Related Experiment Video
Updated: Aug 14, 2025
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Clinical research staff perceptions on a natural language processing-driven tool for eligibility prescreening: An
Betina Idnay1, Yilu Fang2, Caitlin Dreisbach3
1Columbia University, School of Nursing, New York, NY, USA; Columbia University, Department of Neurology, New York, NY, USA; Columbia University, Department of Biomedical Informatics, New York, NY, USA.
Criteria2Query (C2Q) improves clinical trial recruitment by semi-autonomously identifying eligible patients. This natural language processing tool demonstrated high usability among research staff after iterative refinements.
Area of Science:
- Clinical research informatics
- Human-computer interaction
- Natural language processing
Background:
- Participant recruitment is a major challenge in clinical research.
- Manual eligibility prescreening of electronic health records is resource-intensive.
- Criteria2Query (C2Q) was developed to semi-autonomously identify eligible patients using NLP.
Purpose of the Study:
- To evaluate the perceived usability of the Criteria2Query (C2Q) tool.
- To assess C2Q's effectiveness for clinical research eligibility prescreening.
Main Methods:
- Usability testing using cognitive walkthrough and think-aloud protocol with 20 research staff.
- Iterative system refinement based on expert-rated usability problems.
- Directed deductive content analysis of transcribed evaluations guided by an HCI framework.
Main Results:
- C2Q demonstrated high usability (2.26/7) in the final refinement cycle.
- Usability issues decreased with each iterative refinement.
- Key themes identified related to user goals, task performance, and system navigation.
Conclusions:
- Iterative refinement informed by usability testing significantly improved C2Q.
- C2Q is a usable tool for clinical research staff in eligibility prescreening.
- Recommendations focus on enhancing system intuitiveness and user experience.
More Related Videos
07:31Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
08:53Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community
Published on: May 31, 2019
