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
- Distinguishing between agentic systems and simple tool-using LLM applications.
- Defining autonomy limits, policies, and the role of human oversight.
- Understanding the healthcare data environment and its constraints (EHR, FHIR, PHI).
Architecting Agent Workflows
- Implementing planning, memory, tool utilization, and reflective cycles.
- Advanced prompt engineering, function/tool integration, and action decision-making.
- Managing state and orchestration patterns.
Retrieval-Augmented Agent Design
- Ingesting and chunking medical documentation.
- Utilizing embeddings, vector databases, and assessing relevance.
- Ensuring response accuracy and developing citation strategies.
Healthcare Integration and Interoperability
- Essentials of FHIR/SMART for connecting agents.
- Processing both structured and unstructured clinical data.
- Managing events, APIs, and maintaining audit trails.
Safety, Risk Management, and Governance
- Establishing guardrails, conducting red-team exercises, and designing fail-safes.
- Handling PHI, de-identification processes, and enforcing access controls.
- Integrating human-in-the-loop reviews and defining escalation pathways.
Assessment and Monitoring Strategies
- Performing offline evaluations, creating golden sets, and defining KPIs.
- Detecting hallucinations and verifying factual accuracy.
- Ensuring observability, logging, and managing costs and latency.
Deployment Models and Practical Application
- Choosing between API-based and on-premises model solutions.
- Developing a retrieval-augmented agent using LangChain, FastAPI, and ChromaDB.
- Simulating incident responses and executing rollback procedures.
Conclusion and Future Directions
Requirements
- A solid grasp of fundamental Python programming.
- Practical experience with data analysis or machine learning workflows.
- 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 industry.
