Autism spectrum disorder (ASD) can be reliably diagnosed at 18 months, yet significant diagnostic delays persist in the United States. This double-blinded, multi-site, prospective, active comparator cohort study tested the accuracy of an artificial intelligence-based Software as a Medical Device designed to aid primary care healthcare providers (HCPs) in diagnosing ASD. The Device combines behavioral features from three distinct inputs (a caregiver questionnaire, analysis of two short home videos, and an HCP questionnaire) in a gradient boosted decision tree machine learning algorithm to produce either an ASD positive, ASD negative, or indeterminate output. This study compared Device outputs to diagnostic agreement by two or more independent specialists in a cohort of 18–72-month-olds with developmental delay concerns (425 study completers, 36% female, 29% ASD prevalence). Device output PPV for all study completers was 80.8% (95% confidence intervals (CI), 70.3%–88.8%) and NPV was 98.3% (90.6%–100%). For the 31.8% of participants who received a determinate output (ASD positive or negative) Device sensitivity was 98.4% (91.6%–100%) and specificity was 78.9% (67.6%–87.7%). The Device’s indeterminate output acts as a risk control measure when inputs are insufficiently granular to make a determinate recommendation with confidence. If this risk control measure were removed, the sensitivity for all study completers would fall to 51.6% (63/122) (95% CI 42.4%, 60.8%), and specificity would fall to 18.5% (56/303) (95% CI 14.3%, 23.3%). Among participants for whom the Device abstained from providing a result, specialists identified that 91% had one or more complex neurodevelopmental disorders. No significant differences in Device performance were found across participants’ sex, race/ethnicity, income, or education level. For nearly a third of this primary care sample, the Device enabled timely diagnostic evaluation with a high degree of accuracy. The Device shows promise to significantly increase the number of children able to be diagnosed with ASD in a primary care setting, potentially facilitating earlier intervention and more efficient use of specialist resources.

自闭症谱系障碍 (ASD) 可以在 18 个月时得到可靠诊断，但在美国仍然存在严重的诊断延误。这项双盲、多站点、前瞻性、主动比较队列研究测试了基于人工智能的软件作为医疗设备的准确性，旨在帮助初级保健医疗保健提供者 (HCP) 诊断 ASD。该设备在梯度提升决策树机器学习算法中结合来自三个不同输入（护理人员问卷、两个简短家庭视频的分析和 HCP 问卷）的行为特征，以产生 ASD 阳性、ASD 阴性或不确定输出。这项研究将设备输出与两名或更多独立专家的诊断协议进行了比较，这些专家在一组 18-72 个月大的有发育迟缓问题的儿童中（425 名研究完成者，36% 的女性，29% 的 ASD 患病率）。所有研究完成者的设备输出 PPV 为 80.8%（95% 置信区间 (CI)，70.3%–88.8%），NPV 为 98.3% (90.6%–100%)。对于收到确定输出（ASD 阳性或阴性）的 31.8% 的参与者，设备敏感性为 98.4% (91.6%–100%)，特异性为 78.9% (67.6%–87.7%)。当输入的粒度不足以自信地提出确定的建议时，设备的不确定输出可作为风险控制措施。如果删除此风险控制措施，则所有研究完成者的敏感性将降至 51.6% (63/122) (95% CI 42.4%, 60.8%)，特异性将降至 18.5% (56/303) (95%)置信区间 14.3%、23.3%）。在设备未提供结果的参与者中，专家确定 91% 的人患有一种或多种复杂的神经发育障碍。在参与者的性别、种族/民族、收入或教育水平方面，未发现设备性能存在显着差异。对于近三分之一的初级保健样本，该设备能够以高精度及时进行诊断评估。该设备显示出有望显着增加能够在初级保健机构中被诊断患有 ASD 的儿童数量，从而有可能促进早期干预和更有效地利用专家资源。