Assistant Professor
Data Augmented Technology Assisted Medical Decision Making
What You'll Learn
- Describe the crucial role, strengths, limitations of AI and ML in evidence-based medical decision making
- Evaluate machine learning studies for bias and systematic error to enhance diagnostic decisions.
- Apply the results of machine learning studies and outputs to diagnostic decisions.
- Identify legal and ethical issues and best practices for AI and ML use in healthcare settings
4 Modules
12 Hours
3 hrs per module (approx.)
Rating
About Data Augmented Technology Assisted Medical Decision Making
Artificial intelligence (AI) and machine learning (ML) have the potential to increase diagnostic accuracy, decrease diagnostic errors, and improve patient outcomes. The Data Augmented, Technology Assisted Medical Decision Making (DATA-MD) course will teach you how to use AI to augment your diagnostic decision-making. The National Academy of Medicine (NAM) recommends ensuring that clinicians can effectively use technology - including AI - to improve the diagnostic process. To use these technologies effectively in your clinical practice, you will need to determine when use of AI is appropriate, interpret the outputs of AI, read medical literature about AI, and explain to patients the role that AI plays in their care. In this course, you’ll explore the ethical considerations and potential biases when making medical decisions informed by AI/ML-based technologies. DATA-MD is a one of a kind curriculum designed to provide an introduction to the use of AI in the diagnostic process.
This course was created with the needs of medical students, residents, fellows, practicing physicians, advanced practice providers, and registered nurses in mind. Others, like educators, computer programmers, and data scientists, may also find value in the course.
Continuing Medical Education Information:
This activity is released for CME credit on 07/30/2024 and expires 06/31/2027.
The University of Michigan Medical School is accredited by the Accreditation Council for Continuing Medical Education (ACCME) to provide continuing medical education for physicians.
The University of Michigan Medical School designates this enduring material for a maximum of 3.5 AMA PRA Category 1 Credit(s)™. Physicians should claim only the credit commensurate with the extent of their participation in the activity.
Dr. Cornelius James and Jessica Virzi, planner and co-planner for this educational activity, have no relevant financial relationship(s) with ineligible companies to disclose.
Maggie Makar, Benjamin Li, and Nicholson Price, presenters of this educational activity, have no relevant financial relationship(s) with ineligible companies to disclose. Karandeep Singh, presenter for this educational activity, was a consultant for Flatiron Health. The relevant financial relationship listed for this individual has been mitigated. Cheri Breadon and Jessica Virzi are the coordinators for this activity.
After this activity, participants will be able to
-Use AI to augment your diagnostic clinical decision-making
-Describe the strengths and limitations of AI/ML-based technology in the diagnostic process
-Interpret statistical measures frequently used to evaluate the performance of ML models
-Critically appraise studies that include AI/ML and determine the applicability of study results in clinical practice
If you would like to earn CME credit for participating in this course, please review the information, including expected results, presenters, their disclosures, and CME credit at this website prior to beginning the activity: https://umich.cloud-cme.com/course/courseoverview?P=0&EID=61826
Skills You'll Gain
- AI in Diagnostics
- AI in Patient Services
- Decision Making
- Patient Safety
What You'll Earn
- Certificate of Completion:
- Certificates of completion acknowledge knowledge acquired upon completion of a non-credit course or program.
Welcome Message
Welcome to Data Augmented Technology Assisted Medical Decision Making (DATA-MD). This course explores how artificial intelligence and machine learning can support diagnostic decisions in healthcare. Designed for clinicians, nurses, fellows, healthcare professionals, and graduate students, it addresses AI/ML methodologies, biostatistics, ethical considerations, and practical applications to improve patient care. Continuing Medical Education (CME) credits are available for eligible participants.
This abbreviated syllabus description was created with the help of AI tools and reviewed by staff. The full syllabus is available to those who enroll in the course.
Course Schedule
Module 1: Introduction to Artificial Intelligence and Machine Learning
- Video: Welcome to the Course
- Video: Welcome to Module 1
- Video: ⭐ Meet A.I.L.A.
- Reading: Course Syllabus
- Reading: Pre-Course Survey
- Reading: Meet Your Instructor
- Reading: Continuing Medical Education (CME) Information
- Video: What Is Big Data?
- Video: Locating the Data and Datasets
- Graded Assignment: Knowledge Check: Big Data
- Video: AI/ML in Health Care
- Graded Assignment: Knowledge Check: AI/ML in Health Care
- Video: Meet Professor Maggie Makar
- Video: What is ML?
- Video: Methodologies
- Video: Supervised Learning
- Video: Unsupervised Learning
- Video: Reinforcement Learning
- Video: ⭐Deep Learning
- Graded Assignment: Knowledge Check: Methodologies
- Video: ⭐How Models Are Developed: Part 1
- Video: ⭐How Models Are Developed: Part 2
- Video: ⭐How Models Are Developed: Part 3
- Video: Challenges With Model Development
- Graded Assignment: Knowledge Check: Model Development
- Discussion Prompt: What do you find most exciting using AI/ML in health care?
- Reading: Bibliography
- Reading: Module 1 Lecture Notes
Module 2: Foundational Biostatistics and Epidemiology in AI/ML for Health Care Professionals
- Video: Welcome to Module 2
- Video: Evidence-Based Medicine (EBM)
- Video: Overlap of EBM, AI, and ML
- Reading: Knowledge Check: EBM and AI/ML
- Video: The Diagnostic Process
- Video: Clinical Questions
- Graded Assignment: Knowledge Check: Clinical Questions
- Video: Correlation vs. Causation
- Video: Hypothesis Testing
- Video: Confidence Intervals
- Video: Frequency Measures
- Graded Assignment: Knowledge Check: Key Statistical Principles (Part 1)
- Video: Probability and Bayesian Statistical Analysis
- Video: Bayes Theorem
- Video: Likelihood Ratios
- Graded Assignment: Knowledge Check: Key Statistical Principles (Part 2)
- Video: How Do We Evaluate Predictive Models?
- Video: Introduction to ROC Curves
- Video: Calibration
- Graded Assignment: Knowledge Check: Key Statistical Principles (Part 3)
- Discussion Prompt: What are some concerns that you have about using machine learning in clinical practice?
- Reading: Bibliography
- Reading: Module 2 Lecture Notes
Module 3: Using AI/ML to Augment Diagnostic Decisions
- Video: Welcome to Module 3
- Video: ⭐Clinical Case: Part 1
- Reading: Core Reading: Assessment of Accuracy of an Artificial Intelligence Algorithm to Detect Melanoma in Images of Skin Lesions
- Video: The Diagnostic Process
- Video: Critical Appraisal
- Video: Validity of the Results (Part 1)
- Video: Validity of the Results (Part 1 Continued)
- Video: Validity of the Results (Part 2)
- Video: Validity of the Results (Part 2 Continued)
- Video: What Are the Results?
- Video: ⭐Clinical Case: Part 2
- Video: Do Results Apply?
- Video: Do Results Apply?
- Video: Do Results Apply? (Continued)
- Graded Assignment: Diabetic Retinopathy Case
- Video: Monitoring Performance
- Discussion Prompt: Describe at least two unique features of diagnostic studies that include ML.
- Reading: Bibliography
- Reading: Module 3 Lecture Notes
Module 4: Ethical and Legal Use of AI/ML in the Diagnostic Process
- Video: Welcome to Week 4
- Video: Medical Ethics
- Video: Data Availability
- Video: Data Collection and Curation
- Graded Assignment: Knowledge Check: Intro to Ethical and Legal Use of AI/ML in the Diagnostic Process
- Video: Meet Professor Nicholson Price
- Video: Patient Privacy and Data
- Video: ⭐Data Ownership
- Graded Assignment: Knowledge Check: Data Protection
- Video: Goals of Governance Key Stakeholders
- Graded Assignment: Knowledge Check: Governance, Why Does It Exist?
- Video: Sources and Dimensions of Algorithmic Bias
- Video: Bias and Performance Over Time
- Video: Clinician Response to Bias
- Graded Assignment: Knowledge Check: Health Care AI & Bias
- Video: Transparency
- Graded Assignment: Knowledge Check: Transparency
- Video: Who Is Liable When Something Goes Wrong?
- Video: Trust
- Video: Takeaways For Providers
- Discussion Prompt: What factors will influence your trust in AI-based technologies designed for use in health care?
- Reading: Bibliography
- Reading: Week 4 Lecture Notes
- Reading: Post-course survey
- Reading: Claim Your Continuing Medical Education (CME) Credits
Grading Policy
Learners must achieve an overall grade of 80% to pass the course and earn the certificate. Grades are based entirely on quizzes from each module worth 25% each.
Course content developed by U-M faculty and managed by the university. Faculty titles and affiliations are updated periodically.
Beginner Level
This course is targeted at medical students, residents, fellows, practicing physicians, advanced practice providers, and registered nurses.
What Learners Are Saying
Many have expressed concerns about the ethical use of artificial intelligence and machine learning in healthcare. This is certainly a rapidly evolving field but important questions must be asked and addressed if we are to ensure that clinicians and patients trust AI th…
Cornelius James, MD Assistant Professor of Internal Medicine, Pediatrics, and Learning Health Sciences, University of Michigan Medical School
