Build an OpenAI Agents SDK Trial Matching Agent for IL-6 Inflammation Targets
Novartis and other pharmaceutical firms require automated participant screening to identify candidates eligible for IL-6 inflammatory target trials. Build an agent using OpenAI Agents SDK to parse electronic health records against complex inclusion/exclusion criteria and calculate trial eligibility.
What you are building
The core problem, expected build, and operating context for this challenge.
Develop an OpenAI Agents SDK workflow to screen cardiovascular trial candidate EHR records based on IL-6 inflammatory biomarkers.
How work is evaluated
Evaluates agent decision accuracy when matching patient FHIR bundles to trial inclusion parameters.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
eligibility_classification_match
Verifies that eligible patient is correctly marked true.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
screening_f1_score
F1 score across candidate patient cohort trial matching evaluations. • target: 0.95 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Implement structured autonomous agents with the OpenAI Agents SDK
Extract lab values (e.g., hsCRP, IL-6 levels) and diagnosis codes from FHIR JSON bundles
Evaluate eligibility logic against clinical trial protocol inclusion/exclusion constraints
Generate explicit reasoning logs explaining why patient records passed or failed screening
Reference links and supporting material
Cohort of 30 synthetic FHIR patient records with varying inflammatory biomarker profiles and cardiovascular history.
How this agent runs
Evaluates agent decision accuracy when matching patient FHIR bundles to trial inclusion parameters.
Challenge input
JSON FHIR patient resource bundle containing Observation and Condition resources.
OpenAI Agents SDK
Official framework for autonomous agent development.
Evaluated output
JSON containing is_eligible (boolean), matched_criteria (list), and exclusion_reasons (list).
- Verifies that eligible patient is correctly marked true.
- F1 score across candidate patient cohort trial matching evaluations. • target: 0.95 • range: 0-1
- Benchmark: FHIR Trial Screening Benchmark
- Screening F1 Score target: 0.95
- 1 public reference case
- Python execution harness
- Python sandbox
View technical recipe
Configured tools
- OpenAI · Required
- OpenVINO Toolkit · Optional
- Lepton AI · Optional
Evaluation contract
- eligibility_classification_match · Weight 1
- screening_f1_score · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.