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 simple tool-use LLM applications
- Defining autonomy limits, policy adherence, and human oversight mechanisms
- Navigating the healthcare data ecosystem and constraints (EHR, FHIR, PHI)
Designing Effective Agent Workflows
- Integrating planning, memory, tool usage, and reflection loops
- Advanced prompt engineering, function/tool integration, and action selection logic
- Managing state and applying orchestration patterns
Building Retrieval-Augmented Agents
- Ingesting and chunking medical documentation for optimal processing
- Utilizing embeddings, vector stores, and assessing relevance
- Ensuring grounded responses and implementing citation strategies
Healthcare Integration and Interoperability
- Core FHIR/SMART principles for seamless agent connectivity
- Processing both structured and unstructured clinical data
- Implementing eventing, API management, and comprehensive audit trails
Safety, Risk Management, and Governance
- Establishing guardrails, red-teaming practices, and fail-safe design
- Managing PHI, de-identification techniques, and access controls
- Implementing human-in-the-loop reviews and clear escalation paths
Evaluation and Continuous Monitoring
- Conducting offline evaluations, creating golden sets, and defining KPIs
- Detecting hallucinations and verifying factuality
- Enhancing observability, logging, and managing cost/latency
Deployment Strategies and Practical Lab
- Choosing between API-based and on-premise model architectures
- Constructing a retrieval-augmented agent using LangChain, FastAPI, and ChromaDB
- Simulating incident response protocols and rollback procedures
Conclusion and Future Steps
Requirements
- Foundational proficiency in Python programming
- Practical experience with data analysis or Machine Learning workflows
- Knowledge of healthcare data standards and concepts (e.g., EHR, FHIR)
Target Audience
- Data scientists and ML engineers specializing in healthcare
- Teams focused on clinical informatics and digital health products
- IT executives and innovation managers within the healthcare sector
