Center for Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, United States of America.
PLoS One. 2012;7(8):e43855. doi: 10.1371/journal.pone.0043855. Epub 2012 Aug 27.
The Autism Diagnostic Interview-Revised (ADI-R) is one of the most commonly used instruments for assisting in the behavioral diagnosis of autism. The exam consists of 93 questions that must be answered by a care provider within a focused session that often spans 2.5 hours. We used machine learning techniques to study the complete sets of answers to the ADI-R available at the Autism Genetic Research Exchange (AGRE) for 891 individuals diagnosed with autism and 75 individuals who did not meet the criteria for an autism diagnosis. Our analysis showed that 7 of the 93 items contained in the ADI-R were sufficient to classify autism with 99.9% statistical accuracy. We further tested the accuracy of this 7-question classifier against complete sets of answers from two independent sources, a collection of 1654 individuals with autism from the Simons Foundation and a collection of 322 individuals with autism from the Boston Autism Consortium. In both cases, our classifier performed with nearly 100% statistical accuracy, properly categorizing all but one of the individuals from these two resources who previously had been diagnosed with autism through the standard ADI-R. Our ability to measure specificity was limited by the small numbers of non-spectrum cases in the research data used, however, both real and simulated data demonstrated a range in specificity from 99% to 93.8%. With incidence rates rising, the capacity to diagnose autism quickly and effectively requires careful design of behavioral assessment methods. Ours is an initial attempt to retrospectively analyze large data repositories to derive an accurate, but significantly abbreviated approach that may be used for rapid detection and clinical prioritization of individuals likely to have an autism spectrum disorder. Such a tool could assist in streamlining the clinical diagnostic process overall, leading to faster screening and earlier treatment of individuals with autism.
自闭症诊断访谈修订版（ADI-R）是协助自闭症行为诊断的最常用工具之一。该测试包含 93 个问题，必须由护理提供者在一次集中的会议中回答，通常持续 2.5 小时。我们使用机器学习技术研究了自闭症基因研究交换（AGRE）中为 891 名被诊断为自闭症的个体和 75 名不符合自闭症诊断标准的个体提供的完整 ADI-R 答案集。我们的分析表明，ADI-R 中包含的 93 个项目中的 7 个足以以 99.9%的统计准确性对自闭症进行分类。我们进一步测试了这个 7 项问题分类器在两个独立来源的完整答案集中的准确性，一个是来自西蒙斯基金会的 1654 名自闭症个体的集合，另一个是来自波士顿自闭症联盟的 322 名自闭症个体的集合。在这两种情况下，我们的分类器的准确率都接近 100%，正确地对来自这两个资源的所有个体进行了分类，这些个体之前已经通过标准 ADI-R 被诊断为自闭症。然而，由于用于研究的数据中自闭症谱系外病例数量较少，我们衡量特异性的能力受到限制，但是真实和模拟数据都表明特异性的范围从 99%到 93.8%。随着发病率的上升，快速有效地诊断自闭症需要仔细设计行为评估方法。我们的研究是对大型数据存储库进行回顾性分析的初步尝试，旨在得出一种准确但显著简化的方法，该方法可用于快速检测和临床优先考虑可能患有自闭症谱系障碍的个体。这种工具可以帮助简化临床诊断过程，从而更快地对自闭症患者进行筛查和早期治疗。
