文献速递神经肿瘤

机器学习预测中线胶质瘤H3K27M突变的性能:系统评价与Meta分析

The Performance of Machine Learning for Prediction of H3K27 M Mutation in Midline Gliomas: A Systematic Review and Meta-Analysis.
PubMed 文献 · World Neurosurg · 2023-11-22

该系统评价与Meta分析检索了截至2023年5月的文献,纳入13项研究共1510例弥漫性中线胶质瘤患者,其中6项研究进入Meta分析。基于MRI的机器学习模型预测H3K27M突变的汇总敏感度为0.91、特异度为0.81,诊断性能良好,但置信区间宽,需进一步研究。

要点

  • 基于MRI放射组学的机器学习模型预测H3K27M突变汇总敏感度0.91(95%CI 0.77-0.97),特异度0.81(95%CI 0.73-0.88)。
  • 汇总阳性似然比4.86(95%CI 3.25-7.24),阴性似然比0.11(95%CI 0.04-0.29)。
  • 汇总诊断比值比42.61(95%CI 13.77-131.87),但置信区间宽,需进一步研究提高准确性。

核心结论

  • 基于MRI放射组学的机器学习模型无创预测弥漫性中线胶质瘤H3K27M突变状态具有良好的诊断性能,是有前景的工具;但汇总指标置信区间宽,需进一步研究提高机器学习算法准确性并促进其融入日常临床实践。

研究设计与样本

  • 系统评价与Meta分析,检索PubMed/Medline、Scopus、Embase和Web of Science从建库至2023年5月,纳入评估机器学习模型预测弥漫性中线胶质瘤H3K27M突变诊断性能的原始研究。
  • 共纳入13项研究(12项回顾性研究,1项同时为回顾性和前瞻性研究),包含1510例弥漫性中线胶质瘤患者(男性777例)。
  • 采用QUADAS-2进行质量评价,使用STATA version 17.0计算汇总敏感度、特异度、阳性似然比、阴性似然比、诊断评分和诊断比值比。

主要发现

  • 6项研究进入Meta分析,汇总敏感度为0.91(95%CI 0.77-0.97)。
  • 汇总特异度为0.81(95%CI 0.73-0.88)。
  • 汇总阳性似然比为4.86(95%CI 3.25-7.24),阴性似然比为0.11(95%CI 0.04-0.29)。
  • 汇总诊断评分为3.75(95%CI 2.62-4.88),诊断比值比为42.61(95%CI 13.77-131.87)。

临床怎么用

  • 原文结论认为基于MRI放射组学的机器学习模型是无创预测H3K27M突变状态的有前景工具,但汇总指标置信区间宽,需进一步研究提高算法准确性并促进其融入日常临床实践。

局限性

  • 汇总指标置信区间宽,需要进一步研究提高机器学习算法准确性并促进其融入日常临床实践。

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

BACKGROUND: Diffuse midline gliomas (DMGs) encompass a set of tumors, and those tumors with H3K27 M mutation carry a poor prognosis. In recent years, machine learning (ML)-based radiomics have shown promising results in predicting gene mutation status non-invasively. Therefore, this study aims to comprehensively evaluate the diagnostic performance of ML-based magnetic resonance imaging radiomics in predicting H3K27 M mutation status in DMG patients. METHODS: A systematic search was conducted using relevant keywords in PubMed/Medline, Scopus, Embase, and Web of Science from inception to May 2023. Original studies evaluating the diagnostic performance of ML models in predicting H3K27 M mutation status in DMGs were enrolled. Quality assessment of the enrolled studies was conducted using QUADAS-2. Data were analyzed using STATA version 17.0 to calculate pooled sensitivity, specificity, positive and negative likelihood ratio, diagnostic score, and diagnostic odds ratio. RESULTS: A total of 13 studies, including 12 retrospectives and 1 both retrospective and prospective study, enrolled 1510 (male = 777) DMG patients. Six studies underwent meta-analysis which showed a pooled sensitivity, specificity, positive and negative likelihood ratio, diagnostic score, and diagnostic odds ratio of 0.91 (95% CI 0.77-0.97), 0.81 (95% CI 0.73-0.88), 4.86 (95% CI 3.25-7.24), 0.11 (95% CI 0.04-0.29), 3.75 (95% CI 2.62-4.88), and 42.61 (95% CI 13.77-131.87), respectively. CONCLUSIONS: Non-invasive prediction of H3K27 M mutation status in patients with DMGs using magnetic resonance imaging radiomics is a promising tool with good diagnostic performance. However, the pooled metrics had a wide confidence interval, which required further studies to enhance ML algorithms' accuracy and facilitate their integration into daily clinical practice.

来源:World Neurosurg,查看原文。版权归原作者所有。

引用

  1. Habibi MA, Aghaei F, Tajabadi Z, et al. The Performance of Machine Learning for Prediction of H3K27 M Mutation in Midline Gliomas: A Systematic Review and Meta-Analysis. World Neurosurg. 2023. PMID: 37995996. doi:10.1016/j.wneu.2023.11.061

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。