Smart Patient Summary Agent for FHIR

An AI agent built on InterSystems IRIS AI Hub that generates role-specific clinical summaries from FHIR patient data. Given a patient ID, it queries a FHIR R4 server, extracts structured clinical signals, and produces four distinct narrative summaries tailored to:

• ED Doctor — safety-first, immediate action priorities, disposition context
• Care Manager — continuity gaps, transitions, care coordination tasks
• Patient — plain language, self-care guidance, warning signs
• Family Caregiver — monitoring checkpoints, medication safety, escalation triggers

Output is deterministic and evidence-based — same FHIR data, four different narrative framings.

Team

• Gil Tavassy — Developer Community profile · LinkedIn

Submission mode: solo project.

Architecture

One container runs the summary engine and connects to your FHIR server:

The container connects to a FHIR R4 server running on your host machine (or any reachable URL configured in .env).

Prerequisites

• Docker Desktop (Windows / Mac) or Docker Engine (Linux)
• InterSystems IRIS AI Hub EAP image — the AI Hub is baked into this image.
  1. Register / log in at https://evaluation.intersystems.com/Eval/early-access/AIHub and select the AI Hub program.
  2. Download two files:
     • irishealth-community-2026.2.0AI.162.0-docker.tar.gz (x64) — or the arm64 variant for Mac M-series
     • iris-container-x64.key (or iris-container-arm64.key for ARM64)
  3. Load and tag the image (one-time step per machine):

     docker image load -i irishealth-community-2026.2.0AI.162.0-docker.tar.gz
     docker tag docker.iscinternal.com/docker-intersystems/intersystems/irishealth-community:2026.2.0AI.162.0 irishealth-community:2026.2.0AI.162.0
     

Quick start

1. Clone this repository.
2. Copy your iris-container-x64.key into the keys/ folder at the repo root.
3. Open .env and set FHIR_BASE_URL to your FHIR server’s address. The default (http://host.docker.internal:52773/fhir/r4) points to the standard IRIS web port on your host machine — no change needed if that is where your server runs.
4. Build and start:

   docker compose build
   docker compose up -d
   

5. Wait ~60 seconds for the container to become healthy.
6. Load patient data into your FHIR server (see Patient data below).
7. Run a summary.

Patient data

The summary engine requires at least one patient in your FHIR R4 server.

Load with any FHIR R4 client (Postman, HAPI FHIR CLI, curl) or generate realistic synthetic profiles with Synthea.

Note the patient ID returned when you POST the Patient resource — you’ll use it in the demo commands below.

Running a summary

Replace <patientId> with your patient’s FHIR ID:

# All four roles, detailed mode
docker exec smart-patient-summary-generator-iris-1 bash -c \
  "printf 'Do ##class(Sample.AI.Examples.FHIRSummary).DemoNarrativeAllRoles(\"\",\"detailed\")\nHalt\n' \
  | iris session IRIS -U USER 2>&1 | grep -Ev '^(USER>|Node:)'"
Single role (ed, care_manager, patient, or caregiver)
docker exec smart-patient-summary-generator-iris-1 bash -c 

"printf 'Do ##class(Sample.AI.Examples.FHIRSummary).DemoNarrative("","ed","detailed")\nHalt\n' 

| iris session IRIS -U USER 2>&1 | grep -Ev '^(USER>|Node:)'"
Brief mode (2 items per section)
docker exec smart-patient-summary-generator-iris-1 bash -c 

"printf 'Do ##class(Sample.AI.Examples.FHIRSummary).DemoNarrativeAllRoles("","brief")\nHalt\n' 

| iris session IRIS -U USER 2>&1 | grep -Ev '^(USER>|Node:)'"

All entry points

detailMode: "brief" (2 items/section) or "detailed" (full evidence).

Environment variables

Set in .env (loaded automatically by Docker Compose):

FHIR resources used

The engine queries: Patient, Observation, AllergyIntolerance, Condition, MedicationRequest, Encounter, CarePlan.

Output structure

Each role summary contains:

• Patient Overview — demographics and evidence inventory
• Clinical Details — conditions, medications, allergies, encounters, observations, care plans
• Current Issues — deterministic extraction of active problems, abnormal findings, alerts
• Recent Changes — trend signals and data freshness
• Risks / Follow-up — evidence-based escalation triggers
• Role-Specific Action Plan — immediate priorities, weekly actions, escalation criteria

What is the AI Hub?

InterSystems AI Hub is the AI SDK for IRIS — it provides ObjectScript, Python, and Java APIs for building agents, tool-based pipelines, and RAG applications that run natively on IRIS.

• ObjectScript SDK guide
• Advanced features
• Examples
• MCP Server guide
• LangChain guide
• Config Store guide