Clinical Trials Normalizer

Search clinicaltrials.gov and get cleaned, normalized trial data — drug names standardized, medical conditions unified, and sponsor names deduplicated.

What this Actor does

The clinicaltrials.gov database contains 500,000+ clinical trials, but the data is messy. The same drug appears under 5 different names, conditions are described inconsistently, and sponsors have duplicate entries. This Actor:

• 🔍 Searches clinicaltrials.gov by condition, drug, sponsor, status, phase, country, and date range
• 💊 Normalizes drug names — maps 200+ brand names to generics (Keytruda → Pembrolizumab, Ozempic → Semaglutide, etc.)
• 🏥 Unifies conditions — standardizes 80+ common disease abbreviations and synonyms
• 🏢 Cleans sponsor names — strips legal suffixes (Inc, LLC, Ltd) and normalizes formatting
• 📊 Outputs structured data — CSV/JSON with normalized fields, aggregate stats, and a human-readable summary

Example

Search for "pembrolizumab" trials for "lung cancer":

{
  "condition": "lung cancer",
  "intervention": "pembrolizumab",
  "status": "RECRUITING",
  "maxResults": 50
}

The Actor returns a clean dataset where:

• "KEYTRUDA", "Pembrolizumab (MK-3475)", and "pembrolizumab" all become Pembrolizumab
• "NSCLC", "Non-Small Cell Lung Cancer", and "non-small cell lung cancer" all become Non-Small Cell Lung Cancer
• "Merck Sharp & Dohme LLC", "Merck & Co., Inc." → Merck Sharp & Dohme

Input Parameters

Field	Description
condition	Medical condition (e.g. "asthma", "breast cancer")
intervention	Drug or treatment (e.g. "aspirin", "pembrolizumab")
sponsor	Organization name (e.g. "Pfizer", "NCI")
status	Recruitment status filter
phase	Trial phase (1-4)
studyType	Interventional, Observational, or Expanded Access
locationCountry	Country filter (e.g. "United Kingdom")
startDateFrom / startDateTo	Date range (YYYY-MM-DD)
maxResults	Max trials to return (default 100, max 1000)

Output

Each trial record includes:

• NCT ID, title, acronym, status, phase, study type
• Normalized drug names + raw names for comparison
• Normalized conditions + raw conditions
• Clean sponsor name, enrollment count, age range, sex
• Locations, countries, primary outcomes, FDA regulation flags
• Direct link to clinicaltrials.gov study page

Plus aggregate stats: top drugs, top conditions, top sponsors, top countries, status breakdowns.

Use Cases

• Pharma competitive intelligence — track competitor trial pipelines
• Biotech investment research — identify active therapeutic areas
• Meta-analysis / systematic reviews — clean, consistent trial data for research
• Patient recruitment — find recruiting trials by location and condition
• Regulatory monitoring — track FDA-regulated drug and device trials

Data Source

ClinicalTrials.gov is a database of privately and publicly funded clinical studies conducted around the world, maintained by the U.S. National Library of Medicine. The API is free and requires no authentication.