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-only LLM applications
- Defining autonomy limits, policy frameworks, and the role of human supervision
- Navigating the healthcare data environment and its constraints (including EHR, FHIR, and PHI)
Designing Agent Workflows
- Implementing planning, memory, tool usage, and reflection cycles
- Applying prompt engineering, function/tool integration, and action selection strategies
- Managing state and orchestration patterns for complex workflows
Retrieval-Augmented Agents
- Processing and chunking medical documents for ingestion
- Utilizing embeddings, vector stores, and evaluating relevance
- Ensuring response grounding and employing effective citation strategies
Healthcare Integrations and Interoperability
- Basics of FHIR/SMART standards for seamless agent connectivity
- Handling both structured and unstructured clinical data effectively
- Managing eventing, APIs, and maintaining comprehensive audit trails
Safety, Risk, and Governance
- Implementing guardrails, conducting red-teaming, and designing fail-safes
- Managing PHI, executing de-identification, and enforcing access controls
- Establishing human-in-the-loop review processes and clear escalation paths
Evaluation and Monitoring
- Conducting offline evaluations, creating golden sets, and defining KPIs
- Detecting hallucinations and performing rigorous factuality checks
- Enhancing observability, logging, and managing cost/latency metrics
Deployment Patterns and Practical Lab
- Comparing API-based versus on-premises model deployment options
- Constructing a retrieval-augmented agent using LangChain, FastAPI, and ChromaDB
- Simulating incident response scenarios and executing rollback procedures
Summary and Future Directions
Requirements
- A solid grasp of fundamental Python programming principles
- Practical experience in data analysis or machine learning workflows
- Familiarity with key healthcare data standards and concepts (such as EHR and FHIR)
Target Audience
- Data scientists and ML engineers specializing in healthcare
- Teams in clinical informatics and digital health product development
- IT leaders and innovation managers within the healthcare industry
