parsing-trial-eligibility

Convert free-text clinical-trial eligibility criteria into structured inclusion and exclusion rules.

5.0k|615|Updated Oct 4, 2025

Search Tags:#decision support #clinical trials #eligibility criteria #patient screening #inclusion exclusion #clinical text #trial matching

Ready to run

npx skills add https://github.com/maziyarpanahi/openmed --skill parsing-trial-eligibility

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: parsing-trial-eligibility
Source: https://github.com/maziyarpanahi/openmed/tree/main/skills/parsing-trial-eligibility
Command: npx skills add https://github.com/maziyarpanahi/openmed --skill parsing-trial-eligibility

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill converts free-text clinical-trial eligibility criteria into structured inclusion and exclusion rules, then compares those rules with patient facts to make trial screening more consistent and explainable.

Core Features & Use Cases

Criteria Structuring: Separates inclusion and exclusion sections and converts individual requirements into typed predicates for conditions, medications, laboratory values, demographics, and performance status.
Patient Matching: Applies deterministic age and sex gates, evaluates patient facts, and produces pass, fail, or unknown results for each criterion.
Explainable Screening: Highlights missing information, handles negation and temporality concerns, and reports candidate eligibility for clinician review rather than autonomous enrollment.

Quick Start

Ask the skill to parse a ClinicalTrials.gov eligibility block and screen a synthetic patient profile with an explainable result for every criterion.

Frequently Asked Questions about parsing-trial-eligibility

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I match patient facts against clinical trial eligibility criteria?▼

You can screen synthetic patients by asking the Skill to parse a ClinicalTrials.gov eligibility block and compare it against a patient profile, generating an explainable pass, fail, or unknown result for every individual requirement.

How does clinical text parsing handle negation and temporality for trial matching?▼

Clinical text parsing handles negation and temporality awareness by extracting clinical entities, applying threshold and unit handling, and structuring typed predicates to accurately evaluate conditions, medications, and laboratory values within eligibility criteria.

Can I use ClinicalTrials.gov study screening for synthetic patient evaluation?▼

Yes, ClinicalTrials.gov study screening supports synthetic patient evaluation by converting free-text eligibility blocks into structured inclusion and exclusion logic, then comparing those rules against synthetic patient facts to generate candidate eligibility reports.

What is the best way to automate inclusion exclusion criteria extraction from clinical text?▼

The best way to automate inclusion exclusion criteria extraction is to separate the sections and convert individual requirements into typed predicates for conditions, demographics, medications, and performance status, creating structured rules for patient matching.

Why does patient screening report unknown results for some eligibility criteria?▼

Patient screening reports unknown results when missing information prevents a definitive evaluation, highlighting gaps in patient facts so clinicians can review candidate eligibility rather than relying on autonomous enrollment decisions.