← All runbooks
smnth / ctg-condition-search-extraction★ Featured · worked examples

ClinicalTrials.gov Condition Search Extraction

Search ClinicalTrials.gov for studies matching the condition {{condition}} that were first posted between {{posted_from}} and {{posted_to}}. For each matching study, open its own ClinicalTrials.gov study page (https://clinicaltrials.gov/study/{NCT_NUMBER})…

agent opencodemodel openai/gpt-5.6-terrasnapshot prism-playwrighteval programmatic9 stepsv1.3.0

Deploy ClinicalTrials.gov Condition Search Extraction to your jetty.io

One-click installs this runbook into a collection on your Jetty account. You can run it from the Spot dashboard, schedule it, or pipe inputs in via the API.

Deploy on jetty.io →View source
Run time15-25 mins
Headline outputstudies.csv

Runs on Jetty's managed sandbox. No setup. Free for your first 10 runs.

Worked examples · 3

Real runs, real outputs.

Multiple myeloma, 2-month posting window
search-extracteval ✓

Multiple myeloma, 2-month posting window

47 API candidates narrowed to 46 studies (one dropped by the condition sanity check), all 46 PASS with every field verbatim from the study's own page and zero 'Not…

studies.csvextraction_audit.jsonsummary.mdvalidation_report.json
openai/gpt-5.6-terra · 10 minView run →Source
Ulcerative colitis, 1-month posting window (with audit trail)
search-extracteval ✓

Ulcerative colitis, 1-month posting window (with audit trail)

22 API candidates, 1 dropped by the condition sanity check (generic IBD only), 21 studies extracted with every field verbatim from the study page — 21/21 PASS, zero 'Not…

studies.csvextraction_audit.jsonsummary.mdvalidation_report.json
openai/gpt-5.6-terra · 5 minView run →Source
Psoriasis, 1-month posting window (sanity check at work)
search-extracteval ✓

Psoriasis, 1-month posting window (sanity check at work)

17 API candidates, of which 5 were dropped by the condition sanity check — three psoriatic-arthritis studies, one healthy-volunteer PK study, one generic…

studies.csvextraction_audit.jsonsummary.mdvalidation_report.json
openai/gpt-5.6-terra · 6 minView run →Source
The shape of the run

9 steps · start to finish.

  1. 1
    Step 1

    Environment Setup

    ▶
    pip install pandas playwright
python -m playwright install chromium

mkdir -p {{results_dir}}

    No secrets are required — both the API and the study pages are public.

  2. 2
    Step 2

    Build the Candidate List

    ▶

    Use the ClinicalTrials.gov API v2 to narrow down which studies to visit. This step only produces a list of NCT numbers — it is NOT the source of any extracted field value.

  3. 3
    Step 3

    Extract Exact Field Values From Each Study Page

    ▶

    For every candidate NCT number remaining after Step 2, open https://clinicaltrials.gov/study/{NCT} in a real browser (Playwright/Chromium) and wait for the page content to fully render (the page is a…

  4. 4
    Step 4

    Evaluate Outputs

    ▶

    For each row, assign an evaluation status:

  5. 5
    Step 5

    Iterate on Errors (max 3 rounds)

    ▶

    If any rows received FAIL or PARTIAL status:

  6. 6
    Step 6

    Write Extraction Audit Trail

    ▶

    Write {{results_dir}}/extraction_audit.json — the full provenance trail assembled while working through Steps 2-5. This exists so a reader can verify no value was fabricated or backfilled from the…

  7. 7
    Step 7

    Write Executive Summary

    ▶

    Write {{results_dir}}/summary.md with the following structure:

  8. 8
    Step 8

    Write Validation Report

    ▶

    Write {{results_dir}}/validation_report.json:

  9. 9
    Step 9

    Final Checklist (MANDATORY — do not skip)

    ▶

    echo "=== FINAL OUTPUT VERIFICATION ===" RESULTS_DIR="{{results_dir}}" for f in "$RESULTS_DIR/studies.csv" "$RESULTS_DIR/summary.md" "$RESULTS_DIR/validation_report.json"…