Timezone: »

Identifying Disparities in Sepsis Treatment by Learning the Expert Policy
Hyewon Jeong · Siddharth Nayak · Taylor Killian · Sanjat Kanjilal · Marzyeh Ghassemi

Sepsis is a life-threatening condition defined by end-organ dysfunction due to a dysregulated host response to infection. Sepsis has been the focus of intense research in the field of machine learning with the primary aim being the ability to predict the onset of disease and to identify the optimal treatment policies for this complex condition. Here, we apply a number of reinforcement learning techniques including behavioral cloning, imitation learning, and inverse reinforcement learning, to learn the optimal policy in the management of septic patients using expert demonstrations. Then we estimate the counterfactual optimal policies by applying the model to another subset of unseen medical populations and identify the difference in cure by comparing it to the real policy. Our data comes from the sepsis cohort of MIMIC-IV and the clinical data warehouses of the Mass General Brigham healthcare system. The ultimate objective of this work is to use the optimal reward function to estimate the counterfactual treatment policy and identify deviations across sub-populations of interest. We hope this approach would help us identify any disparities in care and also changes in cure in response to the publication of national sepsis treatment guidelines.

Author Information

Hyewon Jeong (MIT)
Siddharth Nayak (Massachusetts Institute of Technology)
Taylor Killian (University of Toronto--Vector Institute Massachusetts Institute of Technology)
Sanjat Kanjilal (Harvard Medical School)

Dr. Kanjilal is an Instructor in the Department of Population Medicine at the Harvard Pilgrim Health Care Institute and the Associate Medical Director of Clinical Microbiology at the Brigham & Women’s Hospital (BWH). He is also an infectious diseases physician at the BWH and the course director of HST 040, Mechanisms of Microbial Pathogenesis, at Harvard Medical School. Dr. Kanjilal's research interests focus on harnessing observational and experimental data to improve the diagnosis and management of infectious diseases. Specific areas of work include the development of decision support tools built over machine learning models that assist healthcare providers in a variety of tasks such as antibiotic treatments and diagnostic testing strategies. His long term goal is to improve medical decision making by integrating accurate and interpretable artificial intelligence-supported meta-diagnostics into clinical workflows and to use these models on a broader scale to inform public health policy.

Marzyeh Ghassemi (MIT)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors