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.
Course Outline
Foundations of Agentic AI in Healthcare
- Agentic systems versus tool-only LLM applications
- Defining autonomy boundaries, policies, and human oversight
- Healthcare data landscape and constraints (EHR, FHIR, PHI)
Designing Agent Workflows
- Planning, memory, tool utilization, and reflection cycles
- Prompt engineering, function/tool integration, and action selection
- State management and orchestration strategies
Retrieval-Augmented Agents
- Ingesting and chunking medical documents
- Embeddings, vector stores, and relevance assessment
- Grounding responses and implementing citation strategies
Healthcare Integrations and Interoperability
- Fundamentals of FHIR/SMART for agent connectivity
- Handling structured and unstructured clinical data
- Eventing, API integration, and maintaining audit trails
Safety, Risk, and Governance
- Implementing guardrails, red-teaming, and fail-safe designs
- Managing PHI, de-identification, and access controls
- Human-in-the-loop review and escalation protocols
Evaluation and Monitoring
- Offline evaluations, golden sets, and defining KPIs
- Detecting hallucinations and verifying factuality
- Observability, logging, and managing cost/latency
Deployment Patterns and Hands-on Lab
- Choosing between API-based and on-prem models
- Building a retrieval-augmented agent using LangChain, FastAPI, and ChromaDB
- Simulating incident response and rollback procedures
Summary and Next Steps
Requirements
- Fundamental knowledge of Python programming
- Practical experience with data analysis or ML workflows
- Familiarity with healthcare data standards (e.g., EHR, FHIR)
Target Audience
- Healthcare data scientists and ML engineers
- Clinical informatics and digital health product teams
- Healthcare IT leaders and innovation managers
14 Hours