Artificial (Augmented) Intelligence in Medicine
NOT AVAILABLE FOR AY2026-2027
Department of Health Sciences Education
Details
-
Course Information
Course Number: RHSE660
Prerequisites: Completion of all Phase 2 clerkships
Length of Time: 4 weeks
Phase Availability: Phase 3
Credit Type: Open
Call: No
-
Contact Information
Program Directors: Linda Chang, PharmD, MPH, MHPE, BCPS; Radhika Sreedhar, MD, MHPE, MS, FACP
Departmental Contact Information: Allison King (aking75@uic.edu, 815-395-5802), Susan Ping, (pings@uic.edu, 815-395-5845)
Location: Online
Course details
Narrative Description: Technological advancement, particularly in Artificial Intelligence (AI) technology, is disrupting many societal infrastructures including the healthcare system. Artificial Intelligence (AI) – the creation of machines that work and react like humans – can improve on what humans can do and perform actions that humans cannot do. The Food and Drug Administration (FDA) has cleared and market-approved over 950 AI medical algorithms in the United States as of August 2024. Moreover, non-clinical AI programs that do not require FDA approval are being deployed exponentially across the health care settings in the areas of population health, identifying and addressing gaps in health equity, revenue management, hospital care monitoring, and preventive care. Furthermore, by enabling early detection and intervention, AI-driven predictive analytics can add data to empower individuals to take proactive steps to maintain their health and well-being, ultimately reducing healthcare costs and improving population health outcomes.
Generative AI tools are being incorporated into the electronic medical record to augment the workflow setup, such as prioritizing task lists, performing measurements, facilitating the medical informed consent process, auto-reporting set-ups, summarizing information, and speeding up reading time. Future healthcare providers need to be equipped with the skills to understand the process of AI intervention so they can collaborate with computer scientists and medical informaticians as part of the future clinical team. The healthcare team members do not need to know computing programming and the technical side of AI, but they do need to understand the limitations of AI in healthcare and the processes behind algorithm creation. They also need to know how these technologies impact the various domains of equity assessment, including accountability, fairness, validity, and relevance, such as major potential malfunctions like “dataset shift and data drift”.
Learning about an AI tool parallels acquiring knowledge about a new medication or diagnostic test, with competencies encompassing understanding its mechanism of action, effectiveness, indication for patient cohorts, and potential side effects.
Learning Objectives: Prepare healthcare students to have adequate foundational knowledge to participate on a technical team implementing an Al project. By the end of this course, students will:
- Describe foundational principles of artificial intelligence, including machine learning, deep learning, and natural language processing, and their relevance to healthcare.
- Identify any positive and negative impact of AI on health care
- Explain the Evidence-Based Evaluation of AI-Based
- Demonstrate the ability to collaborate within interdisciplinary teams by contributing to discussions on AI project design, implementation strategies, and integration into clinical workflows.
Learning Activities: This is an online course with virtual face-to-face meetings twice a week. Students must commit to four to five hours of daily work to cover the following topics. There will be weekly quizzes and patient case activities, and students are expected to complete a capstone project to present on research day.
Student Responsibility: Quizzes, virtual class participation, clinical workflow design proposal, patient cases, and student reflection papers.
Overview of Weekly Goal and Method of Assessment:
Overview of Weekly Goal and Method of Assessment:
| Week | Goal | Content | Assessment |
|---|---|---|---|
| 1 | Overview of the impact of Al How Al will help providers practice medicine | Biomedical informatics Foundation | Quiz, patient cases |
| 2 | Foundational concepts of Al and how it works | Essentials of Healthcare Data Science | Quiz and patient cases |
| 3 | Linkages between evidence-based medicine, high-value care, precision medicine, mobile computing and artificial intelligence | Predictive Analytics and Artificial Intelligence | Quiz and patient cases |
| 4 | Forms of artificial intelligence and its application Cases of applied Al in value-based care | Integrating and Applying Al | Quiz and patient cases |
| 5 | Identify the drivers, decision factors and collaboration required across clinical, operational and technology teams to realize return on investment from Al | Integrating and Applying Al | Team Project & project presentation on research day |
Course details
Method of Assessment: Overall Pass/Fail. Minimum pass of 80% for quizzes and patient cases.
Required Reading: Primary literature will be available for each week’s readings. No textbook is needed.
Additional Resources: Required Software will be provided free of charge by the University.
Miscellaneous Information: None