Adeel Abbasi, MD

Assistant Professor, Medicine

Warren Alpert School of Medicine
Brown University
Box G-L, 185 Meeting St.
Providence, RI 02912

Bio

Adeel Abbasi, MD, ScM, is an Assistant Professor of Medicine in the Division of Pulmonary, Critical Care and Sleep Medicine at Brown University, and Associate Medical Director of the Lifespan Adult Extracorporeal Life Support Program. His work in the Biomedical Artificial Intelligence Laboratory at Brown University’s Center for Biomedical Informatics aims to study and improve outcomes in patients treated with mechanical circulatory support, including extracorporeal membrane oxygenation (ECMO), by leveraging bioinformatics techniques including machine learning to address crucial knowledge gaps. His current research aims to predict complications including severe hemorrhage and thrombosis in patients treated with ECMO to identify modifiable risk factors.

Dr. Abbasi is a Parker B. Francis Fellow and his work is also supported by the CardioPulmonary Vascular Biology Center of Biomedical Research Excellence (CPVB COBRE) at the Ocean State Research Institute, and the Advance Clinical and Translational Research (Advance-CTR) Program of Rhode Island.

COBRE Abstract

Hemorrhage and thrombosis are the most significant causes of morbidity and mortality in extracorporeal life support (ECLS), and of these complications, stroke and intracerebral hemorrhage are the most devastating. The use of ECLS has exploded, but there is no way to accurately identify patients at risk for these complications. My long-term research goal is to improve outcomes in patients treated with ECLS. I will elucidate critical knowledge gaps using bioinformatics techniques including machine learning, a rigorous, data-driven artificial intelligence methodology ideally suited but yet to be leveraged in ECLS. My central hypothesis is that machine learning applied to ECLS data will identify key and modifiable factors associated with these poor outcomes. I will test these hypotheses by developing and analyzing machine learning models to predict hemorrhage (Aim 1) and thrombosis (Aim 2) within the Medical Information Mart for Intensive Care (MIMIC)-IV dataset, a freely available critical care dataset.

The proposed research is highly innovative and timely given the COVID-19 pandemic, which has been marked by the use of ECLS, thrombotic and neurological complications.

Publications

Project Updates

Mentors

Funded Research

Adeel Abbasi, MD

Adeel Abbasi, MD

Ocean State Research Institute

Research Funded by

Quick Links