Skip to Content

BMI 6001 Special Topics in Biomedical Informatics

3 semester credit hours
Lecture contact hours: 2; Lab contact hours: 3
Web-based and classroom instruction
Prerequisite: Depending on instructor/topic - could require consent

This course provides a timely way to examine cutting-edge topics of interest to students and faculty. The varying content may include topics such as technical writing in Biomedical Informatics, comparing knowledge use across disciplines or computational knowledge methods in Biomedical Informatics. May be repeated as topics vary.

  • BMI 6001: Special Topics in Biomedical Informatics: AI Agent Design and Human-AI Collaborations in Healthcare – Section 129

    BMI 6001: Special Topics in Biomedical Informatics

    AI Agent Design and Human-AI Collaborations in Healthcare – Section 129

    • Credit hours: 3 semester credit hours
    • Lecture contact hours: 2
    • Lab contact hours: 3
    • Delivery format: Web-based and classroom instruction (both)
    • Prerequisite: BMI 5310 or consent of the instructor

    Course Description

    This course introduces the design and evaluation of agentic artificial intelligence (AI) systems in healthcare. Students will explore how AI agents can support clinical and operational decision-making, collaborate with human stakeholders, and adapt to feedback in complex environments. Emphasis is placed on agentic reasoning frameworks, Human-in-the-Loop (HITL) design, prompt engineering, interaction modeling, and governance strategies. Through case-based discussions and a semester-long design project, students will develop a structured approach to designing AI agents that are transparent, trustworthy, and aligned with healthcare quality and safety goals. Students will have the option to demonstrate their agent prototypes using any of the following tools: low/no-code design studio, programming languages or interface mockups, depending on their technical background. The course prepares students to collaborate with AI developers, lead responsible innovation, and contribute to the safe and effective integration of AI agents in healthcare systems.


    Learning Objectives

    Upon successful completion of the course, students will:

    • Analyze healthcare use cases to identify opportunities for agentic AI support, including Human-in-the-Loop (HITL) integration and stakeholder collaboration.
    • Apply agentic reasoning frameworks to design decision-support workflows and adaptive agent behavior.
    • Design agent architectures and interaction models that incorporate autonomy, planning, prompt engineering, and human-agent teaming.
    • Evaluate agent designs using criteria for usability, trust, safety, and explainability, and plan for governance, risk mitigation, and continuous monitoring.
    • Communicate agent design specifications and implementation strategies through structured documentation, visual modeling, and prototype demonstrations.
  • BMI 6001: Special Topics in Biomedical Informatics: RWD/RWE Methods and Applications Across the Medical Product Lifecycle – Section 142

    BMI 6001: Special Topics in Biomedical Informatics

    RWD/RWE Methods and Applications Across the Medical Product Lifecycle – Section 142

    • Credit hours: 3 semester credit hours
    • Lecture contact hours: 2
    • Lab contact hours: 3
    • Delivery format: Web-based and classroom instruction (both)
    • Prerequisite: None

    Course Description

    This course introduces foundational concepts, methods, and applications of real-world data (RWD) and real-world evidence (RWE) across the medical product development lifecycle. Students learn how regulators, payers, and life sciences organizations use RWD to generate RWE in support of decisions across the product lifecycle, including trial optimization, label expansion, post-marketing safety, and value demonstration. Emphasis is placed on assessing data quality and fitness for purpose in RWD, selecting appropriate study designs, implementing basic analytic workflows, and critically appraising published and sponsor-generated RWE. Through lectures, hands-on labs, and team projects, students will design and justify RWD/RWE studies that align with current regulatory and industry expectations for transparent, decision-grade evidence.


    Learning Objectives

    This course provides a practical, methods-focused introduction to real-world data (RWD) and real-world evidence (RWE) for clinical studies, with a focus on the medical product lifecycle. Students will:

    • Characterize major RWD sources, including EHR (encompassing structured data, unstructured clinical notes, imaging, and waveforms), claims, registries, digital health, and patient-generated data, and evaluate their strengths, limitations, and fitness for purpose for specific clinical, regulatory, and payer questions.
    • Explain how key stakeholders, including regulators, payers, health technology assessment bodies, and life sciences organizations, use RWE across the medical product lifecycle, from trial optimization and label expansion to post-marketing safety and value demonstration.
    • Design RWE-generating studies using appropriate observational study designs and frameworks, including target trial emulation, new-user active comparator cohorts, and external control arms, consistent with current regulatory and industry best practices.
    • Implement foundational analytic workflows including cohort construction, confounding control, bias assessment, and sensitivity analyses, and accurately interpret resulting findings in the context of RWD/RWE studies.
    • Critically appraise published and sponsor-generated RWE as it relates to regulatory decision-making, label expansion, health technology assessment, and payer coverage decisions.