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 for Healthcare
- Distinctions between agentic systems and simple tool-based LLM applications
- Defining autonomy limits, policies, and the role of human oversight
- Navigating the healthcare data ecosystem and its constraints (EHR, FHIR, PHI)
Architecting Agent Workflows
- Implementing planning, memory, tool integration, and reflection cycles
- Applying prompt engineering, function/tool calls, and action selection strategies
- Managing state and orchestration patterns effectively
Retrieval-Augmented Agents
- Processing medical documents through ingestion and chunking techniques
- Utilizing embeddings, vector databases, and assessing relevance
- Ensuring response accuracy through grounding and citation methods
Healthcare Integrations and Interoperability
- FHIR and SMART fundamentals for enabling agent connectivity
- Handling both structured and unstructured clinical data
- Managing eventing, API integrations, and audit trails
Safety, Risk, and Governance
- Establishing guardrails, conducting red-teaming, and designing fail-safes
- Managing PHI, de-identification processes, and access controls
- Implementing human-in-the-loop reviews and escalation protocols
Evaluation and Monitoring
- Conducting offline assessments, creating golden sets, and defining KPIs
- Detecting hallucinations and performing factuality verifications
- Ensuring observability, logging, and optimizing cost and latency
Deployment Strategies and Practical Laboratory
- Comparing API-based versus on-premise model deployment options
- Developing a retrieval-augmented agent using LangChain, FastAPI, and ChromaDB
- Simulating incident response and executing rollback procedures
Conclusion and Future Directions
Requirements
- Foundational knowledge of Python programming
- Practical experience with data analysis or machine learning workflows
- Familiarity with healthcare data standards (e.g., EHR, FHIR)
Target Audience
- Healthcare data scientists and ML engineers
- Clinical informatics specialists and digital health product teams
- IT executives and innovation managers within the healthcare sector
