基于磁共振成像的机器学习在阿尔茨海默病检测中的诊断性能:一项Meta分析
该Meta分析纳入19篇文献中的24个模型,评估基于结构MRI的机器学习区分 probable AD 与正常老年人的诊断性能。汇总敏感度0.85(95%CI 0.81-0.89),特异度0.88(95%CI 0.84-0.91),AUC 0.93(95%CI 0.91-0.95)。结论认为ML诊断性能良好,但需更多高质量前瞻性研究验证后方可临床推广。
要点
- 基于结构MRI的ML模型区分 probable AD 与正常老年人汇总AUC达0.93。
- 汇总敏感度0.85、特异度0.88,阳性似然比7.15,阴性似然比0.17。
- 目前证据仍限于研究场景,临床落地前需前瞻性大样本验证。
核心结论
- 基于结构MRI数据的机器学习在区分 probable AD 患者与正常老年人方面诊断性能良好。
- 在引入临床实践前,仍需更多高质量、大规模前瞻性研究以提升ML的可靠性和泛化性。
研究设计与样本
- 研究类型为系统评价与Meta分析,检索Medline、Embase和Cochrane Library截至2021年7月。
- 共纳入19篇论文中的24个模型,均基于ML算法提取的不同脑特征进行诊断。
- 采用QUADAS-2工具和CLAIM清单评估纳入研究的质量和潜在偏倚。
- 使用随机效应模型计算汇总敏感度和特异度,Deeks检验评估发表偏倚。
诊断标准与关键数值
- ML检测AD的汇总敏感度为0.85(95%CI 0.81-0.89),特异度为0.88(95%CI 0.84-0.91)。
- 汇总阳性似然比7.15(95%CI 5.40-9.47),阴性似然比0.17(95%CI 0.12-0.22)。
- 汇总诊断比值比43.34(95%CI 26.89-69.84),SROC曲线下面积0.93(95%CI 0.91-0.95)。
临床应用与阅片要点
- 结构MRI的ML模型可作为 probable AD 与正常老年人鉴别的辅助参考,但不能替代临床综合评估。
- 解读相关研究时需注意模型基于不同脑特征提取方法,阈值和特征定义各异,不宜直接跨模型套用。
局限性
- 纳入研究数量有限(19篇论文、24个模型),证据体量仍小。
- 原文指出需更多高质量、大规模前瞻性研究来提升ML的可靠性和泛化性。
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)。
英文原文(摘要)· 点击展开
PURPOSE: Advanced machine learning (ML) algorithms can assist rapid medical image recognition and realize automatic, efficient, noninvasive, and convenient diagnosis. We aim to further evaluate the diagnostic performance of ML to distinguish patients with probable Alzheimer's disease (AD) from normal older adults based on structural magnetic resonance imaging (MRI).
METHODS: The Medline, Embase, and Cochrane Library databases were searched for relevant literature published up until July 2021. We used the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool and Checklist for Artificial Intelligence in Medical Imaging (CLAIM) to evaluate all included studies' quality and potential bias. Random-effects models were used to calculate pooled sensitivity and specificity, and the Deeks' test was used to assess publication bias.
RESULTS: We included 24 models based on different brain features extracted by ML algorithms in 19 papers. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio, and area under the summary receiver operating characteristic curve for ML in detecting AD were 0.85 (95%CI 0.81-0.89), 0.88 (95%CI 0.84-0.91), 7.15 (95%CI 5.40-9.47), 0.17 (95%CI 0.12-0.22), 43.34 (95%CI 26.89-69.84), and 0.93 (95%CI 0.91-0.95).
CONCLUSION: ML using structural MRI data performed well in diagnosing probable AD patients and normal elderly. However, more high-quality, large-scale prospective studies are needed to further enhance the reliability and generalizability of ML for clinical applications before it can be introduced into clinical practice.
引用
- Hu, Wang, Guo, et al. Diagnostic performance of magnetic resonance imaging-based machine learning in Alzheimer's disease detection: a meta-analysis. Neuroradiology. 2022. PMID: 36477499. doi:10.1007/s00234-022-03098-2
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。