Precision Medicine in the Age of AI
to
Marylyn Ritchie, Ph.D.
Chief AI Officer, MUSC Director, MUSC AI Center for Health Innovation and Informatics SmartState Endowed Chair of Translational Biomedical Informatics Associate Dean of AI, College of Medicine Director, Division for Biomedical Informatics and AI
Medical University of South Carolina
Dr. Marylyn D. Ritchie is Chief Artificial Intelligence Officer for the MUSC Enterprise and Director of the MUSC AI Center for Health Innovation and Informatics. She also serves as Associate Dean for Artificial Intelligence and SmartState Endowed Chair in Translational Biomedical Informatics. An expert in translational bioinformatics, Dr. Ritchie develops methods integrating electronic health records with genomic data to advance research and patient care. She has more than 20 years of experience and over 500 publications. Dr. Ritchie is a Fellow of the American College of Medical Informatics and was elected to the National Academy of Medicine in 2021.
Summary
Artificial intelligence is reshaping precision medicine by changing how biomedical data are transformed into knowledge, clinical evidence, and actionable decisions. This lecture will examine how AI can integrate electronic health record data, clinical phenotypes, genomics, transcriptomics, proteomics, imaging, and other data modalities to advance disease characterization, risk prediction, and therapeutic discovery. Examples from complex chronic disease will illustrate the use of AI-enabled phenotyping, multimodal integration, and machine learning to identify clinically meaningful patterns and improve upon traditional analytic approaches.
The lecture will also explore how generative and agentic AI may transform the scientific workflow by serving as collaborative partners in hypothesis generation, data analysis, experimental design, and clinical translation. Finally, it will address the governance, validation, cybersecurity, ethical oversight, and workforce competencies needed to ensure that AI augments rather than replaces human expertise. The central premise is that the future of precision medicine should be AI-enabled but human-led, with researchers and healthcare professionals retaining responsibility for critical evaluation, judgment, and accountable implementation.
Learning Objectives:
- Describe how AI can support precision medicine by integrating electronic health record, genomic, multiomics, imaging, and clinical data for phenotyping, discovery, and risk prediction.
- Evaluate examples of AI-enabled approaches to complex disease research, including their potential advantages, limitations, and dependence on high-quality data and appropriate validation.
- Identify the governance, ethical, workforce, and domain-specific competencies required to implement AI responsibly while maintaining meaningful human oversight.
This page was last updated on Thursday, October 1, 2026