Assessing Patient-Provider Communication Using Computational Linguistics, Machine Learning, and LLMs
Computational linguistics and large language models applied to secure patient-provider messaging, to improve clinical communication and patient-centered outcomes.
Award: PCORI (Role: PI)
This work uses advanced computational linguistics in the analysis of secure messaging between patients and providers to enhance patient-centered outcomes. Secure messaging, a common form of communication in clinical practice, presents an opportunity to analyze rich linguistic data to improve patient decision-making effectiveness. We will leverage large language models for improved predictive analysis, integrating them with traditional machine learning methods to better identify effective deliberations in clinical exchanges. This approach aims to enhance the depth and breadth of insights from data analytics, improve the translation of comparative effectiveness research into clinical practice, and assist health systems in employing AI to support effective clinical communication.
Selected papers
This project is ongoing; the work below establishes the methods it builds on.
- Brown, W., Balyan, R., Karter, A. J., Crossley, S., Semere, W., Duran, N. D., Lyles, C., Liu, J., Moffet, H. H., Daniels, R., McNamara, D. S., & Schillinger, D. (2021). Challenges and solutions to employing natural language processing and machine learning to measure patients’ health literacy and physician writing complexity: The ECLIPPSE study. Journal of Biomedical Informatics, 113, 103658. [PDF]
- Schillinger, D., Duran, N. D., McNamara, D. S., Crossley, S. A., Balyan, R., & Karter, A. J. (2021). Precision communication: Physicians’ linguistic adaptation to patients’ health literacy. Science Advances, 7, eabj2836. [PDF]
See the full list on the publications page.