文献速递医学人工智能与信息学流行病学与生物统计

肿瘤学领域基于机器学习的预后临床预测模型报告质量亟待改善

Reporting of prognostic clinical prediction models based on machine learning methods in oncology needs to be improved.
PubMed 文献 · J Clin Epidemiol · 2021-06-29

该系统综述检索2019年1月至5月MEDLINE和Embase数据库,纳入62篇肿瘤学领域使用机器学习方法开发预后临床预测模型的研究,采用TRIPOD声明评估报告质量。结果显示TRIPOD报告条目依从率中位数仅为41%,仅19%的出版物依从率至少达50%,开发-only研究报告依从性更低。

要点

  • 肿瘤学机器学习预后预测模型的TRIPOD报告依从率中位数仅41%
  • 仅19%(12/62)的出版物报告依从率至少达到50%
  • 仅开发研究的报告依从性(中位数38%)低于开发+验证研究(中位数49%)

核心结论

  • 肿瘤学领域使用机器学习的临床预测模型报告质量差,亟需紧急改进,以便读者和利益相关者能够评价研究方法、理解研究结果并减少研究浪费。

研究设计与样本

  • 系统综述,检索MEDLINE和Embase数据库2019年1月1日至2019年5月9日的文献,纳入肿瘤学领域使用机器学习方法(按原始研究作者定义)开发预后临床预测模型的非影像学研究。
  • 共纳入62篇出版物,其中48篇为仅开发研究,14篇为开发加验证研究;所有出版物共开发了152个模型。
  • 使用TRIPOD(多变量预测模型个体预后或诊断透明报告)声明评估纳入出版物的报告质量。

主要发现

  • TRIPOD报告条目依从率中位数为41%(范围10%-67%)。
  • 至少50%依从率的出版物占19%(n=12/62)。
  • 仅开发研究的依从率中位数为38%(范围10%-67%),开发加验证研究的依从率中位数为49%(范围33%-59%)。

关键数值与推荐

  • TRIPOD报告条目依从率中位数41%,范围10%-67%。
  • 至少50%依从率的出版物比例为19%(12/62)。
  • 仅开发研究依从率中位数38%(范围10%-67%),开发加验证研究依从率中位数49%(范围33%-59%)。

临床怎么用

  • 临床医生和研究人员在阅读肿瘤学机器学习预后预测模型研究时,应参照TRIPOD声明评估其报告完整性,谨慎解读研究结果。
  • 模型开发者在发表研究时应遵循TRIPOD报告规范,提高报告透明度,以利于方法评价和结果理解。

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: Evaluate the completeness of reporting of prognostic prediction models developed using machine learning methods in the field of oncology. STUDY DESIGN AND SETTING: We conducted a systematic review, searching the MEDLINE and Embase databases between 01/01/2019 and 05/09/2019, for non-imaging studies developing a prognostic clinical prediction model using machine learning methods (as defined by primary study authors) in oncology. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement to assess the reporting quality of included publications. We described overall reporting adherence of included publications and by each section of TRIPOD. RESULTS: Sixty-two publications met the inclusion criteria. 48 were development studies and 14 were development with validation studies. 152 models were developed across all publications. Median adherence to TRIPOD reporting items was 41% [range: 10%-67%] and at least 50% adherence was found in 19% (n=12/62) of publications. Adherence was lower in development only studies (median: 38% [range: 10%-67%]); and higher in development with validation studies (median: 49% [range: 33%-59%]). CONCLUSION: Reporting of clinical prediction models using machine learning in oncology is poor and needs urgent improvement, so readers and stakeholders can appraise the study methods, understand study findings, and reduce research waste.

来源:J Clin Epidemiol,查看原文。版权归原作者所有。

引用

  1. Dhiman P, Ma J, Navarro CA, et al. Reporting of prognostic clinical prediction models based on machine learning methods in oncology needs to be improved. J Clin Epidemiol. 2021. PMID: 34214626. doi:10.1016/j.jclinepi.2021.06.024

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。