文献速递医学人工智能与信息学流行病学与生物统计基础与转化研究

肿瘤学机器学习预后模型研究的开放科学实践需大幅改进

Open science practices need substantial improvement in prognostic model studies in oncology using machine learning.
PubMed 文献 · J Clin Epidemiol · 2023-10-28

该系统综述检索2022年12月MEDLINE数据库,纳入46篇使用机器学习开发肿瘤多变量预后模型的研究。开放科学实践采纳率低:仅1项报告研究方案、1项注册、2项共享数据、12项提供代码共享声明,11项提供模型可用信息,8项使用报告指南。

要点

  • 仅1项研究报告研究方案,仅1项研究注册。
  • 35项(76%)提供数据共享声明,但仅2项(4%)实际共享数据。
  • 仅11项(24%)提供足够信息使模型可用于实践。

核心结论

  • 肿瘤学中使用机器学习方法开发预后模型的研究对开放科学原则的采纳情况差。
  • 肿瘤学预测研究需要指导和增加对开放科学益处及最佳实践的认识。

研究设计与样本

  • 系统综述,检索MEDLINE数据库2022年12月1日至2022年12月31日期间使用机器学习方法(按作者定义)开发肿瘤学多变量预后模型的研究。
  • 由两位作者独立筛选记录并提取开放科学实践信息,共纳入46篇描述多变量预后模型开发的文献。

主要发现

  • 仅1项研究报告了研究方案可用性,仅1项研究注册。
  • 35项研究(76%)提供数据共享声明,其中21项(46%)表示数据可向作者索取,7项声明数据共享不适用,2项研究(4%)实际共享数据。
  • 仅12项研究(26%)提供代码共享声明,其中2项(4%)表示代码可向作者索取。
  • 仅11项研究(24%)提供足够信息使模型可用于实践。
  • 8项研究(18%)提及使用报告指南,其中4项(10%)使用TRIPOD声明,1项(2%)使用MI-CLAIM和CONSORT-AI,1项(2%)使用STROBE,1项(2%)使用STARD,1项(2%)使用TREND。

局限性

  • 原文未报告局限性

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVE: To describe the frequency of open science practices in a contemporary sample of studies developing prognostic models using machine learning methods in the field of oncology. STUDY DESIGN AND SETTING: We conducted a systematic review, searching the MEDLINE database between December 1, 2022, and December 31, 2022, for studies developing a multivariable prognostic model using machine learning methods (as defined by the authors) in oncology. Two authors independently screened records and extracted open science practices. RESULTS: We identified 46 publications describing the development of a multivariable prognostic model. The adoption of open science principles was poor. Only one study reported availability of a study protocol, and only one study was registered. Funding statements and conflicts of interest statements were common. Thirty-five studies (76%) provided data sharing statements, with 21 (46%) indicating data were available on request to the authors and seven declaring data sharing was not applicable. Two studies (4%) shared data. Only 12 studies (26%) provided code sharing statements, including 2 (4%) that indicated the code was available on request to the authors. Only 11 studies (24%) provided sufficient information to allow their model to be used in practice. The use of reporting guidelines was rare: eight studies (18%) mentioning using a reporting guideline, with 4 (10%) using the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis Or Diagnosis statement, 1 (2%) using Minimum Information About Clinical Artificial Intelligence Modeling and Consolidated Standards Of Reporting Trials-Artificial Intelligence, 1 (2%) using Strengthening The Reporting Of Observational Studies In Epidemiology, 1 (2%) using Standards for Reporting Diagnostic Accuracy Studies, and 1 (2%) using Transparent Reporting of Evaluations with Nonrandomized Designs. CONCLUSION: The adoption of open science principles in oncology studies developing prognostic models using machine learning methods is poor. Guidance and an increased awareness of benefits and best practices of open science are needed for prediction research in oncology.

来源:J Clin Epidemiol,查看原文。版权归原作者所有。

引用

  1. Collins GS, Whittle R, Bullock GS, et al. Open science practices need substantial improvement in prognostic model studies in oncology using machine learning. J Clin Epidemiol. 2023. PMID: 37898461. doi:10.1016/j.jclinepi.2023.10.015

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。