Help us improve
Share bugs, ideas, or general feedback.
From phenoml-skills
This skill provides real-world evidence (RWE) analysis using PhenoML APIs. It enables biopharma analysts to define patient cohorts, generate population statistics, compare cohorts, and assess study feasibility.
npx claudepluginhub phenoml/phenoml-skills --plugin phenoml-workflowHow this skill is triggered — by the user, by Claude, or both
Slash command
/phenoml-skills:rwe-analyzeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill provides real-world evidence (RWE) analysis using PhenoML APIs. It enables biopharma analysts to define patient cohorts, generate population statistics, compare cohorts, and assess study feasibility.
Systematically discovers novel research topics from longitudinal cohort databases by profiling cohort variables, matching PI expertise, and scanning literature saturation to output ranked gap proposals.
Generates clinical decision support documents for pharmaceutical research: biomarker-stratified cohort analyses with survival statistics, GRADE-graded treatment recommendations, and publication-ready LaTeX/PDF output.
Generates clinical decision support documents for pharmaceutical research: biomarker-stratified cohort analyses with survival statistics and evidence-based treatment recommendation reports with GRADE grading. Outputs publication-ready LaTeX/PDF.
Share bugs, ideas, or general feedback.
This skill provides real-world evidence (RWE) analysis using PhenoML APIs. It enables biopharma analysts to define patient cohorts, generate population statistics, compare cohorts, and assess study feasibility.
A single script (fetch_cohort.py) fetches patient data and generates IPS (International Patient Summary) natural language summaries. YOU (Claude) then interpret these summaries to provide whatever analysis the user needs.
Use this skill when users need to:
Before using this skill, ensure:
python-dotenv, phenomlAlways start by checking the environment configuration:
python skills/rwe-analyze/scripts/check_env.py --env-file .env
If credentials are missing, guide the user to set up their .env file with:
Use the single fetch script for all use cases:
Single cohort:
python skills/rwe-analyze/scripts/fetch_cohort.py \
--cohort "<natural language criteria>" \
--env-file .env
Two cohorts for comparison:
python skills/rwe-analyze/scripts/fetch_cohort.py \
--cohort "<first cohort>" \
--cohort-2 "<second cohort>" \
--env-file .env
The script outputs IPS natural language summaries. YOU (Claude) then analyze them based on what the user asked for:
Population Analysis:
Cohort Comparison:
Study Feasibility:
Always use --env-file: Pass the .env file path explicitly.
Natural language cohort descriptions: The PhenoML API accepts natural language:
IPS format: The IPS summaries include sections for:
User: "I need to understand our diabetic patient population"
Response: Run fetch_cohort.py with --cohort "patients with diabetes", then analyze the IPS summaries to report demographics, common comorbidities, and medication patterns.
User: "Compare patients on metformin versus those on insulin"
Response: Run fetch_cohort.py with --cohort "diabetic patients on metformin" --cohort-2 "diabetic patients on insulin", then compare the IPS summaries.
User: "How many diabetics aged 40-70 without kidney problems would qualify for our trial?"
Response: Run fetch_cohort.py with --cohort "patients with diabetes", then evaluate each patient's IPS against the criteria (age 40-70, no kidney disease) and report eligibility.
| Script | PhenoML APIs |
|---|---|
| fetch_cohort.py | tools.analyze_cohort(), fhir.search(), summary.create(mode="ips") |