IMMUNE

In Silico, Medical Record-based Model for Understanding the INitiation of Autoimmune Events (IMMUNE) aims to test the feasibility and effectiveness of using a hybrid in silico/ in vivo (computer-simulated/ in living organism) model system, combined with machine learning strategies as a platform for understanding the etiology of autoimmune disease.

IMMUNE brings together a team of immunologists, oncologists, informaticists and machine learning experts working within an electronic health record (EHR) network, to identify a cohort of cancer patients who have undergone immune checkpoint inhibitor (ICI) therapy. From this cohort, the team will design and implement a broad and deep longitudinal database of EHR data, including treatment and response data and laboratory results, to enable the development of phenotypic profiles and models for autoimmune disease development in humans.

Evaluation

This project will create computable phenotypes to identify patients with rheumatoid arthritis that develops spontaneously or following immune checkpoint inhibitor (ICI) therapy. Following identification, these phenotypes will be extended to the PCORnet Common Data Model to expand the cohort size and per-patient data depth.

Supervised and unsupervised machine learning strategies will then be used to develop and compare preliminary phenotypic profiles for patients with rheumatoid arthritis in the presence or absence of cancer and ICI therapy.

Principal Investigators

Theresa Walunas, PhD
Abel Kho, MD, MS

Project Team

Jeffrey Sosman, MD
Carlos Galvez, MD
Al’ona Furmanchuck, PhD, CHIP Faculty
Yuan Luo, PhD, CHIP Faculty
Jennifer Pacheco
Luke Rasmussen, MS
Steven Tran

Funding

Funding for this project was provided by the National Institutes of Health/ National Institute of Arthritis and Musculoskeletal and Skin Diseases (NIH/ NIAMS).