Artificial Intelligence in Medicine

Course Faculty

Fran├žois Modave

Fran├žois Modave Ph.D.

Assistant Dean, Quality And Patient Safety Initiative (QPSi), Academy, Training, And Fellowship Programs, Professor Of Artificial Intelligence, Associate Chair For Research, Department Of Anesthesiology
Chris R Giordano

Chris R Giordano MD

Professor Of Anesthesiology; Division Chief, Liver Transplantation; Director, Anesthesiology/Critical Care Clerkship
Meghan M Brennan

Meghan M Brennan MD, MS

Assistant Professor Of Anesthesiology
Benjamin Shickel

Benjamin Shickel PhD

Assistant Professor


Artificial Intelligence (AI) methodologies, combined with virtually limitless computing resources and computational power offer unparalleled ways to analyze biomedical data in order to discover new knowledge leading to evidence-based decisions in a clinical setting. In order to understand how AI can be used for clinical research and clinical care, it is critical to understand the datasets we are exploring as well as data provenance and semantics, and more generally information and knowledge. These topics fall within the realm of the field of biomedical informatics.

AI, in particular its subfields, machine learning and deep learning promise to revolutionize healthcare because of their flexibility in analyzing large heterogeneous data sets, combined with state-of-art computing infrastructures. Multidisciplinary projects involving AI in healthcare remain constrained by two key factors: (1) Insufficient bandwidth amongst core AI faculty for mentoring, teaching, and engagement with new project initiatives, and (2) insufficient numbers of physician-scientists, and more generally, researchers with training in requisite principles of AI for necessary multidisciplinary collaborations.

In this track, the students will gain an understanding of the main domains that are relevant to Artificial Intelligence in medicine, including elements of biomedical informatics, focused on data structures, standards, information, and knowledge, foundations of AI, introduction to computing tools to support AI in medicine, model development, testing, validation, and interpretation of the results.

Learning Objectives

  • Explain the differences between data, information, and knowledge
  • Identify the utility and design of data structures, standards, and provenance
  • Understand the history and philosophy of AI and its main paradigms
  • Recognize the various methodologies in AI (logic-based models and expert systems, supervised, unsupervised, semi-supervised machine learning) and when and how they are used and applied
  • Identify the syntax of the programming language Python and how it is applied in AI
  • Design basic code, modify existing code, and use libraries of various coding for AI utility
  • Operate constructively and efficiently within an AI team in order to:
  • critically analyze the available data sets
  • choose a set of models to build to answer a specific data science question
  • build, test, validate, and compare the models
  • interpret the results from an AI standpoint
  • present the findings
  • Appraise and critique the AI tool findings to the clinical community


  • Attendance to all lectures and seminars
  • Completion of all assignments (e.g., assessment of a published study, development of an AI, etc.) and quizzes on time
  • Participation in group discussions during the course
  • Capstone project presentation


  • Participation in interactive lectures, seminars, and group sessions
  • Performance on quizzes
  • Capstone project (A certificate of distinction will be considered for students who go beyond the requirements and whose research project leads to presentation at a national meeting or published manuscript in a scientific journal)


  • Choose pathway (and project) in MS1 year and start the didactics
  • Complete the project in the MSRP portion of pathway
  • Continue didactics and seminars in MS2 year
  • Complete Capstone and apply for Distinction (MS4)