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 LLM tool applications
- Defining autonomy limits, operational policies, and human supervision roles
- Navigating the healthcare data environment and its constraints (EHR, FHIR, PHI)
Architecting Agent Workflows
- Integrating planning, memory, tool utilization, and reflective loops
- Advanced prompt engineering, function/tool management, and action selection strategies
- Managing state and implementing orchestration patterns
Retrieval-Augmented Agents
- Ingesting and chunking medical documentation
- Utilizing embeddings, vector databases, and assessing relevance
- Ensuring response accuracy and implementing citation methods
Healthcare Integration and Interoperability
- Core principles of FHIR/SMART for enabling agent connectivity
- Processing both structured and unstructured clinical data
- Managing eventing, API interactions, and maintaining audit trails
Safety, Risk Management, and Governance
- Implementing guardrails, conducting red-teaming, and designing fail-safe mechanisms
- Handling PHI, de-identification processes, and enforcing access controls
- Establishing human-in-the-loop review processes and escalation paths
Evaluation and Monitoring Strategies
- Conducting offline evaluations, defining golden sets, and establishing KPIs
- Detecting hallucinations and performing factuality verification
- Enhancing observability, logging, and managing cost and latency
Deployment Strategies and Practical Laboratory
- Choosing between API-based and on-premise model deployments
- Developing a retrieval-augmented agent using LangChain, FastAPI, and ChromaDB
- Simulating incident response and executing rollback procedures
Summary and Future Directions
Requirements
- Fundamental proficiency in Python programming
- Practical experience with data analysis or machine learning workflows
- Knowledge of key healthcare data standards and concepts (e.g., EHR, FHIR)
Target Audience
- Healthcare data scientists and machine learning engineers
- Teams focused on clinical informatics and digital health product development
- IT leadership and innovation managers within the healthcare sector
