Speaker Profile

Pradeep Ravikumar

Biography
Dr. Ravikumar's research group at CMU works on the foundations of statistical machine learning. Their key research falls under two verticals: "graceful AI" and "scrappy AI". In graceful AI, we aim to learn ML models that are robust to train and test time corruptions, resilient to distribution shifts, and explainable. In scrappy AI, we aim to learn ML models under resource constraints by providing or discovering various notions of "structure" and domain knowledge. Dr. Ravikumar's thesis has received honorable mentions in the ACM SIGKDD Dissertation award and the CMU School of Computer Science Distinguished Dissertation award. He is a Sloan Fellow, a Siebel Scholar, a recipient of the NSF CAREER Award, and was Program Chair for AISTATS in 2013. He is Associate Editor-in-Chief for IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), and action editor for the Machine Learning journal, and the Journal of Machine Learning Research.

AI and Data Science Showcase:
CMU
We provide an automating diagnosis coding engine, that auto-completes diagnosis codes retrospectively in electronic health records (EHRs). Our solution has three modules: an EHR data cleaning module, a clinical knowledge semantics module, and a multi-modal multi-label prediction module.

Diagnosis Coding Engine for Electronic Health Records
We present an automating diagnosis coding engine, that auto-completes diagnosis codes retrospectively in electronic health records (EHRs). Our solution has three modules: a data cleaning module that corrects for data quality issues in the EHR, a semantics module, that incorporates translates clinical knowledge to diagnosis code semantics, and a multi-modal multi-label prediction module for predicting the diagnosis codes.