Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 14 hours
Course Outline
Foundations of Agentic AI in Healthcare
- Distinguishing agentic systems from tool-only LLM applications.
- Defining autonomy limits, governance policies, and human supervision roles.
- Navigating the healthcare data ecosystem and its constraints, such as EHR, FHIR, and PHI.
Designing Agent Workflows
- Implementing planning, memory, tool usage, and reflection cycles.
- Applying prompt engineering, function calling, and action selection strategies.
- Managing state and establishing orchestration patterns.
Retrieval-Augmented Agents
- Ingesting and segmenting medical documents for effective processing.
- Utilizing embeddings, vector stores, and relevance assessment techniques.
- Ensuring response grounding and developing citation methodologies.
Healthcare Integrations and Interoperability
- Fundamentals of FHIR and SMART for enabling agent connectivity.
- Handling structured and unstructured clinical data effectively.
- Managing event streams, APIs, and maintaining comprehensive audit trails.
Safety, Risk, and Governance
- Implementing guardrails, red-teaming strategies, and fail-safe design principles.
- Managing PHI through de-identification and strict access controls.
- Establishing human-in-the-loop reviews and clear escalation pathways.
Evaluation and Monitoring
- Conducting offline evaluations, defining golden sets, and establishing KPIs.
- Detecting hallucinations and performing rigorous factuality checks.
- Enhancing observability, logging, and managing cost and latency.
Deployment Patterns and Practical Laboratory
- Comparing API-based solutions versus on-premise model deployments.
- Developing a retrieval-augmented agent using LangChain, FastAPI, and ChromaDB.
- Simulating incident response and executing rollback procedures.
Summary and Future Directions
Requirements
- A foundational grasp of basic Python programming.
- Practical experience with data analysis or machine learning workflows.
- Familiarity with healthcare data standards, including EHR and FHIR.
Target Audience
- Data scientists and machine learning engineers in the healthcare sector.
- Teams involved in clinical informatics and digital health products.
- IT executives and innovation managers within healthcare organizations.
