{"title":"人工智能辅助氟-18氟脱氧葡萄糖正电子发射断层扫描与结构磁共振成像在阿尔茨海默病诊断准确性的比较：系统评价和荟萃分析。","authors":"Bingbing Wang, Tailiang Zhao, Rongrong Ma, Xiaochuan Huo, Xiaoxiao Xiong, Minjie Wu, Yuran Wang, Liu Liu, Zhijiang Zhuang, Bin Wang, Jixin Shou","doi":"10.2196/76981","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Neuroimaging is crucial in the diagnosis of Alzheimer disease (AD). In recent years, artificial intelligence (AI)-based neuroimaging technology has rapidly developed, providing new methods for accurate diagnosis of AD, but its performance differences still need to be systematically evaluated.</p><p><strong>Objective: </strong>This study aims to conduct a systematic review and meta-analysis comparing the diagnostic performance of AI-assisted fluorine-18 fluorodeoxyglucose positron emission tomography (18F-FDG PET) and structural magnetic resonance imaging (sMRI) for AD.</p><p><strong>Methods: </strong>Databases including Web of Science, PubMed, and Embase were searched from inception to January 2025 to identify original studies that developed or validated AI models for AD diagnosis using 18F-FDG PET or sMRI. Methodological quality was assessed using the TRIPOD-AI (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis-Artificial Intelligence) checklist. A bivariate mixed-effects model was employed to calculate pooled sensitivity, specificity, and summary receiver operating characteristic curve area (SROC-AUC).</p><p><strong>Results: </strong>A total of 38 studies were included, with 28 moderate-to-high-quality studies analyzed. Pooled SROC-AUC values were 0.94 (95% CI 0.92-0.96) for sMRI and 0.96 (95% CI 0.94-0.98) for 18F-FDG PET, demonstrating statistically significant intermodal differences (P=.02). Subgroup analyses revealed that for machine learning, pooled SROC-AUCs were 0.89 (95% CI 0.86-0.92) for sMRI and 0.95 (95% CI 0.92-0.96) for 18F-FDG PET, while for deep learning, these values were 0.96 (95% CI 0.94-0.97) and 0.97 (95% CI 0.96-0.99), respectively. Meta-regression identified heterogeneity arising from study quality stratification, algorithm types, and validation strategies.</p><p><strong>Conclusions: </strong>Both AI-assisted 18F-FDG PET and sMRI exhibit high diagnostic accuracy in AD, with 18F-FDG PET demonstrating superior overall diagnostic performance compared to sMRI.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"8 ","pages":"e76981"},"PeriodicalIF":4.8000,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Comparative Diagnostic Accuracy of AI-Assisted Fluorine-18 Fluorodeoxyglucose Positron Emission Tomography Versus Structural Magnetic Resonance Imaging in Alzheimer Disease: Systematic Review and Meta-Analysis.\",\"authors\":\"Bingbing Wang, Tailiang Zhao, Rongrong Ma, Xiaochuan Huo, Xiaoxiao Xiong, Minjie Wu, Yuran Wang, Liu Liu, Zhijiang Zhuang, Bin Wang, Jixin Shou\",\"doi\":\"10.2196/76981\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Neuroimaging is crucial in the diagnosis of Alzheimer disease (AD). In recent years, artificial intelligence (AI)-based neuroimaging technology has rapidly developed, providing new methods for accurate diagnosis of AD, but its performance differences still need to be systematically evaluated.</p><p><strong>Objective: </strong>This study aims to conduct a systematic review and meta-analysis comparing the diagnostic performance of AI-assisted fluorine-18 fluorodeoxyglucose positron emission tomography (18F-FDG PET) and structural magnetic resonance imaging (sMRI) for AD.</p><p><strong>Methods: </strong>Databases including Web of Science, PubMed, and Embase were searched from inception to January 2025 to identify original studies that developed or validated AI models for AD diagnosis using 18F-FDG PET or sMRI. Methodological quality was assessed using the TRIPOD-AI (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis-Artificial Intelligence) checklist. A bivariate mixed-effects model was employed to calculate pooled sensitivity, specificity, and summary receiver operating characteristic curve area (SROC-AUC).</p><p><strong>Results: </strong>A total of 38 studies were included, with 28 moderate-to-high-quality studies analyzed. Pooled SROC-AUC values were 0.94 (95% CI 0.92-0.96) for sMRI and 0.96 (95% CI 0.94-0.98) for 18F-FDG PET, demonstrating statistically significant intermodal differences (P=.02). Subgroup analyses revealed that for machine learning, pooled SROC-AUCs were 0.89 (95% CI 0.86-0.92) for sMRI and 0.95 (95% CI 0.92-0.96) for 18F-FDG PET, while for deep learning, these values were 0.96 (95% CI 0.94-0.97) and 0.97 (95% CI 0.96-0.99), respectively. Meta-regression identified heterogeneity arising from study quality stratification, algorithm types, and validation strategies.</p><p><strong>Conclusions: </strong>Both AI-assisted 18F-FDG PET and sMRI exhibit high diagnostic accuracy in AD, with 18F-FDG PET demonstrating superior overall diagnostic performance compared to sMRI.</p>\",\"PeriodicalId\":36245,\"journal\":{\"name\":\"JMIR Aging\",\"volume\":\"8 \",\"pages\":\"e76981\"},\"PeriodicalIF\":4.8000,\"publicationDate\":\"2025-10-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"JMIR Aging\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2196/76981\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"GERIATRICS & GERONTOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"JMIR Aging","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2196/76981","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GERIATRICS & GERONTOLOGY","Score":null,"Total":0}
引用次数: 0
摘要
背景：神经影像学在阿尔茨海默病（AD）的诊断中至关重要。近年来，基于人工智能（AI）的神经影像学技术发展迅速，为AD的准确诊断提供了新的方法，但其性能差异仍需系统评估。目的：本研究旨在对人工智能辅助的氟-18氟脱氧葡萄糖正电子发射断层扫描（18F-FDG PET）和结构磁共振成像（sMRI）对AD的诊断效果进行系统评价和荟萃分析。方法：检索Web of Science、PubMed和Embase等数据库，从创建到2025年1月，以确定使用18F-FDG PET或sMRI开发或验证AI模型用于AD诊断的原始研究。使用TRIPOD-AI（透明报告个体预后或诊断的多变量预测模型-人工智能）检查表评估方法学质量。采用双变量混合效应模型计算合并敏感性、特异性和总受试者工作特征曲线面积（SROC-AUC）。结果：共纳入38项研究，分析了28项中等至高质量的研究。sMRI的合并SROC-AUC值为0.94 (95% CI 0.92-0.96)， 18F-FDG PET的合并SROC-AUC值为0.96 (95% CI 0.94-0.98)，显示出具有统计学意义的多式联运差异（P= 0.02）。亚组分析显示，对于机器学习，sMRI的合并sroc - auc为0.89 (95% CI 0.86-0.92)， 18F-FDG PET的sroc - auc为0.95 (95% CI 0.92-0.96)，而对于深度学习，这些值分别为0.96 （95% CI 0.94-0.97）和0.97 （95% CI 0.96-0.99）。meta回归识别了研究质量分层、算法类型和验证策略引起的异质性。结论：人工智能辅助的18F-FDG PET和sMRI对AD的诊断准确率都很高，与sMRI相比，18F-FDG PET的总体诊断性能更好。
Comparative Diagnostic Accuracy of AI-Assisted Fluorine-18 Fluorodeoxyglucose Positron Emission Tomography Versus Structural Magnetic Resonance Imaging in Alzheimer Disease: Systematic Review and Meta-Analysis.
Background: Neuroimaging is crucial in the diagnosis of Alzheimer disease (AD). In recent years, artificial intelligence (AI)-based neuroimaging technology has rapidly developed, providing new methods for accurate diagnosis of AD, but its performance differences still need to be systematically evaluated.
Objective: This study aims to conduct a systematic review and meta-analysis comparing the diagnostic performance of AI-assisted fluorine-18 fluorodeoxyglucose positron emission tomography (18F-FDG PET) and structural magnetic resonance imaging (sMRI) for AD.
Methods: Databases including Web of Science, PubMed, and Embase were searched from inception to January 2025 to identify original studies that developed or validated AI models for AD diagnosis using 18F-FDG PET or sMRI. Methodological quality was assessed using the TRIPOD-AI (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis-Artificial Intelligence) checklist. A bivariate mixed-effects model was employed to calculate pooled sensitivity, specificity, and summary receiver operating characteristic curve area (SROC-AUC).
Results: A total of 38 studies were included, with 28 moderate-to-high-quality studies analyzed. Pooled SROC-AUC values were 0.94 (95% CI 0.92-0.96) for sMRI and 0.96 (95% CI 0.94-0.98) for 18F-FDG PET, demonstrating statistically significant intermodal differences (P=.02). Subgroup analyses revealed that for machine learning, pooled SROC-AUCs were 0.89 (95% CI 0.86-0.92) for sMRI and 0.95 (95% CI 0.92-0.96) for 18F-FDG PET, while for deep learning, these values were 0.96 (95% CI 0.94-0.97) and 0.97 (95% CI 0.96-0.99), respectively. Meta-regression identified heterogeneity arising from study quality stratification, algorithm types, and validation strategies.
Conclusions: Both AI-assisted 18F-FDG PET and sMRI exhibit high diagnostic accuracy in AD, with 18F-FDG PET demonstrating superior overall diagnostic performance compared to sMRI.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
