Clinicaltrials Database

cd scientific-databases/clinicaltrials-database/scripts
python3 query_clinicaltrials.py

import requests

url = "https://clinicaltrials.gov/api/v2/studies"
params = {
    "query.cond": "breast cancer",
    "filter.overallStatus": "RECRUITING",
    "pageSize": 10
}

response = requests.get(url, params=params)
data = response.json()

print(f"Found {data['totalCount']} trials")

import requests

nct_id = "NCT04852770"
url = f"https://clinicaltrials.gov/api/v2/studies/{nct_id}"

response = requests.get(url)
study = response.json()

# Access specific modules
title = study['protocolSection']['identificationModule']['briefTitle']
status = study['protocolSection']['statusModule']['overallStatus']

from scripts.query_clinicaltrials import search_studies

results = search_studies(
    condition="type 2 diabetes",
    status="RECRUITING",
    page_size=20,
    sort="LastUpdatePostDate:desc"
)

print(f"Found {results['totalCount']} recruiting diabetes trials")
for study in results['studies']:
    protocol = study['protocolSection']
    nct_id = protocol['identificationModule']['nctId']
    title = protocol['identificationModule']['briefTitle']
    print(f"{nct_id}: {title}")

from scripts.query_clinicaltrials import search_studies

results = search_studies(
    intervention="Pembrolizumab",
    status=["RECRUITING", "ACTIVE_NOT_RECRUITING"],
    page_size=50
)

# Filter by phase in results
phase3_trials = [
    study for study in results['studies']
    if 'PHASE3' in study['protocolSection'].get('designModule', {}).get('phases', [])
]

from scripts.query_clinicaltrials import search_studies

results = search_studies(
    condition="cancer",
    location="New York",
    status="RECRUITING",
    page_size=100
)

# Extract location details
for study in results['studies']:
    locations_module = study['protocolSection'].get('contactsLocationsModule', {})
    locations = locations_module.get('locations', [])
    for loc in locations:
        if 'New York' in loc.get('city', ''):
            print(f"{loc['facility']}: {loc['city']}, {loc.get('state', '')}")

from scripts.query_clinicaltrials import search_studies

results = search_studies(
    sponsor="National Cancer Institute",
    page_size=100
)

# Extract sponsor information
for study in results['studies']:
    sponsor_module = study['protocolSection']['sponsorCollaboratorsModule']
    lead_sponsor = sponsor_module['leadSponsor']['name']
    collaborators = sponsor_module.get('collaborators', [])
    print(f"Lead: {lead_sponsor}")
    if collaborators:
        print(f"  Collaborators: {', '.join([c['name'] for c in collaborators])}")

from scripts.query_clinicaltrials import search_studies

results = search_studies(
    condition="alzheimer disease",
    status="COMPLETED",
    sort="LastUpdatePostDate:desc",
    page_size=50
)

# Filter for trials with results
trials_with_results = [
    study for study in results['studies']
    if study.get('hasResults', False)
]

print(f"Found {len(trials_with_results)} completed trials with results")

from scripts.query_clinicaltrials import get_study_details

study = get_study_details("NCT04852770")
eligibility = study['protocolSection']['eligibilityModule']

print(f"Eligible Ages: {eligibility.get('minimumAge')} - {eligibility.get('maximumAge')}")
print(f"Eligible Sex: {eligibility.get('sex')}")
print(f"\nInclusion Criteria:")
print(eligibility.get('eligibilityCriteria'))

from scripts.query_clinicaltrials import get_study_details

study = get_study_details("NCT04852770")
contacts_module = study['protocolSection']['contactsLocationsModule']

# Overall contacts
if 'centralContacts' in contacts_module:
    for contact in contacts_module['centralContacts']:
        print(f"Contact: {contact.get('name')}")
        print(f"Phone: {contact.get('phone')}")
        print(f"Email: {contact.get('email')}")

# Study locations
if 'locations' in contacts_module:
    for location in contacts_module['locations']:
        print(f"\nFacility: {location.get('facility')}")
        print(f"City: {location.get('city')}, {location.get('state')}")
        if location.get('status'):
            print(f"Status: {location['status']}")

from scripts.query_clinicaltrials import search_with_all_results

# Get all trials (automatically handles pagination)
all_trials = search_with_all_results(
    condition="rare disease",
    status="RECRUITING"
)

print(f"Retrieved {len(all_trials)} total trials")

from scripts.query_clinicaltrials import search_studies

all_studies = []
page_token = None
max_pages = 10  # Limit to avoid excessive requests

for page in range(max_pages):
    results = search_studies(
        condition="cancer",
        page_size=1000,  # Max page size
        page_token=page_token
    )

    all_studies.extend(results['studies'])

    # Check for next page
    page_token = results.get('pageToken')
    if not page_token:
        break

print(f"Retrieved {len(all_studies)} studies across {page + 1} pages")