Predicting accrual success for better clinical trial resource allocation
Abstract Accrual success is one key determining factor for the success of clinical trials. Global data analyses of all terminated trials reported that 55% of trials were terminated due to low accrual rates. Failure to meet accrual goals have a significant impact on costs for sponsors, academic insti...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-88400-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571816919433216 |
|---|---|
| author | Sisi Ma Yinzhao Wang John Wagner Steve Johnson Serguei Pakhomov Constantin Aliferis |
| author_facet | Sisi Ma Yinzhao Wang John Wagner Steve Johnson Serguei Pakhomov Constantin Aliferis |
| author_sort | Sisi Ma |
| collection | DOAJ |
| description | Abstract Accrual success is one key determining factor for the success of clinical trials. Global data analyses of all terminated trials reported that 55% of trials were terminated due to low accrual rates. Failure to meet accrual goals have a significant impact on costs for sponsors, academic institutions, investigators, and society at large. The ability to predict trial accrual success with high precision before the trial starts would be highly valuable, preventing the allocation of critical resources for trials unlikely to meet accrual goals. In the present study, we constructed a dataset for predicting clinical trial failure based on poor accrual using clinicaltrial.gov data containing information on 57,846 trials. Features of the dataset were informed by prior literature and constructed using data-driven natural language processing methods. We built predictive models for accrual failure using state-of-the-art supervised machine learning protocols and methods. Models resulted in good predictive performance that was stable over a 10-year time period, with predictive performance of cross-validation AUC = 0.744 (+/-0.018) and prospective validation AUC = 0.737 (+/-0.038). We also improved model calibration and examined model performance with the reject option. These modifications enable model translation into decision support tools for various real-world settings. To the best of our knowledge, this is the first study to develop models for predicting clinical trial failure due to accrual based on a large dataset with a comprehensive set of trial features. |
| format | Article |
| id | doaj-art-b55b9a73369e4bc3b1f3da218d603972 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-b55b9a73369e4bc3b1f3da218d6039722025-02-02T12:18:22ZengNature PortfolioScientific Reports2045-23222025-01-0115111510.1038/s41598-025-88400-xPredicting accrual success for better clinical trial resource allocationSisi Ma0Yinzhao Wang1John Wagner2Steve Johnson3Serguei Pakhomov4Constantin Aliferis5Institute for Health Informatics, University of MinnesotaInstitute for Health Informatics, University of MinnesotaMedical School, University of MinnesotaInstitute for Health Informatics, University of MinnesotaCollege of Pharmacy, University of MinnesotaInstitute for Health Informatics, University of MinnesotaAbstract Accrual success is one key determining factor for the success of clinical trials. Global data analyses of all terminated trials reported that 55% of trials were terminated due to low accrual rates. Failure to meet accrual goals have a significant impact on costs for sponsors, academic institutions, investigators, and society at large. The ability to predict trial accrual success with high precision before the trial starts would be highly valuable, preventing the allocation of critical resources for trials unlikely to meet accrual goals. In the present study, we constructed a dataset for predicting clinical trial failure based on poor accrual using clinicaltrial.gov data containing information on 57,846 trials. Features of the dataset were informed by prior literature and constructed using data-driven natural language processing methods. We built predictive models for accrual failure using state-of-the-art supervised machine learning protocols and methods. Models resulted in good predictive performance that was stable over a 10-year time period, with predictive performance of cross-validation AUC = 0.744 (+/-0.018) and prospective validation AUC = 0.737 (+/-0.038). We also improved model calibration and examined model performance with the reject option. These modifications enable model translation into decision support tools for various real-world settings. To the best of our knowledge, this is the first study to develop models for predicting clinical trial failure due to accrual based on a large dataset with a comprehensive set of trial features.https://doi.org/10.1038/s41598-025-88400-xClinical trialClinical trial accrualPredictionDecision support |
| spellingShingle | Sisi Ma Yinzhao Wang John Wagner Steve Johnson Serguei Pakhomov Constantin Aliferis Predicting accrual success for better clinical trial resource allocation Scientific Reports Clinical trial Clinical trial accrual Prediction Decision support |
| title | Predicting accrual success for better clinical trial resource allocation |
| title_full | Predicting accrual success for better clinical trial resource allocation |
| title_fullStr | Predicting accrual success for better clinical trial resource allocation |
| title_full_unstemmed | Predicting accrual success for better clinical trial resource allocation |
| title_short | Predicting accrual success for better clinical trial resource allocation |
| title_sort | predicting accrual success for better clinical trial resource allocation |
| topic | Clinical trial Clinical trial accrual Prediction Decision support |
| url | https://doi.org/10.1038/s41598-025-88400-x |
| work_keys_str_mv | AT sisima predictingaccrualsuccessforbetterclinicaltrialresourceallocation AT yinzhaowang predictingaccrualsuccessforbetterclinicaltrialresourceallocation AT johnwagner predictingaccrualsuccessforbetterclinicaltrialresourceallocation AT stevejohnson predictingaccrualsuccessforbetterclinicaltrialresourceallocation AT sergueipakhomov predictingaccrualsuccessforbetterclinicaltrialresourceallocation AT constantinaliferis predictingaccrualsuccessforbetterclinicaltrialresourceallocation |