inclusion-criteria-gen

name	inclusion-criteria-gen
description	Generate and optimize clinical trial subject inclusion/exclusion criteria to balance scientific rigor with recruitment feasibility. Trigger when users need to design eligibility criteria for new trials, optimize existing criteria for better enrollment, analyze competitor trial eligibility patterns, or assess recruitment barriers. Use cases: Protocol design, eligibility optimization, recruitment strategy, competitive eligibility analysis, feasibility assessment.
version	1.0.0
category	Pharma
tags	["pharma","clinical-trials","inclusion-criteria","exclusion-criteria","protocol-design","recruitment"]
author	AIPOCH
license	MIT
status	Draft
risk_level	High
skill_type	Hybrid (Tool/Script + Network/API)
owner	AIPOCH
reviewer
last_updated	2026-02-06

Inclusion Criteria Generator

Generate and optimize clinical trial subject inclusion/exclusion criteria to balance scientific rigor with recruitment feasibility.

Use Cases

• Protocol Design: Create initial eligibility criteria for new clinical trials
• Criteria Optimization: Refine existing criteria to improve enrollment without compromising safety/efficacy
• Competitive Analysis: Analyze eligibility patterns across similar trials
• Recruitment Strategy: Identify and mitigate barriers to enrollment
• Feasibility Assessment: Evaluate if proposed criteria are realistic for target population

Usage

CLI Usage

# Generate criteria from study design
python scripts/main.py generate \
  --indication "Type 2 Diabetes" \
  --phase "Phase 2" \
  --population "adults" \
  --duration "24 weeks" \
  --output criteria.json

# Optimize existing criteria
python scripts/main.py optimize \
  --input current_criteria.json \
  --enrollment-target 200 \
  --current-enrollment 120 \
  --output optimized_criteria.json

# Analyze criteria complexity
python scripts/main.py analyze \
  --input criteria.json \
  --output analysis_report.json

# Compare with competitor trials
python scripts/main.py benchmark \
  --input criteria.json \
  --condition "Type 2 Diabetes" \
  --output benchmark_report.json

Python API

from scripts.main import CriteriaGenerator, CriteriaOptimizer

# Generate new criteria
generator = CriteriaGenerator()
criteria = generator.generate(
    indication="Type 2 Diabetes",
    phase="Phase 2",
    population="adults",
    study_duration="24 weeks",
    endpoints=["HbA1c reduction", "weight change"]
)

# Optimize existing criteria
optimizer = CriteriaOptimizer()
optimized = optimizer.optimize(
    criteria=existing_criteria,
    enrollment_target=200,
    current_enrollment=,
    retention_rate=
)


analysis = optimizer.analyze_complexity(criteria)