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 for Healthcare
- Distinguishing between agentic systems and tool-only LLM applications.
- Defining autonomy boundaries, operational policies, and human oversight roles.
- Navigating the healthcare data landscape and its constraints (EHR, FHIR, PHI).
Designing Agent Workflows
- Implementing planning, memory, tool usage, and reflection loops.
- Advanced prompt engineering, function/tool integration, and action selection strategies.
- Managing state and applying orchestration patterns effectively.
Retrieval-Augmented Agents
- Ingesting and chunking medical documents for optimal processing.
- Utilizing embeddings, vector stores, and assessing relevance.
- Ensuring response grounding and developing effective citation strategies.
Healthcare Integrations and Interoperability
- Foundations of FHIR/SMART for seamless agent connectivity.
- Processing both structured and unstructured clinical data efficiently.
- Managing eventing, APIs, and maintaining comprehensive audit trails.
Safety, Risk, and Governance
- Implementing guardrails, red-teaming techniques, and fail-safe design principles.
- Managing PHI through de-identification and strict access controls.
- Establishing human-in-the-loop review processes and clear escalation paths.
Evaluation and Monitoring
- Conducting offline evaluations, defining golden sets, and setting KPIs.
- Detecting hallucinations and performing rigorous factuality checks.
- Enhancing observability, logging, and managing cost and latency.
Deployment Patterns and Hands-on Lab
- Comparing API-based versus on-premise model deployment options.
- Building a retrieval-augmented agent using LangChain, FastAPI, and ChromaDB.
- Simulating incident response and executing rollback procedures.
Summary and Next Steps
Requirements
- Proficiency in fundamental Python programming.
- Practical experience with data analysis or machine learning workflows.
- Working knowledge of healthcare data standards and concepts, such as EHR and FHIR.
Target Audience
- Healthcare data scientists and ML engineers.
- Clinical informatics specialists and digital health product teams.
- IT executives and innovation managers within the healthcare sector.