Purpose

Autism Spectrum Disorder (ASD) is diagnosed through observation or interview assessments, which is time-consuming, subjective, and with questionable validity and reliability. Thus, we aimed to evaluate the role of machine learning (ML) with neuroimaging data to provide a reliable classification of ASD.

Methods

A systematic search of PubMed, Scopus, and Embase was conducted to identify relevant publications. Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) was used to assess the studies’ quality. A bivariate random-effects model meta-analysis was employed to evaluate the pooled sensitivity, the pooled specificity, and the diagnostic performance through the hierarchical summary receiver operating characteristic (HSROC) curve of ML with neuroimaging data in classifying ASD. Meta-regression was also performed.

Results

Forty-four studies (5697 ASD and 6013 typically developing individuals [TD] in total) were included in the quantitative analysis. The pooled sensitivity for differentiating ASD from TD individuals was 86.25 95% confidence interval [CI] (81.24, 90.08), while the pooled specificity was 83.31 95% CI (78.12, 87.48) with a combined area under the HSROC (AUC) of 0.889. Higgins I² (> 90%) and Cochran’s Q (p < 0.0001) suggest a high degree of heterogeneity. In the bivariate model meta-regression, a higher pooled specificity was observed in studies not using a brain atlas (90.91 95% CI [80.67, 96.00], p = 0.032). In addition, a greater pooled sensitivity was seen in studies recruiting both males and females (89.04 95% CI [83.84, 92.72], p = 0.021), and combining imaging modalities (94.12 95% [85.43, 97.76], p = 0.036).

Conclusion

ML with neuroimaging data is an exciting prospect in detecting individuals with ASD but further studies are required to improve its reliability for usage in clinical practice.

中文翻译：

---

使用神经影像数据进行机器学习以识别自闭症谱系障碍：系统评价和荟萃分析

目的

自闭症谱系障碍 (ASD) 是通过观察或访谈评估来诊断的，这种评估耗时、主观且有效性和可靠性值得怀疑。因此，我们旨在评估机器学习 (ML) 与神经影像数据的作用，以提供可靠的 ASD 分类。

方法

对 PubMed、Scopus 和 Embase 进行了系统搜索，以确定相关出版物。诊断准确性研究的质量评估-2 (QUADAS-2) 用于评估研究的质量。采用双变量随机效应模型荟萃分析，通过 ML 的分层汇总接收者操作特征 (HSROC) 曲线和神经影像学数据对 ASD 进行分类，评估汇总敏感性、汇总特异性和诊断性能。还进行了元回归。

结果

定量分析包括了 44 项研究（总共 5697 名 ASD 和 6013 名典型发展个体 [TD]）。区分 ASD 与 TD 个体的汇总敏感性为 86.25 95% 置信区间 [CI] (81.24, 90.08)，而汇总特异性为 83.31 95% CI (78.12, 87.48 )，HSROC 下的合并面积(AUC9 )为 0.88 . Higgins I ² (> 90%) 和 Cochran's Q (p < 0.0001) 表明高度异质性。在双变量模型元回归中，在不使用脑图谱的研究中观察到更高的汇总特异性（90.91 95% CI [80.67, 96.00]，p =  0.032）。此外，在招募男性和女性的研究中发现了更高的汇总敏感性（89.04 95% CI [83.84, 92.72 ]， p = 0.021 ) 和组合成像方式 (94.12 95% [85.43, 97.76], p =  0.036 )。

结论

具有神经影像学数据的机器学习在检测 ASD 个体方面具有令人兴奋的前景，但需要进一步研究以提高其在临床实践中使用的可靠性。