Reimagining OSCE Grading and Medical Education at UT Southwestern – Healthcare AI Pioneers
Jesse chats with Dr. Thomas Dalton, Associate Professor of Internal Medicine and Geriatrics at UT Southwestern Medical Center, and Dr. Andrew Jamieson Assistant Professor in the Lyda Hill Department of Bioinformatics at UT Southwestern Medical Center and Principal Investigator of Jamieson Lab. Together, they discuss objective structured clinical examinations, how UT Southwestern created a model to help solve problems with OSCEs, inter-rater reliability in the human baseline in their research data compared with benchmarks, how the resulting system was operationally deployed for real students being graded on real exams, what happens to human graders who are no longer needed for OSCE scoring, applying multimodal AI to video recordings of student physical exams, how AI assessment tools translate from medical school into graduate medical education, where AI-powered assessment could be headed, and much more.
Headline
OpenAI launches ChatGPT for clinicians.
Resource Link
About Our Guests
Dr. Thomas Dalton
Thomas Dalton, M.D., is an Associate Professor in the Department of Internal Medicine at UT Southwestern Medical Center and a member of its Division of Geriatric Medicine. His clinical interests center on acute care of the older adult, perioperative care for older adults undergoing elective surgery, and building interprofessional teams to help older adults and their families navigate the health care system.
Originally from the North Texas area, Dr. Dalton holds a bachelor’s degree from the University of North Texas and a medical degree from UT Southwestern, where he also completed residency training in Internal Medicine. After serving an additional year as Chief Resident, he obtained fellowship training in Geriatric Medicine with a concentration in Medical Education at Duke University.
Board-certified in internal medicine and geriatric medicine, he joined the UT Southwestern faculty in 2014.
Outside of his clinical work, Dr. Dalton directs the largest course at the medical school aimed at teaching and mentoring medical students in their clinical skills and professional identity formation. He also serves on several committees dedicated to medical curricula, interprofessional education, and other topics.
Dr. Dalton has been included in D Magazine‘s Best Doctors list and Texas Monthly‘s Super Doctors list annually since 2016.
Dr. Dalton is the recipient of multiple clinical and educational awards and honors, and he has been inducted into the Southwestern Academy of Teachers and the University of Texas Shine Academy of Health Science Eduation.
Dr. Andrew Jamieson
Andrew R. Jamieson, Ph.D., is an Assistant Professor in the Lyda Hill Department of Bioinformatics at UT Southwestern Medical Center. He leads a team of scientists and machine learning engineers developing advanced AI systems to solve both clinical and research problems—ranging from automated analysis of human performance and communication to decision support in complex biomedical workflows. His most recent work focuses on leveraging multimodal foundation models that integrate video, audio, and text to turn rich, real-world interactions into objective, scalable assessment and feedback. In collaboration with UT Southwestern’s Simulation Center, his group has pioneered automated evaluation of clinical encounters, including one of the first deployed AI systems for grading medical student post-encounter notes in OSCE-style assessments.
From 2018 to 2021, Dr. Jamieson served as co-leader of the Bioinformatics Core Facility (BICF), where he drove campus-wide collaborations in machine learning, image analysis, and data engineering. His work has been featured on the cover of Cell Systems (July 2021), where he developed a generative deep network to learn latent representations of live-imaged, label-free melanoma cells and uncover features associated with metastatic behavior. He has also partnered with pathologists and radiation oncologists to build custom pipelines and visualization tools for highly multiplexed spatial biology and other complex imaging modalities.
In response to the COVID-19 pandemic, Dr. Jamieson’s team developed the UTSW COVID-19 forecast model, providing critical operational insight to institutional leadership and the public. He is an active educator and program builder, contributing to graduate-level courses, nanocourses, and the Masters in Health Informatics program, with a particular emphasis on practical, safe, and responsible application of AI in real-world clinical and research workflows.
Prior to his academic career, Dr. Jamieson held key roles in industry, including positions at GE Healthcare in molecular diagnostics and BioPharma, and as the first data scientist at a big data analytics start-up. He received his B.A. in Physics with honors (2006) and Ph.D. in Medical Physics (2012) from the University of Chicago, where his early work in computer-aided diagnosis of breast cancer laid the groundwork for a career at the intersection of AI, complex data, and medicine.