Overview
Since 2021, I have contributed to the AI in Medicine / AI in Healthcare course as part of AIMSS’s education programming. The course is designed for healthcare providers and trainees and is offered for elective/professional development credit, with instruction from subject matter experts. The course emphasizes practical AI literacy: how to evaluate AI systems, integrate tools into clinical and research workflows, and use AI responsibly (privacy, academic integrity, and patient safety).
Lectures and recorded sessions from the course
Figure for Case-based Learning: Conclusion & Wrap-up
Case-based Learning: Conclusion & Wrap-up
2023-06-05
Case-based learning wrap-up session using medical AI papers; key takeaways and closing discussion.
Figure for Applications of AI in Genetics and Genomics
Applications of AI in Genetics and Genomics
2022-04-11
Lecture on applied AI in genomic medicine for the AI in Medicine Course (AIMSS, 2022).
Figure for Flow of Information in Patient Care
Flow of Information in Patient Care
2021-04-11
Premier lecture for the Introduction to Medicine & Medical Data stream of the AI in Medicine Course (AIMSS, 2021).
Learning outcomes
  • Explain core AI concepts relevant to healthcare (model behavior, generalization, bias, validation, performance metrics)
  • Critically appraise AI claims in papers/products and identify common failure modes (dataset shift, leakage, bias, poor ground truth)
  • Apply AI tools appropriately for research workflows (literature synthesis, analysis support, drafting) with transparent documentation and verification
  • Articulate responsible-use practices (privacy/confidentiality, integrity, disclosure of AI assistance, and “no harm” framing)
Key takeaways
  • AI is already embedded in healthcare and research; competency now includes the ability to evaluate AI outputs and limitations, not just to use tools.
  • The best near-term value is workflow integration (augmenting literature review, analysis, and writing) while maintaining ethical and scientific rigor.