人工智能用于检测自闭症谱系障碍：系统综述与荟萃分析。
完整摘要 · 中文译文
背景：孤独症谱系障碍（ASD）是一种异质性神经发育状况，早期识别对于及时干预至关重要。传统诊断依赖于临床访谈、行为观察、照护者报告和标准化工具，这些方法耗时且依赖资源。人工智能（AI）为筛查和辅助诊断提供了机会，但各项研究在数据来源、模型类型和验证方法上存在差异，需要系统性评价。 方法：我们检索了PubMed、Embase、Cochrane Library、Web of Science和IEEE Xplore中关于基于AI的ASD检测研究。符合条件的研究需提供可在独立受试者或病例水平提取或可靠重建的ASD与非ASD诊断准确性数据。使用改良QUADAS-AI工具评估偏倚风险和适用性。采用双变量Reitsma随机效应模型估计合并灵敏度和特异度。HSROC AUC基于5，000次研究水平Bootstrap重抽样，采用偏差校正和加速（BCa）95%置信区间计算；当SROC拟合不稳定时不予报告。敏感性分析针对数据集重叠、模型选择和参考标准质量。 结果：在17，387条记录中，纳入26项研究。合并灵敏度为0.908（95% CI：0.861-0.940），合并特异度为0.868（95% CI：0.830-0.898），HSROC AUC为0.936（BCa 95% CI：0.860-0.973）。对21项研究进行的数据集独立分析得出较低的估计值（灵敏度0.870，特异度 ficity 0.841，AUC 0.900）。留一法结果总体稳定。漏斗图不对称性在主要分析中不显著，在各敏感性分析中方向和统计学显著性不一。 结论：基于人工智能的模型在ASD检测方面显示出相对较高的合并诊断性能，但显著的异质性、方法学和适用性方面的顾虑、有限的外部验证以及底层数据集潜在的non-independence限制了证据的确定性和可推广性。漏斗图分析未提供传统小样本效应或选择性报告的consistent证据。因此，人工智能应被视为辅助工具而非独立的诊断工具。在更广泛的临床实施之前，需要在具有代表性的人群中进行前瞻性多中心验证、参与者层面的评估、明确定义的参考诊断、预先设定的模型和操作阈值以及独立的评估数据集。
完整摘要 · 英文原文
BACKGROUND: Autism spectrum disorder (ASD) is a heterogeneous neurodevelopmental condition, and early identification is essential for timely intervention. Conventional diagnosis relies on clinical interviews, behavioral observations, caregiver reports, and standardized tools, which are time-consuming and resource-dependent. Artificial intelligence (AI) offers opportunities for screening and adjunctive diagnosis, but studies vary in data sources, model types, and validation methods, requiring systematic evaluation. METHODS: We searched PubMed, Embase, the Cochrane Library, Web of Science, and IEEE Xplore for studies of AI-based ASD detection. Eligible studies were required to provide ASD-versus-non-ASD diagnostic-accuracy data that could be extracted or reliably reconstructed at the independent participant or case level. Risk of bias and applicability were assessed using a modified QUADAS-AI tool. Pooled sensitivity and specificity were estimated with a bivariate Reitsma random-effects model. HSROC AUCs were calculated with bias-corrected and accelerated (BCa) 95% confidence intervals based on 5,000 study-level bootstrap replicates and were omitted when SROC fits were unstable. Sensitivity analyses addressed dataset overlap, model selection, and reference-standard quality. RESULTS: Of 17,387 records, 26 studies were included. Pooled sensitivity was 0.908 (95% CI: 0.861-0.940), pooled specificity was 0.868 (95% CI: 0.830-0.898), and the HSROC AUC was 0.936 (BCa 95% CI: 0.860-0.973). A dataset-independent analysis of 21 studies yielded lower estimates (sensitivity 0.870, specificity 0.841, AUC 0.900). Leave-one-out results were generally stable. Funnel-plot asymmetry was not significant in the primary analysis and varied in direction and statistical significance across sensitivity analyses. CONCLUSIONS: AI-based models showed relatively high pooled diagnostic performance for ASD detection, but substantial heterogeneity, methodological and applicability concerns, limited external validation, and potential non-independence of underlying datasets limit the certainty and generalizability of the evidence. Funnel-plot analyses did not provide consistent evidence of conventional small-study effects or selective reporting. AI should therefore be considered an adjunct rather than a standalone diagnostic tool. Prospective multicenter validation in representative populations, participant-level evaluation, clearly defined reference diagnoses, prespecified models and operating thresholds, and independent evaluation datasets are needed before broader clinical implementation.