Predicting clinical trial duration via statistical and machine learning models

IF 1.4 Q4 MEDICINE, RESEARCH & EXPERIMENTAL

Contemporary Clinical Trials Communications Pub Date : 2025-03-31 DOI:10.1016/j.conctc.2025.101473

Joonhyuk Cho , Qingyang Xu , Chi Heem Wong , Andrew W. Lo

引用次数: 0

Abstract

We apply survival analysis as well as machine learning models to predict the duration of clinical trials using the largest dataset so far constructed in this domain. Neural network-based DeepSurv yields the most accurate predictions and we identify key factors that are most predictive of trial duration. This methodology may help clinical researchers optimize trial designs for expedited testing, and can also reduce the financial risk of drug development, which in turn will lower the cost of funding and increase the amount of capital allocated to this sector.

查看原文本刊更多论文

通过统计和机器学习模型预测临床试验持续时间

我们应用生存分析和机器学习模型来预测临床试验的持续时间，使用迄今为止在该领域构建的最大数据集。基于神经网络的DeepSurv产生最准确的预测，我们确定了最能预测试验持续时间的关键因素。这种方法可以帮助临床研究人员优化试验设计以加快测试，还可以降低药物开发的财务风险，从而降低资助成本并增加分配给该部门的资金数额。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Contemporary Clinical Trials Communications Pharmacology, Toxicology and Pharmaceutics-Pharmacology

CiteScore

2.70

自引率

6.70%

发文量

146

审稿时长

20 weeks

期刊介绍： Contemporary Clinical Trials Communications is an international peer reviewed open access journal that publishes articles pertaining to all aspects of clinical trials, including, but not limited to, design, conduct, analysis, regulation and ethics. Manuscripts submitted should appeal to a readership drawn from a wide range of disciplines including medicine, life science, pharmaceutical science, biostatistics, epidemiology, computer science, management science, behavioral science, and bioethics. Contemporary Clinical Trials Communications is unique in that it is outside the confines of disease specifications, and it strives to increase the transparency of medical research and reduce publication bias by publishing scientifically valid original research findings irrespective of their perceived importance, significance or impact. Both randomized and non-randomized trials are within the scope of the Journal. Some common topics include trial design rationale and methods, operational methodologies and challenges, and positive and negative trial results. In addition to original research, the Journal also welcomes other types of communications including, but are not limited to, methodology reviews, perspectives and discussions. Through timely dissemination of advances in clinical trials, the goal of Contemporary Clinical Trials Communications is to serve as a platform to enhance the communication and collaboration within the global clinical trials community that ultimately advances this field of research for the benefit of patients.