中国循证医学杂志2024,Vol.24Issue(12) :1411-1418.DOI:10.7507/1672-2531.202405140

基于18F-FDG PET/CT与结构MRI的人工智能辅助诊断系统在阿尔茨海默病中诊断准确性比较的Meta分析

Accuracy comparison of artificial intelligence-assisted diagnosis systems based on 18F-FDG PET/CT and structural MRI in the diagnosis of Alzheimer's disease:a meta-analysis

赵太良 王冰冰 梁威 程森 高海东 王建业 寿记新
中国循证医学杂志2024,Vol.24Issue(12) :1411-1418.DOI:10.7507/1672-2531.202405140

基于18F-FDG PET/CT与结构MRI的人工智能辅助诊断系统在阿尔茨海默病中诊断准确性比较的Meta分析

Accuracy comparison of artificial intelligence-assisted diagnosis systems based on 18F-FDG PET/CT and structural MRI in the diagnosis of Alzheimer's disease:a meta-analysis

赵太良 1王冰冰 1梁威 1程森 1高海东 1王建业 1寿记新2
扫码查看

作者信息

  • 1. 郑州大学第五附属医院神经外科(郑州 450052)
  • 2. 郑州大学第五附属医院神经外科(郑州 450052);郑州大学(郑州 450052)
  • 折叠

摘要

目的 比较基于18氟-脱氧葡萄糖PET/CT(18F-deoxyglucose PET/CT,18F-FDG PET/CT)与结构MRI(structural MRI,sMRI)的人工智能(artificial intelligence,AI)辅助诊断系统在阿尔茨海默病(Alzheimer disease,AD)中的诊断准确性.方法 计算机检索Web of Science、PubMed和Embase数据库,搜集有关开发或验证基于18F-FDG PET/CT或sMRI用于AD诊断的AI辅助诊断系统的诊断性研究,检索时限均从建库至2024年4月.由2名研究者独立筛选文献、提取资料并使用PROBAST清单评价纳入研究的偏倚风险和临床适用性后,采用双变量随机效应模型计算合并灵敏度、特异度和综合受试者操作特征(summary receiver operating characteristic,SROC)曲线下面积(area under curve,AUC).结果 共纳入26篇研究,提取了 38项有关诊断性能的2x2列联表.其中,24项基于18F-FDG PET/CT区分AD患者与认知功能正常(normal cognitive,NC)人群;14项基于sMRI区分AD患者与NC人群.Meta分析结果显示:对于18F-FDG PET/CT,AI辅助诊断系统合并灵敏度、特异度和 AUC 分别为 89%[95%CI(88%,91%)]、93%[95%CI(91%,94%)]和 0.96[95%CI(0.93,0.97)];对于sMRI,AI辅助诊断系统合并灵敏度、特异度和SROC-AUC分别为88%[95%CI(85%,90%)]、90%[95%CI(87%,92%)]和 0.94[95%CI(0.92,0.96)].结论 基于 18F-FDG PET/CT 或 sMRI 的 AI 辅助诊断系统在诊断AD时展现出了相似的性能,两者均具备较高的准确性.

Abstract

Objective To conduct a meta-analysis comparing the accuracy of artificial intelligence(AI)-assisted diagnostic systems based on 18F-fluorodeoxyglucose PET/CT(18F-FDG PET/CT)and structural MRI(sMRI)in the diagnosis of Alzheimer's disease(AD).Methods Original studies dedicated to the development or validation of AI-assisted diagnostic systems based on 18F-FDG PET/CT or sMRI for AD diagnosis were retrieved from the Web of Science,PubMed,and Embase databases.Studies meeting the inclusion criteria were collected,and the risk of bias and clinical applicability of the included studies were assessed using the PROBAST checklist.The pooled sensitivity,specificity,and area under the summary receiver operating characteristic(SROC)curve(AUC)were calculated using a bivariate random-effects model.Results Twenty-six studies met the inclusion criteria,yielding a total of 38 2x2 contingency tables related to diagnostic performance.Specifically,24 contingency tables were based on 18F-FDG PET/CT to distinguish AD patients from normal cognitive(NC)controls,and 14 contingency tables were based on sMRI for the same purpose.The meta-analysis results showed that for 18F-FDG PET/CT,the AI-assisted diagnostic systems had a pooled sensitivity,specificity,and SROC-AUC of 89%(95%CI 88%to 91%),93%(95%CI 91%to 94%),and 0.96(95%CI 0.93 to 0.97),respectively.For sMRI,the AI-assisted diagnostic systems had a pooled sensitivity,specificity,and SROC-AUC of 88%(95%CI 85%to 90%),90%(95%CI 87%to 92%),and 0.94(95%CI 0.92 to 0.96),respectively.Conclusion AI-assisted diagnostic systems based on either 18F-FDG PET/CT or sMRI demonstrated similar performance in the diagnosis of AD,with both showing high accuracy.

关键词

人工智能/阿尔茨海默病/正电子发射型计算机断层显像/磁共振成像/Meta分析

Key words

Artificial intelligence/Alzheimer's disease/Positron emission tomography/Magnetic resonance imaging/Meta-analysis

引用本文复制引用

出版年

2024
中国循证医学杂志
四川大学

中国循证医学杂志

CSTPCDCSCD北大核心
影响因子:1.761
ISSN:1672-2531
段落导航相关论文