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
Core Principles of Agentic AI in Healthcare
- Distinctions between agentic systems and standard LLM tool applications
- Defining autonomy limits, policies, and human supervision roles
- Overview of the healthcare data ecosystem and constraints (EHR, FHIR, PHI)
Architecting Agent Workflows
- Cycles of planning, memory, tool execution, and reflection
- Techniques for prompt engineering, function/tool usage, and decision-making
- Strategies for state management and orchestration
Retrieval-Augmented Agents
- Ingestion and segmentation of medical documents
- Use of embeddings, vector databases, and relevance assessment
- Methods for grounding responses and managing citations
Healthcare Integration and Interoperability
- Basics of FHIR/SMART for connecting agents
- Handling both structured and unstructured clinical data
- Implementation of eventing, APIs, and audit logging
Safety, Risk Management, and Governance
- Application of guardrails, red-teaming, and fail-safe architectures
- Compliance with PHI handling, de-identification, and access restrictions
- Human-in-the-loop review processes and escalation protocols
Evaluation and Continuous Monitoring
- Offline testing, golden dataset creation, and KPI formulation
- Detection of hallucinations and verification of factual accuracy
- Monitoring observability, logs, and management of cost/latency
Deployment Strategies and Practical Lab
- Choosing between API-based and on-premises model deployments
- Development of a retrieval-augmented agent using LangChain, FastAPI, and ChromaDB
- Simulated incident response and rollback procedure drills
Conclusion and Future Directions
Requirements
- Fundamental knowledge of Python programming
- Practical experience with data analysis or machine learning pipelines
- Understanding of healthcare data standards (such as EHR and FHIR)
Target Audience
- Healthcare data scientists and ML engineers
- Clinical informatics and digital health product teams
- IT executives and innovation managers in the healthcare sector