EHR-based Phenotyping Project

This project is developing novel machine-learning approaches and software for automatically phenotyping subjects from their electronic health records (EHRs), and for predicting clinically relevant phenotypes before they are exhibited. These approaches will be used to identify cases and controls for various studies, identify significant risk factors for diseases and disorders of interest, and predict risk for specific clinical events.

Related CPCP Publications

Modeling the temporal evolution of postoperative complications. Feld SI, Cobian AG, Tevis SE, Kennedy GD, Craven MW. Proceedings of the American Medical Informatics Association Annual Symposium, 2016

Publication details

Baseline regularization for computational drug repositioning with longitudinal observational data. Kuang Z, Thomson J, Caldwell M, Peissig P, Stewart R, Page D. Proceedings of the 25th International Joint Conference on Artificial Intelligence, 2016

Publication details

Computational drug repositioning using continuous self-controlled case series. Kuang Z, Thomson J, Caldwell M, Peissig P, Stewart R, Page D. Proceedings of the 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2016

Publication details

Comparing mammography abnormality features to genetic variants in the prediction of breast cancer in women recommended for breast biopsy. Burnside ES, Liu J, Wu Y, Onitilo AA, McCarty CA, Page CD, Peissig PL, Trentham-Dietz A, Kitchner T, Fan J, Yuan M. Academic Radiology 23(1):62–69, 2016

Publication details

Lead

David Page

Investigators

Mark Craven

Peggy Peissig

Ross Kleiman

Akshay Sood

Zhaobin "Charles" Kuang

Alex Cobian

Resources

CPCP Retreat 2016: Entity Matching for EHR- and Transcriptome-based Phenotyping Symposium Video

CPCP Retreat 2016: Using Active Learning to Phenotype Electronic Medical Records Symposium Video

CPCP Retreat 2016: High-Throughput Predictive Phenotyping from Electronic Health Records Symposium Video

Small Talks about Big Data: Predicting Health Events from EHRs Using Machine Learning Small Talk Video