Clinical trial demographics extractor

Read full text
Authors: Abigail Tubbs, Enrique Alvarez Vazquez
Cited by: 0
References: 22

Abstract

ClinicalTrials.gov contains demographic data (race, ethnicity, sex/gender, age), but lacks a bulk export by trial ID. While an Application Programming Interface (API) exists, it requires technical skill. Since the 2017 Final Rule, demographic reporting has improved, but access remains limited. We developed a Python-based web app that extracts and standardizes demographics for user-defined NCT ID cohorts. It queries API version 2.0, normalizes data to U.S. Office of Management and Budget and Food and Drug Administration standards, and calculates percentages. In 1,464 cardiovascular trials, demographic availability and distributions varied. Outputs matched source data. This open tool supports equity audits and inclusive trial planning.

Fields of Study & Subjects

Sex and Gender in Healthcare Electronic Health Records Systems Machine Learning in Healthcare

Publication details

Journal / source
SoftwareX
Volume
34
Pages
102678–102678
Publication date
1 May 2026
Language
EN