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
Fundamentals of Agentic AI in Healthcare
- Distinguishing agentic systems from simple tool-using LLM applications
- Defining autonomy limits, policies, and the role of human supervision
- Overview of the healthcare data environment and its constraints (EHR, FHIR, PHI)
Architecting Agent Workflows
- Integration of planning, memory, tool utilisation, and reflective cycles
- Techniques in prompt engineering, function/tool integration, and decision selection
- Managing state and orchestration strategies
Implementing Retrieval-Augmented Agents
- Ingesting and segmenting medical documents
- Utilising embeddings, vector databases, and assessing relevance
- Ensuring grounded responses and effective citation methods
Healthcare System Integration and Interoperability
- Essentials of FHIR/SMART for connecting agents to healthcare systems
- Handling both structured and unstructured clinical data
- Managing event streams, APIs, and maintaining audit trails
Safety, Risk Management, and Governance
- Establishing guardrails, conducting red-teaming, and designing fail-safes
- Managing PHI, implementing de-identification, and enforcing access controls
- Incorporating human-in-the-loop reviews and defining escalation protocols
Assessment and Continuous Monitoring
- Conducting offline assessments, using golden sets, and defining KPIs
- Detecting hallucinations and verifying factuality
- Managing observability, logging, and optimising cost and latency
Deployment Strategies and Practical Lab
- 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
- A foundational understanding 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 and digital health product teams
- IT leaders and innovation managers within the healthcare sector
