Carolina Institute for Developmental Disabilities, University of North Carolina at Chapel Hill; The National Institute of Mental Health and Neurosciences, Bangalore, India.
Carolina Institute for Developmental Disabilities, University of North Carolina at Chapel Hill.
J Am Acad Child Adolesc Psychiatry. 2021 Aug;60(8):968-977. doi: 10.1016/j.jaac.2020.10.015. Epub 2020 Nov 5.
This study aimed to develop a classifier for infants at 12 months of age based on a parent-report measure (the First Year Inventory 2.0 [FYI]), for the following reasons: (1) to classify infants at elevated risk, above and beyond that attributable to familial risk status for ASD; and (2) to serve as a starting point to refine an approach for risk estimation in population samples.
A total of 54 high-familial risk (HR) infants later diagnosed with ASD (HR-ASD), 183 HR infants not diagnosed with ASD at 24 months of age (HR-Neg), and 72 low-risk controls participated in the study. All infants contributed FYI data at 12 months of age and had a diagnostic assessment for ASD at age 24 months. A data-driven, cross-validated analytic approach was used to develop a classifier to determine screening accuracy (eg, sensitivity) of the FYI to classify HR-ASD and HR-Neg.
The newly developed FYI classifier had an estimated sensitivity of 0.71 (95% CI: 0.50, 0.91) and specificity of 0.72 (95% CI: 0.49, 0.91).
This classifier demonstrates the potential to improve current screening for ASD risk at 12 months of age in infants already at elevated familial risk for ASD, increasing opportunities for detection of autism risk in infancy. Findings from this study highlight the utility of combining parent-report measures with machine learning approaches.
本研究旨在基于家长报告量表（第一年末调查 2.0[FYI]）为 12 月龄婴儿开发一种分类器，原因如下：（1）对处于自闭症谱系障碍（ASD）高风险的婴儿进行分类，超出了家族风险状况归因于的风险；（2）作为一种方法，用于细化在人群样本中进行风险估计的方法。
共有 54 名高家族风险（HR）的婴儿后来被诊断出患有 ASD（HR-ASD），183 名 HR 婴儿在 24 个月时未被诊断出患有 ASD（HR-Neg），72 名低风险对照者参加了研究。所有婴儿在 12 个月时都提供了 FYI 数据，在 24 个月时进行了 ASD 诊断评估。采用数据驱动的交叉验证分析方法开发了一种分类器，以确定 FYI 对 HR-ASD 和 HR-Neg 进行分类的筛查准确性（例如，敏感性）。
新开发的 FYI 分类器的估计敏感性为 0.71（95%CI：0.50，0.91），特异性为 0.72（95%CI：0.49，0.91）。
该分类器有可能提高目前对 12 月龄时已经处于 ASD 高家族风险的婴儿进行 ASD 风险的筛查，增加了在婴儿期发现自闭症风险的机会。这项研究的结果突出了结合家长报告测量和机器学习方法的实用性。
