Will they participate? Predicting patients' response to clinical trial invitations in a pediatric emergency
Yizhao Ni1, Andrew F Beck2, Regina Taylor3
1Department of Biomedical Informatics, Cincinnati Children's Hospital Medical Center, Cincinnati, OH 45229-3039, USA yizhao.ni@cchmc.org.
Insights
Machine learning algorithms can predict patient participation in clinical trials. This approach significantly improves upon random prediction, optimizing patient recruitment strategies for better trial enrollment.
Area of Science:
- Clinical Informatics
- Biostatistics
- Machine Learning
Background:
- Patient recruitment is a critical bottleneck in clinical trial success.
- Predicting patient willingness to participate can streamline trial enrollment.
- Current recruitment methods often rely on manual processes with limited predictive power.
Purpose of the Study:
- To develop an automated algorithm for predicting patient response to clinical trial invitations.
- To evaluate the algorithm's performance using real-world data from a pediatric emergency department.
- To identify key predictors influencing patient decisions regarding clinical trial participation.
Main Methods:
- Collected response data from 3345 patients across 18 clinical trials.
- Retrospectively extracted demographic, socioeconomic, and clinical data.
- Applied machine learning algorithms to predict participation and identify influential features.
Main Results:
- Machine learning algorithms significantly outperformed random prediction (e.g., 71.52% precision, 92.68% recall on test set).
- Validated algorithm performance using precision, recall, F-measure, and ROC curve analysis.
- Identified key predictors and confirmed literature findings, highlighting areas for recruitment optimization.
Conclusions:
- Automated prediction using machine learning algorithms shows great potential for enhancing clinical trial recruitment.
- Predictive models can improve the efficiency and effectiveness of approaching patients for trial invitations.
- Further research can leverage these findings to optimize patient recruitment processes.
Objective:
(1) To develop an automated algorithm to predict a patient's response (ie, if the patient agrees or declines) before he/she is approached for a clinical trial invitation; (2) to assess the algorithm performance and the predictors on real-world patient recruitment data for a diverse set of clinical trials in a pediatric emergency department; and (3) to identify directions for future studies in predicting patients' participation response.
Materials And Methods:
We collected 3345 patients' response to trial invitations on 18 clinical trials at one center that were actively enrolling patients between January 1, 2010 and December 31, 2012. In parallel, we retrospectively extracted demographic, socioeconomic, and clinical predictors from multiple sources to represent the patients' profiles. Leveraging machine learning methodology, the automated algorithms predicted participation response for individual patients and identified influential features associated with their decision-making. The performance was validated on the collection of actual patient response, where precision, recall, F-measure, and area under the ROC curve were assessed.
Results:
Compared to the random response predictor that simulated the current practice, the machine learning algorithms achieved significantly better performance (Precision/Recall/F-measure/area under the ROC curve: 70.82%/92.02%/80.04%/72.78% on 10-fold cross validation and 71.52%/92.68%/80.74%/75.74% on the test set). By analyzing the significant features output by the algorithms, the study confirmed several literature findings and identified challenges that could be mitigated to optimize recruitment.
Conclusion:
By exploiting predictive variables from multiple sources, we demonstrated that machine learning algorithms have great potential in improving the effectiveness of the recruitment process by automatically predicting patients' participation response to trial invitations.
More Related Videos
06:28E-Patient Counseling Trial E-PACO: Computer Based Education versus Nurse Counseling for Patients to Prepare for Colonoscopy
Published on: August 1, 2019
07:31Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Related Concept Videos
01:16Clinical Trials
There are four phases in a clinical trial. A phase one...
01:11Clinical Trials: Overview