指南与共识产科母胎医学

机器学习预测SGA与FGR对TRIPOD+AI指南依从性的系统综述

Assessing adherence to TRIPOD+AI guidelines in machine learning models for predicting small for gestational age and fetal growth restriction: a systematic review.
指南 / 共识 · Am J Obstet Gynecol MFM · 2025-11-28

该系统综述检索MEDLINE和Scopus(2024年6月21日),纳入20项使用常规临床变量预测FGR/SGA的机器学习模型研究。FGR/SGA定义不一致,TRIPOD+AI依从性参差不齐,仅15%报告校准,仅30%满足最低样本量,提示过拟合与泛化受限。

要点

  • FGR/SGA定义不一致,尤其在技术类期刊中
  • 无模型报告公平性或亚组异质性,仅15%报告校准
  • 仅30%研究满足机器学习最低样本量要求

核心结论

  • 机器学习预测FGR/SGA虽有潜力,但存在结局定义不一致、模型效能不足及校准与临床适用性报告欠佳等关键局限。

研究设计与样本

  • 遵循PRISMA 2020指南,于2024年6月21日检索MEDLINE和Scopus,最终纳入20项使用常规临床变量预测FGR/SGA并报告至少AUROC和/或准确率的机器学习模型研究。
  • 排除预印本、会议摘要、系统综述、动物研究及仅依赖生物标志物或基因组学的模型。
  • 由两名独立评审员借助Rayyan软件筛选文献,使用PROBAST清单评估偏倚风险,采用4点Likert量表评估对TRIPOD+AI指南方法、结果和讨论部分的依从性,并评估样本量是否充足。

主要发现

  • 检索共识别272项研究,其中20项符合纳入标准。
  • FGR/SGA定义不一致,尤其在技术类期刊中更为明显。
  • 对TRIPOD+AI指南的依从性参差不齐,无模型报告公平性或相关亚组间的异质性,仅15%报告校准。
  • 仅30%的研究满足机器学习模型所需的最低样本量,提示潜在过拟合和泛化能力有限。

临床怎么用

  • 临床解读机器学习预测FGR/SGA模型时,应关注结局定义是否统一、样本量是否充足以及校准度是否报告。

局限性

  • 仅纳入MEDLINE和Scopus检索的研究,可能遗漏其他数据库文献。
  • 排除了仅依赖生物标志物或基因组学的模型,可能限制对部分临床场景的覆盖。

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

OBJECTIVES: Fetal growth restriction (FGR) significantly contribute to perinatal morbidity, mortality, and long-term adverse health outcomes. While small for gestational age (SGA) is often used as a proxy for FGR, it does not necessarily indicate pathological growth restriction. Given the increasing interest in machine learning (ML) for predicting FGR/SGA, this study systematically reviews ML applications in this domain, evaluating their methodological rigor and reporting quality, following standardized guidelines. DATA SOURCES: The systematic search was conducted in MEDLINE and Scopus on June 21, 2024, following PRISMA 2020 guidelines. STUDY ELIGIBILITY CRITERIA: Eligible studies implemented ML models for FGR/SGA prediction using routinely available clinical variables and reported at least one area under the receiver operating characteristic (AUROC) and/or accuracy. Exclusions included preprints, conference abstracts, systematic reviews, animal studies, and models relying exclusively on biomarkers or genomics, as not part of the clinical practice. STUDY APPRAISAL AND SYNTHESIS METHODS: Two independent reviewers screened articles with the help of the Rayyan software. Risk of bias was assessed using the PROBAST checklist. Adherence to the guidelines on the transparent reporting of a multivariable prediction model for individual prognosis or diagnosis+artificial intelligence (TRIPOD+AI) was evaluated across methods, results, and discussion sections using a 4-point Likert scale. Sample size adequacy was assessed for each study, accounting for outcome type, predictors, and outcome prevalence. RESULTS: The search identified 272 studies, with 20 meeting the inclusion criteria. Definitions of FGR/SGA were inconsistent, particularly in technical journals. Adherence to TRIPOD+AI guidelines was variable, as no model reported on fairness or heterogeneity across relevant subgroups, and only 15% reported on calibration. Only 30% of studies met the minimum sample size required for ML models, indicating potential overfitting and limited generalizability. CONCLUSION: Despite the potential of ML models in predicting FGR/SGA, key limitations persist, including inconsistent outcome definitions, underpowered models, and suboptimal reporting of calibration and clinical applicability. Future studies should emphasize standardized definitions, robust sample sizes, and comprehensive reporting to enhance model reliability and clinical translation. VIDEO ABSTRACT.

来源:Am J Obstet Gynecol MFM,查看原文。版权归原作者所有。

引用

  1. Zamagni G, Fregona C, Barbieri M, et al. Assessing adherence to TRIPOD+AI guidelines in machine learning models for predicting small for gestational age and fetal growth restriction: a systematic review. Am J Obstet Gynecol MFM. 2025. PMID: 41320158. doi:10.1016/j.ajogmf.2025.101862

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。