Trustworthy Machine Learning for Equitable Healthcare

Project Summary Infectious diseases, such as pulmonary tuberculosis and sepsis, are associated with significant patient mor- bidity and mortality. Because of their public health significance, recent research in artificial intelligence (AI) and machine learning (ML) have explored how deep learning models may be used as clinical decision support tools

to work alongside clinicians in improving patient care. However, it is well-documented that AI algorithms—even those approved by the Food and Drug Administration (FDA)—are inaccurate and perform poorly on real-world pa- tients, especially those from minority backgrounds. As a result, such tools often inadvertently propagate existing

biases due to their poor performance on historically marginalized patient populations. Especially in high-stakes applications such as healthcare where there is a small margin for error, it is important to train neural networks that are clinically interpretable, trustworthy, and reliable even for patients from underrepresented backgrounds.

The reasons behind biased model performance are complex, but can be largely distilled into two major causes of algorithmic bias: (1) black-box predictive models may not be well-calibrated with true clinical decision-making used by physicians; and (2) minority patients are underrepresented in model training datasets. In this work, I

propose a series of algorithmic and practical innovations to address these two root causes of algorithmic bias in the clinical diagnosis and management of pulmonary tuberculosis and sepsis. I will accomplish this task by increasing the accessibility and reliability of AI models for traditionally marginalized patient populations.

Firstly, in order to better align predictive models with clinical reasoning for the diagnosis of pulmonary tuberculosis, I will show how publicly available vision-language foundational models can be used to improve the diagnostic accuracy of clinicians in resource-limited settings (Aim 1). Secondly, I will propose and validate a novel

computational algorithm that leverages historical aggregate patient data to better inform the clinical care of minority patients diagnosed with sepsis (Aim 2). These experiments will collectively demonstrate how AI al- gorithms can be better leveraged for various applications spanning multiple domains of patient care. In providing

solutions for these clinically relevant problems, I will further develop the technical skills and scientific reasoning needed as a future radiologist and academic researcher in machine learning. I look forward to leveraging both my graduate education and clinical training together to ultimately become a well-rounded physician-scientist and

independent investigator.