系统文献综述:利用治疗前放射影像的机器学习算法预测胶质瘤分子亚型
本系统综述检索Ovid Embase、Ovid MEDLINE、Cochrane Central Register of Controlled Trials和Web of Science,筛选12,318篇摘要、1323篇全文,最终纳入85篇文章,比较不同机器学习方法从MR影像预测胶质瘤分子亚型的效果。异柠檬酸脱氢酶突变状态内部验证AUC 0.88、准确率85%,有限外部验证AUC 0.86、准确率87%;O6-甲基鸟嘌呤-DNA甲基转移酶启动子甲基化内部验证AUC 0.79、准确率77%,有限外部验证AUC 0.89、准确率83%。PROBAST评分显示所有文章存在高偏倚。
要点
- 异柠檬酸脱氢酶突变预测内部验证AUC 0.88、准确率85%,有限外部验证AUC 0.86、准确率87%。
- O6-甲基鸟嘌呤-DNA甲基转移酶启动子甲基化预测内部验证AUC 0.79、准确率77%,有限外部验证AUC 0.89、准确率83%。
- PROBAST评分显示所有文章存在高偏倚,外部验证使用有限。
核心结论
- 内部和外部验证数据集报告的胶质瘤分子亚型预测AUC和准确率较高,但外部验证使用有限且所有文章偏倚风险增高,可能阻碍这些技术的临床转化。
研究设计与样本
- 系统文献综述,遵循PRISMA指南,筛选12,318篇摘要、1323篇全文,最终纳入85篇文章,比较不同机器学习方法从MR影像预测胶质瘤分子亚型,并依据PROBAST指南对每项研究进行偏倚分析。
诊断标准与关键数值
- 异柠檬酸脱氢酶突变状态预测:内部验证AUC 0.88、准确率85%;有限外部验证数据集AUC 0.86、准确率87%。
- O6-甲基鸟嘌呤-DNA甲基转移酶启动子甲基化预测:内部验证AUC 0.79、准确率77%;有限外部验证AUC 0.89、准确率83%。
局限性
- 外部验证数量少和数据不完整的研究导致数据分析不均衡。
- 比较每项研究的最佳预测流程可能引入偏倚。
- PROBAST评分显示所有文章存在高偏倚。
- 外部验证使用有限和所有文章偏倚风险增高可能阻碍这些技术的临床转化。
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)。
英文原文(摘要)· 点击展开
BACKGROUND: The molecular profile of gliomas is a prognostic indicator for survival, driving clinical decision-making for treatment. Pathology-based molecular diagnosis is challenging because of the invasiveness of the procedure, exclusion from neoadjuvant therapy options, and the heterogeneous nature of the tumor.
PURPOSE: We performed a systematic review of algorithms that predict molecular subtypes of gliomas from MR Imaging.
DATA SOURCES: Data sources were Ovid Embase, Ovid MEDLINE, Cochrane Central Register of Controlled Trials, Web of Science.
STUDY SELECTION: Per the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, 12,318 abstracts were screened and 1323 underwent full-text review, with 85 articles meeting the inclusion criteria.
DATA ANALYSIS: We compared prediction results from different machine learning approaches for predicting molecular subtypes of gliomas. Bias analysis was conducted for each study, following the Prediction model Risk Of Bias Assessment Tool (PROBAST) guidelines.
DATA SYNTHESIS: Isocitrate dehydrogenase mutation status was reported with an area under the curve and accuracy of 0.88 and 85% in internal validation and 0.86 and 87% in limited external validation data sets, respectively. For the prediction of O6-methylguanine-DNA methyltransferase promoter methylation, the area under the curve and accuracy in internal validation data sets were 0.79 and 77%, and in limited external validation, 0.89 and 83%, respectively. PROBAST scoring demonstrated high bias in all articles.
LIMITATIONS: The low number of external validation and studies with incomplete data resulted in unequal data analysis. Comparing the best prediction pipelines of each study may introduce bias.
CONCLUSIONS: While the high area under the curve and accuracy for the prediction of molecular subtypes of gliomas are reported in internal and external validation data sets, limited use of external validation and the increased risk of bias in all articles may present obstacles for clinical translation of these techniques.
引用
- Lost J, Verma T, Jekel L, et al. Systematic Literature Review of Machine Learning Algorithms Using Pretherapy Radiologic Imaging for Glioma Molecular Subtype Prediction. AJNR Am J Neuroradiol. 2023. PMID: 37770204. doi:10.3174/ajnr.A8000
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。