Data Science Supporting Clinical Decision Making - What, Why, How?

Explore the intersection of data science and clinical decision-making in this 38-minute conference talk. Delve into the opportunities and challenges presented by electronic health records, and discover strategies for making clinical data more usable and effective. Learn about applying natural language processing to transform clinical documentation into structured data for surveillance and prediction applications. Gain insights into patient-derived data, informatics in medicine, evidence-based medicine, and systematic review of evidence. Examine timelines of clinical events, risk prediction for patients with atrial fibrillation, and the differences between structured and unstructured data. Investigate automated information extraction techniques, including family history relation extraction and neural methods. Understand DRG prediction methods, medical data characteristics, and the importance of data reusability in supporting clinical decision-making.

Intro
Heaps of clinical data
Patient-derived data
Informatics in Medicine: Structured representations
Electronic Health Records: Texts!
"Evidence-based" Medicine
Systematic Review of Evidence
Natural Experiments through data
Timelines of clinical events
Clinical journeys captured in data
Answering Clinical Questions with EHR Data
Risk prediction for patients with Atrial Fibrillation
Structured vs Unstructured data
Extracting key concepts
Automated Information Extraction
Family History Relation Extraction
Neural methods for Information Extraction
DRG prediction methods
Medical data characteristics
Reusability