Beijing University of Chinese Medicine, Beijing, 100029, China.
Applied Health Research Centre (AHRC), Li Ka Shing Knowledge Institute, St Michael's Hospital, University of Toronto, Toronto, M5B 1W8, Canada.
Osteoporos Int. 2021 Jul;32(7):1279-1286. doi: 10.1007/s00198-021-05887-6. Epub 2021 Feb 27.
Artificial intelligence (AI) is a potentially reliable assistant in the diagnosis of osteoporosis. This meta-analysis aims to assess the diagnostic accuracy of the AI-based systems using medical images. We searched PubMed and Web of Science from inception to June 15, 2020, for eligible articles that applied AI approaches to diagnosing osteoporosis using medical images. Quality and bias of the included studies were evaluated with the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. The main outcome was the sensitivity and specificity of the performance of the AI-based systems. The data analysis utilized the R Foundation packages of "meta" for univariate analysis and Stata for bivariate analysis. Random effects model was utilized. Seven studies with 3186 patients were included in the meta-analysis. The overall risk of bias of the included studies was assessed as low. The pooled sensitivity was 0.96 (95% CI 0.93-1.00), and the pooled specificity was 0.95 (95% CI 0.91-0.99). However, high heterogeneity was found in this meta-analysis. The results supported that the AI-based systems had good accuracy in diagnosing osteoporosis. However, the high risk of bias in patient selection and high heterogeneity in the meta-analysis made the conclusion less convincing. The application of AI-based systems in osteoporosis diagnosis needs to be further confirmed by more prospective studies in multi-centers including more random samples from complete patient types.
人工智能（AI）在骨质疏松症的诊断中可能是一个可靠的助手。本荟萃分析旨在评估使用医学图像的 AI 系统的诊断准确性。我们从建库到 2020 年 6 月 15 日在 PubMed 和 Web of Science 上搜索了符合条件的文章，这些文章应用 AI 方法使用医学图像诊断骨质疏松症。使用 QUADAS-2 工具评估纳入研究的质量和偏倚。主要结果是 AI 系统的性能的敏感性和特异性。数据分析利用 R 基金会的“meta”包进行单变量分析，利用 Stata 进行双变量分析。使用随机效应模型。荟萃分析纳入了 7 项研究共 3186 名患者。纳入研究的总体偏倚风险评估为低。汇总敏感性为 0.96（95%CI 0.93-1.00），汇总特异性为 0.95（95%CI 0.91-0.99）。然而，本荟萃分析存在高度异质性。结果支持 AI 系统在诊断骨质疏松症方面具有良好的准确性。然而，患者选择偏倚风险高和荟萃分析中的高度异质性使得结论不太有说服力。基于 AI 的系统在骨质疏松症诊断中的应用需要更多多中心的前瞻性研究进一步证实，这些研究应包括来自完整患者类型的更多随机样本。
