Related Experiment Video
Updated: May 20, 2026

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
Published on: September 20, 2018
A human-computer collaborative approach to identifying common data elements in clinical trial eligibility criteria
Zhihui Luo1, Riccardo Miotto, Chunhua Weng
1Department of Biomedical Informatics, Columbia University, New York, NY 10032, United States.
This study developed a human-computer approach to efficiently identify common data elements (CDEs) in clinical trial eligibility criteria. The method significantly aids experts in extracting crucial disease-specific information from complex trial data.
Area of Science:
- Biomedical Informatics
- Clinical Trial Design
- Data Standardization
Background:
- Clinical trial eligibility criteria are complex and often unstructured.
- Identifying common data elements (CDEs) is crucial for trial analysis and comparison.
- Manual extraction of CDEs is time-consuming and prone to errors.
Purpose of the Study:
- To develop and evaluate a human-computer collaborative approach for identifying disease-specific CDEs in clinical trial eligibility criteria.
- To leverage natural language processing and data mining techniques for automated CDE extraction.
- To assess the efficiency and accuracy of the proposed method compared to manual identification.
Main Methods:
- Utilized free-text eligibility criteria from breast cancer and cardiovascular disease trials.
- Employed a semantic annotator to identify Unified Medical Language System (UMLS) terms.
- Applied the Apriori algorithm for frequent term mining, followed by filtering, grouping, and manual review.
Main Results:
- Achieved an average precision of 0.823 and recall of 0.797, resulting in an F-score of 0.810.
- The machine-powered approach identified 80% of cardiovascular CDEs from a reputable source.
- Demonstrated significant effort savings in identifying disease-specific CDEs.
Conclusions:
- A human-computer collaborative approach is feasible and effective for CDE identification.
- This method augments domain experts, improving efficiency and accuracy.
- Facilitates standardization and enhances the comparability of clinical trial data.
Related Concept Videos
Clinical Trials
There are four phases in a clinical trial. A phase one...
Clinical Trials: Overview
Hazard Ratio
For example, in a clinical trial evaluating a...
Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast, controlled...
Methods of Documentation V: CBE
In CBE, healthcare professionals establish predefined standards of practice that define what constitutes...
Clinically Relevant Drug Product Specifications: Methods of Establishment
