Orchestrate Focal Therapy Decision Workflows with CrewAI & o3
Focal therapy for localized prostate cancer presents complex trade-offs between oncological control and quality of life. Deploy a multi-agent consensus system using CrewAI and OpenAI o3 to analyze patient MRI, biopsy, and genomic data to produce evidence-backed treatment consensus with 88% clinician agreement.
What you are building
Multi-agent clinical decision framework built with CrewAI and OpenAI o3 model reasoning.
How work is evaluated
Evaluates multi-agent tumor board agreement and recommendation alignment with guidelines.
Datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
guideline_compliance_test
Verifies recommendation matches evidence-based clinical guidelines.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
consensus_agreement_rate
Percentage agreement with ground truth tumor board decision. • target: 0.88 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Learning goals
Configure multi-agent role-based teams using CrewAI framework.
Utilize OpenAI o3 advanced reasoning capabilities for multi-criteria trade-off evaluations.
Synthesize MRI PIRADS scores and pathology reports into actionable tumor board recommendations.
Resources
Dataset of 40 multi-parametric MRI and pathology patient profiles with consensus expert tumor board decisions.
Challenge setup
Evaluates multi-agent tumor board agreement and recommendation alignment with guidelines.
Challenge input
JSON patient clinical profile including Gleason score, lesion PIRADS, and age
CrewAI
Orchestrates role-playing agents.
o3
OpenAI reasoning model for complex medical trade-off evaluation.
Evaluated output
JSON consensus object with recommended_modality and rationale
- Verifies recommendation matches evidence-based clinical guidelines.
- Percentage agreement with ground truth tumor board decision. • target: 0.88 • range: 0-1
- Benchmark: OncoMDT-Bench
- Consensus Agreement Rate target: 88%
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
Shows the first task, up to three tools, and up to three evidence items.
View technical recipe
Configured tools
- CrewAI · Optional
- Zed · Optional
- o3 · Required
Evaluation contract
- guideline_compliance_test · Weight 1
- consensus_agreement_rate · Weight 1
Metrics
- consensus_agreement_rate · Target 0.88
Benchmarks
- OncoMDT-Bench
- biotech
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON patient clinical profile including Gleason score, lesion PIRADS, and age
Output: JSON consensus object with recommended_modality and rationale
Execution harness: Python
Evaluation tools
- CrewAI · agent_framework
- o3 · llm
Recipe freeze marker
No recipe freeze time is recorded.