Foundations of Artificial Intelligence-Based Medicine

Artificial Intelligence (AI) methodologies, combined with virtually limitless computing resources and computational power offer unparalleled ways to analyze biomedical and clinical data in order to discover new knowledge leading to evidence-based decisions in a clinical setting. They also provide novel insights into quality improvements for clinical departments, which could lead to improved care and patient satisfaction, and reduced costs. In order to understand how AI can be used for clinical care, it is critical to understand not only the methodologies, but also the datasets we are exploring, in particular provenance and semantics. The primary objective of this course is to provide clinicians interested in collaborating with AI researchers with the fundamentals of the field, e.g., establish a common vocabulary to facilitate communication across medical and AI experts. It also prepares clinicians interested in becoming AI users to the subsequent 2 courses: technical aspects of AI, which is focused on covering programming and algorithmic fundamentals; and advanced concepts of AI, which is focused on topics such as deep learning, reinforcement learning, natural language processing etc. Thus, the 4 modules of this course do not dwell into any of the technical details of AI. Rather, the focus is on terminology and intuition.

Learn more about the Quality and Patient Safety initiative

1. Understand the fundamental concepts of Artificial Intelligence (AI), including its different views, subfields, and relationships with biomedical research and informatics.
2. Develop a strong foundation in data science and machine learning, including the hierarchy of data concepts (data, information, knowledge, decisions), data standards, and the importance of data collection, cleaning, and feature engineering
3. Master the skills to identify and apply the most suitable machine learning methods, including supervised and unsupervised learning, algorithm selection, testing, and validation, as well as the pros and cons of each approach.
4. Apply data science and machine learning concepts to real-world problems, including biomedical research, by exploring the principles and intuition behind learning algorithms, and separating the advantages and disadvantages of different methods and approaches.

The University of Florida College of Medicine is accredited by the Accreditation Council for Continuing Medical Education (ACCME) to provide continuing medical education for physicians.

Credit Designation

The University of Florida College of Medicine designates this Enduring Material for a maximum of 4.00 AMA PRA Category 1 Credits™. Physicians should claim only the credit commensurate with the extent of their participation in the activity.

For CME general questions, please contact
Email: [email protected]

Mitigation of Relevant Financial Relationships

University of Florida College of Medicine adheres to the ACCME’s Standards for Integrity and Independence in Accredited Continuing Education. All individuals in a position to control a CME activity's content, including faculty, planners, reviewers, and/or others, must disclose all financial relationships with ineligible companies (commercial interests). Conflict of interest information for the CME Advisory Committee members can be found on the following website: https://cme.ufl.edu/disclosure. All relevant financial relationships have been mitigated.

Member Information

Role in activity

Nature of Relationship(s) / Name of Ineligible Company(s)

Chris Giordano, MD
Clinical Professor
University of Florida

Faculty

Nothing to disclose

Francois Modave, PhD

Faculty

Consulting Fee-Genzyme Corporation (Relationship has ended)

Patrick Tighe, MD
Associate Dean for AI Applications
University of Florida

Faculty

Stocks or stock options, excluding diversified mutual funds-3M Health Care|Stocks or stock options, excluding diversified mutual funds-Microsoft|Stocks or stock options, excluding diversified mutual funds-GE Healthcare|Stocks or stock options, excluding diversified mutual funds-Solventum|Stocks or stock options, excluding diversified mutual funds-Apple