Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2026
|
| Online Access: | https://doi.org/10.5281/zenodo.20290088 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p>The Alzheimer’s Disease Common Data Element Ontology for Clinical Trials (AD-CDO) is a lightweight, data-driven semantic resource designed to formally represent the most frequent and impactful clinical concepts utilized in AD trial eligibility criteria. Unlike traditional top-down ontologies, AD-CDO was empirically derived by extracting over 38,000 clinical tokens from 1,500+ unstructured trial protocols using a hybrid NLP pipeline, followed by statistical optimization (Jenks Natural Breaks) to ensure computational efficiency without sacrificing coverage. The resulting ontology comprises 293 expertly curated classes distributed across seven practical clinical domains: Disease, Medication, Diagnostic Test, Procedure, Social Determinants of Health, Rating Criteria, and Fertility. To enable immediate downstream applicability in clinical informatics, every class is explicitly mapped to interoperable global standards, including the OMOP Common Data Model, UMLS, SNOMED CT, and NLM VSAC value sets. AD-CDO serves as an interoperable translational hub, allowing researchers to computationally transform narrative clinical text into executable EHR queries for automated cohort identification, computable phenotyping, and cross-study harmonization.</p>