4:40 - 5:00 pmSaturday, September 6
LK 120
Generating practice-based evidence by mining electronic health records
LK 120
Generating practice-based evidence by mining electronic health records
Assistant Professor, SHC
Roughly 96% of medical care is best guesses. Given the availability electronic medical records (EMR’s), we can make decisions based on what happened to real people like you. We argue that it is possible... Read more

Description

Roughly 96% of medical care is best guesses. Given the availability electronic medical records (EMR’s), we can make decisions based on what happened to real people like you. We argue that it is possible to examine the outcomes of decisions made by doctors during clinical practice to identify patterns of care—generating evidence based on the collective practice of experts -- thus generating practice-based evidence. Using existing Bio-ontologies, and text-proccesing methods it is possible to transform unstructured patient notes into a de-identified, patient-feature matrix that serves as a substrate for high-throughput data-mining studies. Such Big data-mining makes it possible to monitor for adverse drug events, profile specific drugs, identify off-label drug usage, uncover ‘natural experiments’ and evaluate difficult-to-test clinical hypotheses.
 
We will discuss how, by examining the frequency and co-frequency of drug and disease mentions, we can detect associations among drugs and their adverse events about 2 years before an alert is issued as well as learn the prevalence of known drug-drug interactions. Using the patient feature matrix along with prior knowledge about drugs, diseases, and known usage, we can identify potentially risky off-label uses. We can uncover a natural experiment—of CHF patients being prescribed Cilostazol despite a black box warning—and examine the safety of this drug in this high-risk group of patients. We can test a clinical hypothesis about a possible association between allergic conditions and the risk of developing chronic uveitis in children with juvenile idiopathic arthritis.

Dr. Nigam Shah’s research is focused on developing applications of bio-ontologies, specifically building novel approaches to annotate, index, integrate and analyze diverse information types available in biomedicine. Dr. Shah holds an MBBS from Baroda Medical College, India, a PhD from Penn State University, and completed post-doctoral training at the Stanford Medical School.

Contact Us

We're not around right now. But you can send us an email and we'll get back to you, asap.

Not readable? Change text. captcha txt

Start typing and press Enter to search