Machine Learning Differentiation of Autism Spectrum Sub-Classifications.

IF 3.2 2区心理学 Q1 PSYCHOLOGY, DEVELOPMENTAL Journal of Autism and Developmental Disorders Pub Date : 2024-11-01 Epub Date: 2023-09-26 DOI:10.1007/s10803-023-06121-4

R Thapa, A Garikipati, M Ciobanu, N P Singh, E Browning, J DeCurzio, G Barnes, F A Dinenno, Q Mao, R Das

{"title":"Machine Learning Differentiation of Autism Spectrum Sub-Classifications.","authors":"R Thapa, A Garikipati, M Ciobanu, N P Singh, E Browning, J DeCurzio, G Barnes, F A Dinenno, Q Mao, R Das","doi":"10.1007/s10803-023-06121-4","DOIUrl":null,"url":null,"abstract":"Purpose: Disorders on the autism spectrum have characteristics that can manifest as difficulties with communication, executive functioning, daily living, and more. These challenges can be mitigated with early identification. However, diagnostic criteria has changed from DSM-IV to DSM-5, which can make diagnosing a disorder on the autism spectrum complex. We evaluated machine learning to classify individuals as having one of three disorders of the autism spectrum under DSM-IV, or as non-spectrum.Methods: We employed machine learning to analyze retrospective data from 38,560 individuals. Inputs encompassed clinical, demographic, and assessment data.Results: The algorithm achieved AUROCs ranging from 0.863 to 0.980. The model correctly classified 80.5% individuals; 12.6% of individuals from this dataset were misclassified with another disorder on the autism spectrum.Conclusion: Machine learning can classify individuals as having a disorder on the autism spectrum or as non-spectrum using minimal data inputs.","PeriodicalId":15148,"journal":{"name":"Journal of Autism and Developmental Disorders","volume":" ","pages":"4216-4231"},"PeriodicalIF":3.2000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11461775/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Autism and Developmental Disorders","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1007/s10803-023-06121-4","RegionNum":2,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/9/26 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"PSYCHOLOGY, DEVELOPMENTAL","Score":null,"Total":0}

引用次数: 0

Abstract

Purpose: Disorders on the autism spectrum have characteristics that can manifest as difficulties with communication, executive functioning, daily living, and more. These challenges can be mitigated with early identification. However, diagnostic criteria has changed from DSM-IV to DSM-5, which can make diagnosing a disorder on the autism spectrum complex. We evaluated machine learning to classify individuals as having one of three disorders of the autism spectrum under DSM-IV, or as non-spectrum.

Methods: We employed machine learning to analyze retrospective data from 38,560 individuals. Inputs encompassed clinical, demographic, and assessment data.

Results: The algorithm achieved AUROCs ranging from 0.863 to 0.980. The model correctly classified 80.5% individuals; 12.6% of individuals from this dataset were misclassified with another disorder on the autism spectrum.

Conclusion: Machine learning can classify individuals as having a disorder on the autism spectrum or as non-spectrum using minimal data inputs.

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

自闭症谱系亚分类的机器学习区分。

目的：自闭症谱系障碍的特征可以表现为沟通、执行功能、日常生活等方面的困难。这些挑战可以通过早期识别来缓解。然而，诊断标准已经从DSM-IV变为DSM-5，这可能会使自闭症谱系障碍的诊断变得复杂。我们评估了机器学习，将个体分类为DSM-IV下自闭症谱系的三种障碍之一，或非谱系。方法：我们采用机器学习方法对38560名个体的回顾性数据进行分析。输入包括临床、人口统计和评估数据。结果：该算法的AUROC在0.863到0.980之间。该模型对80.5%的个体进行了正确分类；该数据集中12.6%的个体被错误分类为自闭症谱系中的另一种障碍。结论：机器学习可以使用最少的数据输入将个体分类为自闭症谱系障碍或非谱系障碍。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Journal of Autism and Developmental Disorders PSYCHOLOGY, DEVELOPMENTAL-

CiteScore

8.00

自引率

10.30%

发文量

433

期刊介绍： The Journal of Autism and Developmental Disorders seeks to advance theoretical and applied research as well as examine and evaluate clinical diagnoses and treatments for autism and related disabilities. JADD encourages research submissions on the causes of ASDs and related disorders, including genetic, immunological, and environmental factors; diagnosis and assessment tools (e.g., for early detection as well as behavioral and communications characteristics); and prevention and treatment options. Sample topics include: Social responsiveness in young children with autism Advances in diagnosing and reporting autism Omega-3 fatty acids to treat autism symptoms Parental and child adherence to behavioral and medical treatments for autism Increasing independent task completion by students with autism spectrum disorder Does laughter differ in children with autism? Predicting ASD diagnosis and social impairment in younger siblings of children with autism The effects of psychotropic and nonpsychotropic medication with adolescents and adults with ASD Increasing independence for individuals with ASDs Group interventions to promote social skills in school-aged children with ASDs Standard diagnostic measures for ASDs Substance abuse in adults with autism Differentiating between ADHD and autism symptoms Social competence and social skills training and interventions for children with ASDs Therapeutic horseback riding and social functioning in children with autism Authors and readers of the Journal of Autism and Developmental Disorders include sch olars, researchers, professionals, policy makers, and graduate students from a broad range of cross-disciplines, including developmental, clinical child, and school psychology; pediatrics; psychiatry; education; social work and counseling; speech, communication, and physical therapy; medicine and neuroscience; and public health.