Skip to main content
Back to challenges
Challenge

Focal Therapy vs Radical Surgery Decision Support with Pydantic AI and Qwen 3

Prostate cancer treatment strategy depends on accurate risk stratification between focal therapy and surgery. You will build a type-safe Pydantic AI agent leveraging Qwen 3 to evaluate MRI tissue imaging findings and clinical markers, delivering structured risk scores with 92% diagnostic agreement.

Data ScienceHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Develop a Pydantic AI clinical decision agent with Qwen 3 to triage localized prostate cancer treatment eligibility.

Delivery guide

How work is evaluated

Evaluation

Evaluates Pydantic AI agent's treatment recommendation accuracy against ground truth expert consensus decisions.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

schema_conformance

Ensure output conforms to Pydantic output model

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

recommendation_accuracy

Agreement rate with clinical expert benchmark choices • target: 0.92 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Utilize Pydantic AI framework for strongly-typed Python agent design

  • Integrate Qwen 3 model for biomedical report comprehension and reasoning

  • Implement multi-criteria scoring for prostate cancer focal therapy candidate selection

Resources and assets

Reference links and supporting material

Dataset notes

Prostate cancer patient clinical dataset containing 300 annotated biopsy and MRI diagnostic cases.

Challenge setup

Evaluates Pydantic AI agent's treatment recommendation accuracy against ground truth expert consensus decisions.

Challenge input

JSON object with gleason_score, pirads_score, and psa_level

Pydantic AI

Mandatory type-safe agent system framework.

Qwen 3

Model engine for biomedical text reasoning.

Evaluated output

JSON object with recommended_treatment string, confidence float, and reasoning list

Evaluation checks
  • Ensure output conforms to Pydantic output model
  • Agreement rate with clinical expert benchmark choices • target: 0.92 • range: 0-1
Configured evaluation evidence
  • Benchmark: OncoDecide-Bench
  • Recommendation Accuracy target: 0.92
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Pydantic AI · Optional
  • Haystack · Optional
Policy Serving
  • Qwen 3 · Required
Orchestration
  • Pydantic AI · Optional

Evaluation contract

  • schema_conformance · Weight 1
  • recommendation_accuracy · Weight 1

Metrics

  • recommendation_accuracy · Target 0.92

Benchmarks

  • OncoDecide-Bench
  • biotech

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON object with gleason_score, pirads_score, and psa_level

    Output: JSON object with recommended_treatment string, confidence float, and reasoning list

    Execution harness: Python

Evaluation tools

  • Pydantic AI · Agent Framework
  • Qwen 3 · Model Runtime

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Focal Therapy vs Radical Surgery Decision Support with Pydantic AI and Qwen 3