε4+ v not) by group by time; covariates included baseline age, frailty, race, and cognitive reserve. Results Survivors and controls were 60 to 98 years of age, were well educated, and had similar baseline cognitive scores. Treatment was related to longitudinal cognition scores, with survivors who received chemotherapy having increasingly worse APE scores ( P = .05) and those initiating hormonal therapy having lower LM scores at 12 months ( P = .03) than other groups. These group-by-time differences varied by ApoE genotype, where only ε4+ survivors receiving hormone therapy had short-term decreases in adjusted LM scores (three-way interaction P = .03). For APE, the three-way interaction was not significant ( P = .14), but scores were significantly lower for ε4+ survivors exposed to chemotherapy (−0.40; 95% CI, −0.79 to −0.01) at 24 months than ε4+ controls (0.01; 95% CI, 0.16 to 0.18; P < .05). Increasing age was associated with lower baseline scores on all cognitive measures ( P < .001); frailty was associated with baseline APE and self-reported decline ( P < .001). Conclusion Breast cancer systemic treatment and aging-related phenotypes and genotypes are associated with longitudinal decreases in cognitive function scores in older survivors. These data could inform treatment decision making and survivorship care planning.
38
McBride, Mary L., Patti Groome, Donna Turner, et al. "Using Canadian administrative data to evaluate primary and oncology care of breast cancer patients post-treatment: Subset of the CanIMPACT Study." Journal of Clinical Oncology 34, no. 3_suppl (2016): 5. http://dx.doi.org/10.1200/jco.2016.34.3_suppl.5.
Full textAbstract:
5 Background: CanIMPACT is a multi-provincial Canadian research team funded to identify and address key issues faced by cancer patients and providers at the intersection of primary and specialist oncology care. Canada has national healthcare standards, but provincial/territorial healthcare delivery systems. One facet will use administrative data from the population-based, publicly-funded healthcare system to evaluate issues during pre-diagnosis, treatment, and post-treatment survivorship for breast cancer patients. For the survivorship phase, we aim to conduct the following analyses and compare across provinces: 1) Utilization of physician services overall and by specialty, including oncologists, non-oncology specialists, and primary care; 2) Assessment of adherence to ASCO and Canadian follow-up guideline for breast cancer care, use of surveillance breast imaging, and metastatic investigations; 3) Assessment of adherence to recommended care of chronic illness and preventive care; 4) Quantification of the cost of follow-up overall and by specialty; 5) Comparison of inter- and intra-provincial variation for all outcomes by health administrative region and for vulnerable groups (age ≥ 75 at diagnosis, northern/rural/remote, low income, immigrants), and examine the effect of continuity of primary care and chronic disease on post-treatment care. Methods: Patients will be identified from provincial cancer registries and linked to data extracted from: outpatient physician service claims, hospital inpatient and outpatient data, and cancer facility medical records. Results: Participating provinces have finalized the core questions and detailed protocols, and assessed data comparability. They are in the process of obtaining the required ethics and data access approvals, and data acquisition for processing and analysis. Conclusions: Results will address existing information gaps that can be used to improve transition and care across the cancer care trajectory. Importantly, results will be combined with those of a CanIMPACT qualitative study to inform design of a pragmatic randomized trial focused on improving coordination and quality of care.
39
Thakur, Varsha, Juliano Tiburcio de Freitas, Yuan Li, Keman Zhang, Alyssa Savadelis, and Barbara Bedogni. "MT1-MMP-dependent ECM processing regulates laminB1 stability and mediates replication fork restart." PLOS ONE 16, no. 7 (2021): e0253062. http://dx.doi.org/10.1371/journal.pone.0253062.
Full textAbstract:
Radiotherapy remains a mainstay of treatment for a majority of cancer patients. We have previously shown that the membrane bound matrix metalloproteinase MT1-MMP confers radio- and chemotherapy resistance to breast cancer via processing of the ECM and activation of integrinβ1/FAK signaling. Here, we further discovered that the nuclear envelope protein laminB1 is a potential target of integrinβ1/FAK. FAK interacts with laminB1 contributing to its stability. Stable laminB1 is found at replication forks (RFs) where it is likely to allow the proper positioning of RF protection factors, thus preventing RF degradation. Indeed, restoration of laminB1 expression rescues replication fork stalling and collapse that occurs upon MT1-MMP inhibition, and reduces DNA damage in breast cancer cells. Together, these data highlight a novel mechanism of laminB1 stability and replication fork restart via MT1-MMP dependent extracelluar matrix remodeling.
40
Satbir, Thakur, Son Tran, Mohit Jain, et al. "A Novel Anti-Cancer Vaccine Approach for the Treatment of High-Risk Leukemia in Children." Blood 136, Supplement 1 (2020): 25. http://dx.doi.org/10.1182/blood-2020-143381.
Full textAbstract:
Introduction: There is strong experimental and clinical data to indicate the critical involvement of immune evasion in relapsed leukemia in children. A well-defined characteristic of refractory leukemia is the accumulation of genetic aberrations and mutations that may act as drivers or passengers in the process of tumor recurrence. Many of these mutations get translated into proteins that contain tumor-specific immune-stimulatory epitopes (neoantigens) that can elicit host antitumor immune responses. Although, in general, the mutation rate is lower in pediatric tumors, recent studies have shown that almost 90% of pediatric leukemias carry potentially actionable neoepitopes. In this study, we describe the results from a comprehensive experimental approach of neoantigen prediction coupled with antigen processing and HLA-binding prediction algorithms with in vitro validation assays for the generation of neoantigen vaccines against high-risk leukemias in children. Methods: DNA and RNA from leukemia cells and matched fibroblasts were obtained. Raw reads were aligned to human reference genome and somatic variants (SNVs) were called using Strelka v1.0.1441. RNA-seq data from leukemic cells were used to predict neoantigen expression levels resulting from SNVs using STAR (2.4.1)12 and Cufflinks v2.2.1. Normalized expression data were then cross-referenced with the list of SNVs to identify leukemia-specific mutant proteins. HLA typing for each sample was carried out from RNA-seq data using seq2HLA v2.2. Using the patient's HLA phenotype, we then used NetMHCons v1.1 to predict short peptides derived from leukemia-specific mutant proteins that will bind to autologous HLA Class I molecules. These 8/9-mers were filtered to predict a high likelihood of proteasomal or immune-proteasomal processing and transporter associated with antigen processing (TAP) using NetChop v3.1 and the immune epitope database (IEDB), respectively. The peptides identified were rank-ordered based on the composite immunogenicity score derived from MHC class I binding affinities, proteasomal processing and TCR binding predictions and synthesized accordingly. Peripheral blood derived dendritic cells (DCs) and CD8+ T-cells were isolated and expanded in culture with relevant cytokines. The DCs were pulsed with peptides and then co-cultured with CD8+ T-cells. After five days, the primed CD8+ T-Cells were separated, washed and exposed to the patient's leukemic cells at varying ratios and the leukemia specific CD8+ T-cell activation was quantified by IFN gamma secretion using ELISpot assays. Results: In the leukemia specimen studied, approximately 5% of all on-target germline mutations were found only in leukemic cells. Tumor mutational burden was, on average, 0.34 mut/Mb. Analysis of the highest ranking synthetic peptides (approximately 10 per leukemia sample) showed leukemia-specific activation of patient's T-cells as measured by the mean number of spots observed in ELISpot assays. For example, in patient one (15 year old male, high-risk ALL, one year off therapy), 14 individual short sequences were identified and corresponding peptides were synthesized. Among these, three peptides were not soluble and three peptides showed significant activity above controls. Maximum leukemia specific T-cell activation was noted with peptide #7 QQSALVLL (mean 135 ELISpots compared to 72 in controls, p&lt;0.05, triplicate) indicating a strong nonantigenic potential in this region. Furthermore, this activity was significantly diminished when an extra amino acid was added to this peptide (LQQSALVLL, mean 79 spots) showing the specificity of the approach. A number of other peptides and combinations in non-overlapping regions gave intermediate activities. Discussion: Completed data, including the vaccine peptide sequences and corresponding activities showed the feasibility of identifying pediatric leukemia neoantigen sequences in personalized mutational landscapes of these patients. In addition, we have provided an in vitro experimental approach to validate the potential of such vaccines in future clinical studies and this methodology can also be used to identify agents for effective combinations such as immune checkpoint inhibitors. A clinical trial using these strategies is in development for the treatment of high-risk leukemia in children. Disclosures No relevant conflicts of interest to declare.
41
Marias, Kostas. "The Constantly Evolving Role of Medical Image Processing in Oncology: From Traditional Medical Image Processing to Imaging Biomarkers and Radiomics." Journal of Imaging 7, no. 8 (2021): 124. http://dx.doi.org/10.3390/jimaging7080124.
Full textAbstract:
The role of medical image computing in oncology is growing stronger, not least due to the unprecedented advancement of computational AI techniques, providing a technological bridge between radiology and oncology, which could significantly accelerate the advancement of precision medicine throughout the cancer care continuum. Medical image processing has been an active field of research for more than three decades, focusing initially on traditional image analysis tasks such as registration segmentation, fusion, and contrast optimization. However, with the advancement of model-based medical image processing, the field of imaging biomarker discovery has focused on transforming functional imaging data into meaningful biomarkers that are able to provide insight into a tumor’s pathophysiology. More recently, the advancement of high-performance computing, in conjunction with the availability of large medical imaging datasets, has enabled the deployment of sophisticated machine learning techniques in the context of radiomics and deep learning modeling. This paper reviews and discusses the evolving role of image analysis and processing through the lens of the abovementioned developments, which hold promise for accelerating precision oncology, in the sense of improved diagnosis, prognosis, and treatment planning of cancer.
42
Kit, O. I., Yu A. Gevorkyan, N. V. Soldatkina, et al. "Prognostic factors in colorectal cancer." Koloproktologia 20, no. 2 (2021): 42–49. http://dx.doi.org/10.33878/2073-7556-2021-20-2-42-49.
Full textAbstract:
Aim: to evaluate prognostic factors in colorectal cancer.Material and methods: published data (publications in PubMed, Scopus, eLIBRARY databases) and own results of treatment of 47 patients with T2-4N0-2M0 colon cancer in 2017–2018. The following prognostic factors were studied: metastasis in regional lymph nodes, tumor site, CEA level, KRAS and BRAF mutation status, microsatellite instability, MUSASHI2, p53, VEGF.Results: a correlation between tumor progression and the status of regional lymph nodes demonstrated significant differences (p = 0.038): in N0, the risk of progression was 3.8%, in N1 — 14.9%, in N2 — 43.6%. Statistical processing of the results did not reveal significant differences between groups of patients without and with cancer generalization by their age, gender, tumor site, type of lymph node dissection, T stage, differentiation of adenocarcinoma, levels of CEA, mutations of KRAS, MSI, p53, MUSASHI2, VEGF. We used these prognostic factors to determine biological features of the tumor, its aggressiveness and treatment approaches.Conclusions: the status of regional lymph nodes remains the main factor in determining the prognosis of a colon tumor and in the medical therapy appointment. Molecular genetic factors are currently of great importance for determining tactics in personalized medical treatment.
43
Dr. Selvarani Rangasamy, Mrs Disha Sushant Wankhede,. "REVIEW ON DEEP LEARNING APPROACH FOR BRAIN TUMOR GLIOMA ANALYSIS." INFORMATION TECHNOLOGY IN INDUSTRY 9, no. 1 (2021): 395–408. http://dx.doi.org/10.17762/itii.v9i1.144.
Full textAbstract:
Brain tumor diagnosis has evolved as a very critical need in current medical diagnosis. Early diagnosis of tumor detection is an important need for the primitive treatment of brain tumor patient increasing the survival rate of patient. MRI diagnosis of brain tumor for cancer treatment is a large processing due to volumetric content of scan sample. The processing of clinical data is large and consumes a high processing time. Hence, the need of early diagnosis and proper segmentation of brain tumor region is in need. This paper outlines a review on the developments of MRI sample processing for early diagnosis for brain tumor glioma diagnosis using deep learning approach. The advantage of learning capability and finer processing efficiency has gained an advantage in MRI image processing, which enable a better processing efficiency and accuracy in early diagnosis. Deep learning approach has shown a benefit of image coding based on selective features and state of art processing in diagnosis. The evaluation objective of the MRI sample processing has shown a better accuracy than the comparative existing approaches. The recent trends, the advantages and limitation of the existing approach for MRI diagnosis is outlined.
44
McDonald, Brenna C., Susan K. Conroy, Tim A. Ahles, John D. West, and Andrew J. Saykin. "Alterations in Brain Activation During Working Memory Processing Associated With Breast Cancer and Treatment: A Prospective Functional Magnetic Resonance Imaging Study." Journal of Clinical Oncology 30, no. 20 (2012): 2500–2508. http://dx.doi.org/10.1200/jco.2011.38.5674.
Full textAbstract:
Purpose To prospectively examine alterations in working memory (WM) –associated brain activation related to breast cancer and treatment by using functional magnetic resonance imaging. Patients and Methods Patients treated with chemotherapy (CTx+; n = 16) or without chemotherapy (CTx−; n = 12) and healthy controls (n = 15) were scanned during an n-back task at baseline (after surgery but before radiation, chemotherapy, and/or antiestrogen treatment), 1 month after completion of chemotherapy (M1), and 1 year later (Y1), or at yoked intervals for CTx− and controls. SPM5 was used for all image analyses, which included cross-sectional between-group and group-by-time interaction and longitudinal within-group analyses, all using a statistical threshold of 0.001. Results At baseline, patients with cancer showed increased bifrontal and decreased left parietal activation compared with controls. At M1, both cancer groups showed decreased frontal hyperactivation compared with controls, with increased hyperactivation at Y1. These cross-sectional findings were confirmed by group-by-time interaction analyses, which showed frontal activation decreases from baseline to M1 in patients compared with controls. Within-group analyses showed different patterns of longitudinal activation change by treatment group (CTx+ or CTx−), with prominent alterations in the frontal lobes bilaterally. Conclusion Significant frontal lobe hyperactivation to support WM was found in patients with breast cancer. Superimposed on this background, patients showed decreased frontal activation at M1, with partial return to the previously abnormal baseline at Y1. These functional changes correspond to frontal lobe regions where we previously reported structural changes in this cohort and provide prospective, longitudinal data that further elucidate mechanisms underlying cognitive effects related to breast cancer and its treatment.
45
Mishra, Mark Vikas, Michele Bennett, Armon Vincent, et al. "Natural language processing (NLP) of Internet conversations to evaluate prostate cancer (PC) patients’ perceptions of active surveillance (AS)." Journal of Clinical Oncology 30, no. 34_suppl (2012): 14. http://dx.doi.org/10.1200/jco.2012.30.34_suppl.14.
Full textAbstract:
14 Background: Less than 10% of qualifying PC patients receive primary management with AS. Qualitative research aimed at identifying patient acceptance of AS has been identified as a national health research priority. The primary objective of this study was to determine if NLP of anonymous internet conversations (ICs) could be utilized to identify unmet public needs regarding AS. Methods: After obtaining IRB approval, English-language ICs regarding PC treatment with AS from 2002-2012 were identified using a novel internet search methodology. Web spiders were developed to identify, mine, and gather content from the internet for ICs centered on AS. All ICs identified were screened programmatically to remove any not-on-topic ICs. Collection of ICs was not restricted to any specific geographic region of origin. NLP was used to evaluate content and perform a sentiment analysis. Conversations were scored as positive, negative, or neutral. A sentiment index (SI) was subsequently calculated according to the following formula to compare temporal trends in public sentiment towards AS: [(#Positive IC/#Total IC) – (#Negative IC/#Total IC) x 100]. Results: A total of 464 ICs were identified. Sentiment increased from -13 to +2 over the study period. The increase sentiment has been driven by increased patient emphasis on quality-of-life factors and endorsement of AS by national medical organizations. Unmet needs identified in these ICs include: a gap between quantitative data regarding long-term outcomes with AS versus conventional treatments, desire for treatment information from an unbiased specialist, and absence of public role models managed with AS. Conclusions: This study demonstrates the potential utility of NLP to analyze ICs in order to provide insight into patient preferences and decision-making. Based on our findings, we recommend that multidisciplinary clinics consider including an unbiased specialist to present treatment options and that future decision tools for AS include quantitative data regarding outcomes after AS, so that patients can make decisions with an amount of information that is more similar to the resources available regarding radiation or surgery.
46
Subarna Chatterjee and Kiran Rao P. "Diagnosis of Kidney Renal Cell Tumor through Clinical data mining and CT scan image processing: A Survey." International Journal of Research in Pharmaceutical Sciences 11, no. 1 (2020): 13–24. http://dx.doi.org/10.26452/ijrps.v11i1.1778.
Full textAbstract:
This study deals with the systematic study of the mining of data and medical image-based CAD to classify or predict Kidney Renal (KRCC) tumors. Kidney tumors are of different types having different characteristics and have different methodologies to classify or predict tumor and its stages. KRCC is the most common type of cancer of the kidney, but there are others. Several factors may increase the risk of a person developing KRCC disease like smoking, obesity, High blood pressure, and many more. In almost all cases, only a single kidney is affected, but in rare cases, both can be affected by KRCC. As cancer grows, it may invade structures near the kidney, such as surrounding fatty tissue, veins, renal gland, or the liver. It might also spread to other parts of the body, such as the lungs or bones. It becomes essential to detect the KRCC tumor and classify it at the early stage to assist the pathologist in identifying the cause and severity of the tumor and in monitoring treatment. The pathologist examines the kidney diseases by using two different modes of data (Medical images and clinical databases). In this study, we reviewed different CAD tools to classify or predict KRCC tumor and its stages. For this study, two groups of methods that are data mining and medical image processing methods are selected. These methods allow the accurate quantification and classification of KRCC tumors from the clinical tools. Computer-assisted medical image and clinical database analysis show excellent potential for tumor diagnosis and monitoring.
47
Shen, Lujun, Wang Li, Chen Chen, Feng Shi, and Peihong Wu. "Dynamically trace the prognosis of patients with hepatocellular carcinoma through constructing survival paths with time-series data." Journal of Clinical Oncology 35, no. 15_suppl (2017): e15636-e15636. http://dx.doi.org/10.1200/jco.2017.35.15_suppl.e15636.
Full textAbstract:
e15636 Background: Hepatocellular carcinoma (HCC) is featured by high risk of local recurrence and intrahepatic metastasis, and always requires repeated treatment. A novel prognostic system maximally utilizes time-series data and facilitates dynamic prognosis prediction is warranted. Methods: 1341 BCLC stage B HCC patients received treatment at Sun Yat-sen University Cancer Center from Jan, 2007 to Dec, 2012 were enrolled (979 pts for derivation, 362 pts for validation). Time-series data on serum tumor markers, biochemical and hematological index, medical imaging and associated changes (CT and/or MRI) were collected. Every 3 months represented an individual time point and a total of 9 time points were defined (Table 1); data in each time interval were allocated to associated time point. To construct the survival path, the derivation cohort was sequentially divided into subgroups by one selected feature in each time point; the feature selection criteria were: 1. independent prognostic factor in Cox model; 2. most impactful based on the change of -2Log likelihood after elimination from the model. The survival path of HCC patients was further visualized and its predictive value at each time point was compared with BCLC staging system. Results: Based on the time-series data of derivation cohort, we divided the population into 13 different paths with distinct response of treatment. The survival path system showed superior prognostic value than BCLC staging system at all time points except for the no.2 time point (Table). The validation cohort showed consistent finding. Conclusions: The methodology of survival path was valuable in dynamically tracing the prognosis of HCC patients and could further facilitate treatment planning. The visualization of data by survival path could be a new tool in processing the big data of cancer in the future. [Table: see text]
48
Joly, Florence, Marie Lange, Natacha Heutte, et al. "Baseline cognitive functions among elderly patients with localized breast cancer." Journal of Clinical Oncology 31, no. 15_suppl (2013): 9510. http://dx.doi.org/10.1200/jco.2013.31.15_suppl.9510.
Full textAbstract:
9510 Background: Cognitive deficits (CD) were reported among patients receiving chemotherapy (CT) for cancer, but could also be observed before treatment. Elderly patients were poorly studied although they are more prone to present age-related CD and CD onset or enhancement during CT. This study assessed baseline cognitive functions among elderly localized breast cancer (LBC) patients before adjuvant treatment therapy. Methods: Episodic memory, working memory, executive functions and information processing speed were assessed with neuropsychological tests. Validated questionnaires were used to assess subjective CD, anxiety, depression and fatigue before adjuvant treatment. Geriatric assessment was also realized. Objective CD were defined as a score less than 1.5 standard deviation (SD) of normative data on >2 tests, or less than two SDs on >1 test. Significant subjective CD (evaluated by the FACT-Cog) were defined when the 4 subscales below the first tercile distribution. Results: Results concern 123 elderly LBC (71±4 years): planned treatment included CT and radiotherapy (RT) for 61 patients and RT only for 62 patients. Characteristics are as follows: mastectomy (28%), stage (I: 60%, II: 27%, III: 13%), positive hormonal receptor (88%) and positive Her2 (17%). Before any adjuvant treatment, objective CD were observed in 40% of patients (46% in CT group, episodic memory mainly impaired and 37% in RT group, executive functions and information processing speed mainly impaired). No relation was observed between cancer stage, geriatric frailty and objective CD. Twenty nine percents of patients presented fatigue, 6% anxiety and 10% depression. These variables were not related to objective CD but they were related to subjective CD. Conclusions: More than 40% of elderly LBC patients presented objective CD before any adjuvant therapy that is higher than observed among younger patients. It is important to take account in the decision making of adjuvant treatment in elderly patients. Clinical trial information: NCT01333735.
49
Agelink van Rentergem, Joost A., Ivar E. Vermeulen, Philippe R. Lee Meeuw Kjoe, and Sanne B. Schagen. "Computational Modeling of Neuropsychological Test Performance to Disentangle Impaired Cognitive Processes in Cancer Patients." JNCI: Journal of the National Cancer Institute 113, no. 1 (2020): 99–102. http://dx.doi.org/10.1093/jnci/djaa039.
Full textAbstract:
Abstract There is a need to better identify impaired cognitive processes to increase our understanding of cognitive dysfunction caused by cancer and cancer treatment and to improve interventions. The Trail Making Test is frequently used for evaluating information-processing speed (part A) and executive function (part B), but interpretation of its outcomes is challenging because performance depends on many cognitive processes. To disentangle processes, we collected high-resolution data from 192 non–central nervous system cancer patients who received systemic therapy and 192 cancer-free control participants and fitted a Shifted-Wald computational model. Results show that cancer patients were more cautious than controls (Cohen d = 0.16). Patients were cognitively slower than controls when the task required task switching (Cohen d = 0.16). Our results support the idea that cancer and cancer treatment accelerate cognitive aging. Our approach allows more precise assessment of cognitive dysfunction in cancer patients and can be extended to other instruments and patient populations.
50
Banerjee, Imon, Selen Bozkurt, Jennifer Lee Caswell-Jin, Allison W. Kurian, and Daniel L. Rubin. "Natural Language Processing Approaches to Detect the Timeline of Metastatic Recurrence of Breast Cancer." JCO Clinical Cancer Informatics, no. 3 (December 2019): 1–12. http://dx.doi.org/10.1200/cci.19.00034.
Full textAbstract:
PURPOSE Electronic medical records (EMRs) and population-based cancer registries contain information on cancer outcomes and treatment, yet rarely capture information on the timing of metastatic cancer recurrence, which is essential to understand cancer survival outcomes. We developed a natural language processing (NLP) system to identify patient-specific timelines of metastatic breast cancer recurrence. PATIENTS AND METHODS We used the OncoSHARE database, which includes merged data from the California Cancer Registry and EMRs of 8,956 women diagnosed with breast cancer in 2000 to 2018. We curated a comprehensive vocabulary by interviewing expert clinicians and processing radiology and pathology reports and progress notes. We developed and evaluated the following two distinct NLP approaches to analyze free-text notes: a traditional rule-based model, using rules for metastatic detection from the literature and curated by domain experts; and a contemporary neural network model. For each 3-month period (quarter) from 2000 to 2018, we applied both models to infer recurrence status for that quarter. We trained the NLP models using 894 randomly selected patient records that were manually reviewed by clinical experts and evaluated model performance using 179 hold-out patients (20%) as a test set. RESULTS The median follow-up time was 19 quarters (5 years) for the training set and 15 quarters (4 years) for the test set. The neural network model predicted the timing of distant metastatic recurrence with a sensitivity of 0.83 and specificity of 0.73, outperforming the rule-based model, which had a specificity of 0.35 and sensitivity of 0.88 ( P < .001). CONCLUSION We developed an NLP method that enables identification of the occurrence and timing of metastatic breast cancer recurrence from EMRs. This approach may be adaptable to other cancer sites and could help to unlock the potential of EMRs for research on real-world cancer outcomes.