Topic

Clinical Concept Adjudication

Fillmore and his collaborators have developed scalable methodologies to improve the accuracy and efficiency of clinical concept adjudication within large electronic health record databases. His work includes the creation of interactive machine learning tools for the systematic categorization of laboratory data and rule-based algorithms for phenotyping immune-related adverse events. These advancements reduce the manual burden on clinical experts while increasing the reliability of event detection in massive patient cohorts.

U.S. Veterans and VA Data 2 Immune Checkpoint Inhibitors 1 Immune-Related Adverse Events 1 Hepatocellular Carcinoma 1 Rule-Based Algorithms 1 Retrospective Cohort Study 1 Real World Evidence 1 Case Definition Validation 1 Hepatotoxicity 1 Electronic Health Records 1 Machine Learning 1 Laboratory Data Integration 1

Publications (2)

2024

Phenotyping Hepatic Immune-Related Adverse Events in the Setting of Immune Checkpoint Inhibitor Therapy.

Theodore C. Feldman, David E. Kaplan, Albert Lin, Jennifer La, Jerry S. H. Lee, Mayada Aljehani, David P. Tuck, Mary T. Brophy, Nathanael R. Fillmore^‡, Nhan V. Do^‡^‡ Equal senior authorship

JCO Clinical Cancer Informatics8, e2300159

Immune Checkpoint Inhibitors Immune-Related Adverse Events Hepatocellular Carcinoma Rule-Based Algorithms Retrospective Cohort Study

2019

Interactive Machine Learning for Laboratory Data Integration.

Nathanael Fillmore, Nhan Do, Mary Brophy, Andrew Zimolzak

Studies in Health Technology and Informatics264, 133-137

U.S. Veterans and VA Data Electronic Health Records Machine Learning Clinical Concept Adjudication Laboratory Data Integration