In the era of Electronic Health Records, it is possible to examine the outcomes of decisions made by doctors during clinical practice to identify patterns of care—generating evidence from the collective experience of patients. We will discuss methods that transform unstructured patient notes into a de-identified, temporally ordered, patient-feature matrix. We will then review four use-cases, which use the resulting de-identified data matrix, to illustrate the learning of practice-based evidence from unstructured data in electronic medical records. By examining patterns, such as the frequency and co-frequency of drug and disease mentions, it is possible to monitor for adverse drug events, learn drug-drug interactions, profile the safety of off-label drug usage, uncover ‘natural experiments’ and generate practice-based evidence for difficult-to-test clinical hypotheses.
Dr. Nigam Shah is Assistant Professor of Medicine (Biomedical Informatics) at Stanford University, Assistant Director of the Center for Biomedical Informatics Research, a member of the Biomedical Informatics Graduate Program and a core member of the National Center for Biomedical Ontology. Dr. Shah recieved the AMIA New Investigator Award for 2013. Dr. Shah integrates teaching into his advanced research work and was recognized with the Biosciences Faculty Teaching Award for outstanding teaching contributions in his graduate class on “Data driven medicine” (Biomedin 215). He holds an MBBS from Baroda Medical College, India, a PhD from Penn State University and completed postdoctoral training at Stanford University. More at:https://cap.stanford.edu/profiles/stanford/Nigam_Shah
IMPORTANT NOTICE: This ReadyTalk service includes a feature that allows audio and any documents and other materials exchanged or viewed during the session to be recorded. By joining this session, you automatically consent to such recordings. If you do not consent to the recording, discuss your concerns with the meeting host prior to the start of the recording or do not join the session. Please note that any such recordings may be subject to discovery in the event of litigation.