Danielle Bitterman (Mass General Brigham)

Evaluating the quality and risks of language models for healthcare

There is immense enthusiasm about the potential of large language models to support clinical and administrative workflows in healthcare. In fact, large language models are currently being piloted for several applications in healthcare systems today, including for patient portal messaging and ambient documentation. However, a barrier to effective and safe clinical translation is the lack of standardized approaches to evaluate and monitor the knowledge quality, reasoning ability, and risks of these models. In this lecture, I will discuss current limitations of language model knowledge representation in the context of high-impact clinical applications. I will present our research into measuring language model risks, including bias and logical reasoning errors, in ways that are systematic, generalizable, and clinically-relevant. The intersection of these risks with human factors such as over-reliance and automation bias when implemented in a decision-support capacity will be discussed.

Dr. Danielle Bitterman is an Assistant Professor at Harvard Medical School, whose research is dedicated to developing and implementing AI advances for safe, equitable cancer care. She is a physician-scientist in the Artificial Intelligence in Medicine Program at Mass General Brigham, and a radiation oncologist in the Department of Radiation Oncology at Brigham and Women’s Hospital/Dana-Farber Cancer Dr. Bitterman’s lab uses natural language processing to transform the medical records into systems that actively data-driven care of patients with cancer. Her interests include language model medical knowledge grounding and bias assessments, automated information extraction from the electronic health records, and translational studies of AI in the clinic. Dr. Bitterman received her undergraduate degree at Columbia University, and attended medical school at New York University School of Medicine. She completed an internship in internal medicine at the Brigham and Women's Hospital, and her residency at the Harvard Radiation Oncology Program. She completed her post-doctoral fellowship in natural language processing at the Computational Health Informatics Program at Boston Children’s Hospital.