Leveraging Medical Big Data for Optimizing Decisions in Healthcare
Leveraging medical big data to optimize medical decisions is crucial in modern healthcare. By integrating various data sources and technologies, such as medical ontology and predictive models, researchers can enhance diagnostic accuracy, treatment outcomes, and patient care. This approach involves mining both text and non-text data to identify patterns, predict values, and support decision-making processes among physicians, patients, and researchers. The potential of big data in healthcare extends to personalized medicine, survival analysis, and improving hospital systems for better patient outcomes.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Medical DataScope: Leveraging Medical Big Data to Optimize Medical Decisions ChengXiang ( Cheng ) Zhai Department of Computer Science Carl R. Woese Institute for Genomic Biology Department of Statistics School of Information Sciences Personalized Nutrition Initiative University of Illinois at Urbana-Champaign czhai@illinois.edu http://czhai.cs.illinois.edu/ VinUni-Illinois Smart Health Center Discussion Meeting, 10/7/2021 1
Text Information Management & Analysis (TIMAN) Group http://timan.cs.uiuc.edu Text Mining Decision Support Information Retrieval Big Raw Data Small Relevant Data Text >300 papers + 3 books Large group of students (graduated 38 PhD students) Funded by government & industry
Opportunities: Big Data meets Patient Care Multiple Predictors (Features) Predicted Values of Real World Variables Diagnosis, optimal treatment, side effects, survival, .. Predictive Model Optimal Decision Making physicians, patients, researchers, Hospital System Joint Mining of Non-Text and Text Sensor 1 Non-Text Data Sensor k Text Data 3
Opportunities: Big Data meets Patient Care Multiple Predictors (Features) Retrieval Predicted Values of Real World Variables Diagnosis, optimal treatment, side effects, survival, .. Predictive Model Medical DataScope Medical Case Optimal Decision Making Diagnosis Literature physicians, patients, researchers Treatment Hospital System Joint Mining of Non-Text and Text Sensor 1 Non-Text Data Survival Analysis Sensor k Knowledge Base Text Data 4
Project 1: Medical Case Retrieval Query: Female patient, 25 years old, with fatigue and a swallowing disorder (dysphagia worsening during a meal). The frontal chest X-ray shows opacity with clear contours in contact with the right heart border. Right hilar structures are visible through the mass. The lateral X-ray confirms the presence of a mass in the anterior mediastinum. On CT images, the mass has a relatively homogeneous tissue density. Find all medical literature articles discussing a similar case We developed techniques to leverage medical ontology and Feedback to improve accuracy. The UIUC-IBM team was ranked #1 in ImageCLEF 2010 evaluation. http://imageclef.org/2010/medical/results Parikshit Sondhi, Jimeng Sun, ChengXiang Zhai, Robert Sorrentino and Martin S. Kohn, Leveraging Medical Thesauri and Physician Feedback for Improving Medical Literature Retrieval for Case Queries, Journal of American Medical Informatics Association (JAMIA), 19(5): 851-858 (2012). 5
Project 2: Extraction of Medical Cases from Medical Forums Medication Treatment, Prevention Measure Physical Examination (PE) Condition, Symptoms, Disease Background (BKG) Neither PE nor MED Many applications: find similar cases, correlate condition and treatment, summarize treatment options Parikshit Sondhi, Manish Gupta, ChengXiang Zhai and Julia Hockenmaier. Shallow Information Extraction from Medical Forum Data, Proceedings of COLING 2010, pages 1158-1166. 6
Project 3: Extraction of Symptom Graphs from EHR EHR (Patient Records) Multi-Level Symptom Graphs Predict the future onset of a disease (e.g., Congestive Heart Failure) for a patient Discovery of symptom profiles of diseases Discovered symptoms improves accuracy of prediction by +10% Parikshit Sondhi, Jimeng Sun, Hanghang Tong, ChengXiang Zhai, SympGraph: A Mining Framework of Clinical Notes through Symptom Relation Graphs, Proceedings of KDD 2012 (KDD'12), pages 1167-1175, 2012 7
Project 4: Discovery of Adverse Drug Reactions from Forums Green: Disease symptoms Blue: Side effect symptoms Red: Drug Drug: Cefalexin ADR: panic attack faint . Sheng Wang, Yanen Li, Duncan Ferguson, and Chengxiang Zhai, SideEffectPTM: An Unsupervised Topic Model to Mine Adverse Drug Reactions from Health Forums, Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (BCB '14), 2014. 8
Sample ADRs Discovered Drug(Freq) Zoloft (84) Drug Use antidepressant Symptoms in Descending Order weigh gain, weight, depression, side effects, mgs, gain weight, anxiety, nausea, head, brain, pregnancy, pregnant, headaches, depressed, tired Ativan, sleep, Seroquel, doc prescribed seroqual, raising blood sugar levels, anti-psychotic drug, diabetic, constipation, diabetes, 10mg, benzo, addicted Topmax, liver, side effects, migraines, headaches, weight, Topamax, pdoc, neurologist, supplement, sleep, fatigue, seizures, liver problems, kidney stones dizziness, stomach, Benadryl, dizzy, tired, lethargic, tapering, tremors, panic attach, head Ativan (33) anxiety disorders Topamax (20) anticonvulsant Ephedrine (2) stimulant Unreported to FDA 9
Project 5. Traditional Chinese medicine (TCM) TCM patient records = experimental results of herbs on patients Potentially discover effective herbs for treating particular groups of patients Effective chemical ingredients in effective herbs Combination with western medicine + genomics + biomedical knowledge Discover new medical knowledge & Provide a scientific foundation for TCM TCM philosophy Individualized experiments Large-space of empirical hypotheses explored Progress (see Edward Huang s dissertation) 4 papers published (ACM BCB 16, IEEE BIBM 16, ACM BCB 17, AMIA 17) Developed general techniques for disease profiling, disease subcategorization, case retrieval, and cancer patient survival analysis Edward Huang, Integrating heterogeneous data into electronic medical record analysis, PhD Dissertation, 2019, UIUC, http://hdl.handle.net/2142/104778 10
Summary Autonomous AI Assistive AI Multiple Predictors (Features) Retrieval Intelligent Task Agents Predicted Values of Real World Variables Diagnosis, optimal treatment, side effects, survival, .. Learning to explore Predictive Model Medical DataScope ... Learning to interact Medical Case Optimal Decision Making Learning to collaborate Diagnosis Literature physicians, patients, researchers, Treatment Hospital System Joint Mining of Non-Text and Text Sensor 1 Non-Text Data Survival Analysis Sensor k Knowledge Base Text Data 11
Towards an intelligent big data system for improved patient care Two kinds of applications Clinical applications: Big data-based intelligent assistant with physicians and patients as users Medical research: Knowledge discovery from big data with medical researchers as users Integration of the two kinds of applications Clinical applications Collection of more data & validation of research results Medical research applications Turn the collected data into medical knowledge to increase the intelligence of clinical application systems 12
Thank You! More information about our work can be found at http://timan.cs.uiuc.edu/ Looking forward to opportunities for collaboration! czhai@Illinois.edu 13
