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 between agentic systems and tool-based LLM applications.
- Defining autonomy boundaries, operational policies, and human oversight mechanisms.
- Navigating the healthcare data landscape, including EHR, FHIR, and PHI constraints.
Designing Agent Workflows
- Integrating planning, memory, tool usage, and reflection loops.
- Applying prompt engineering, function/tool integration, and action selection strategies.
- Implementing state management and orchestration patterns.
Retrieval-Augmented Agents
- Ingesting and chunking medical documents effectively.
- Utilizing embeddings, vector stores, and relevance assessment techniques.
- Grounding responses with accurate citation strategies.
Healthcare Integrations and Interoperability
- Understanding FHIR/SMART fundamentals for agent connectivity.
- Processing structured and unstructured clinical data.
- Managing eventing, APIs, and maintaining audit trails.
Safety, Risk, and Governance
- Establishing guardrails, conducting red-teaming, and designing fail-safes.
- Managing PHI handling, de-identification, and access control protocols.
- Implementing human-in-the-loop reviews and escalation pathways.
Evaluation and Monitoring
- Conducting offline evaluations, defining golden sets, and establishing KPIs.
- Detecting hallucinations and performing factuality checks.
- Ensuring observability, logging, and managing cost and latency.
Deployment Patterns and Hands-on Lab
- Comparing API-based versus on-premise model deployment options.
- Constructing a retrieval-augmented agent using LangChain, FastAPI, and ChromaDB.
- Simulating incident response and executing rollback procedures.
Summary and Future Directions
Requirements
- Proficiency in basic Python programming.
- Practical experience with data analysis or machine learning workflows.
- Familiarity with healthcare data standards, such as EHR and FHIR.
Target Audience
- Healthcare data scientists and ML engineers.
- Teams in clinical informatics and digital health products.
- IT leaders and innovation managers within the healthcare sector.
