• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

机器学习在自闭症谱系分类中的应用

Machine Learning Differentiation of Autism Spectrum Sub-Classifications.

机构信息

Montera, Inc dba Forta, 548 Market St, PMB 89605, San Francisco, CA, USA.

出版信息

J Autism Dev Disord. 2024 Nov;54(11):4216-4231. doi: 10.1007/s10803-023-06121-4. Epub 2023 Sep 26.

DOI:10.1007/s10803-023-06121-4
PMID:37751097
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11461775/
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.

摘要

目的

自闭症谱系障碍具有表现为沟通、执行功能、日常生活等方面困难的特征。这些挑战可以通过早期识别得到缓解。然而，诊断标准已从 DSM-IV 改为 DSM-5，这使得自闭症谱系障碍的诊断变得复杂。我们评估了机器学习，以根据 DSM-IV 将个体分类为具有三种自闭症谱系障碍之一，或非谱系。

方法

我们采用机器学习分析了来自 38560 名个体的回顾性数据。输入包括临床、人口统计学和评估数据。

结果

该算法的 AUROCs 范围为 0.863 至 0.980。该模型正确分类了 80.5%的个体；该数据集的 12.6%的个体被错误分类为另一种自闭症谱系障碍。

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。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/45cd/11461775/00ed2a8f87c0/10803_2023_6121_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/45cd/11461775/f862dbb644fb/10803_2023_6121_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/45cd/11461775/bcf3179c25fc/10803_2023_6121_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/45cd/11461775/9197a3cb4355/10803_2023_6121_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/45cd/11461775/708bdffe1439/10803_2023_6121_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/45cd/11461775/00ed2a8f87c0/10803_2023_6121_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/45cd/11461775/f862dbb644fb/10803_2023_6121_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/45cd/11461775/bcf3179c25fc/10803_2023_6121_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/45cd/11461775/9197a3cb4355/10803_2023_6121_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/45cd/11461775/708bdffe1439/10803_2023_6121_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/45cd/11461775/00ed2a8f87c0/10803_2023_6121_Fig5_HTML.jpg

相似文献

1
Machine Learning Differentiation of Autism Spectrum Sub-Classifications.机器学习在自闭症谱系分类中的应用
J Autism Dev Disord. 2024 Nov;54(11):4216-4231. doi: 10.1007/s10803-023-06121-4. Epub 2023 Sep 26.
2
Comparison of DSM-IV-TR and DSM-5 Criteria in Diagnosing Autism Spectrum Disorders in Singapore.新加坡诊断自闭症谱系障碍的 DSM-IV-TR 与 DSM-5 标准比较。
J Autism Dev Disord. 2018 Oct;48(10):3273-3281. doi: 10.1007/s10803-018-3594-x.
3
Autism Spectrum Disorder in the DSM-5: Diagnostic Sensitivity and Specificity in Early Childhood.《精神疾病诊断与统计手册》第五版中的自闭症谱系障碍：幼儿期的诊断敏感性和特异性
J Autism Dev Disord. 2016 Jun;46(6):2054-2063. doi: 10.1007/s10803-016-2734-4.
4
A Protocol for the Diagnosis of Autism Spectrum Disorder Structured in Machine Learning and Verbal Decision Analysis.自闭症谱系障碍的机器学习与言语决策分析诊断协议。
Comput Math Methods Med. 2021 Mar 30;2021:1628959. doi: 10.1155/2021/1628959. eCollection 2021.
5
Rates of Autism Spectrum Disorder Diagnosis Under the DSM-5 Criteria Compared to DSM-IV-TR Criteria in a Hospital-Based Clinic.在一家医院诊所中，与《精神疾病诊断与统计手册》第四版修订版（DSM-IV-TR）标准相比，依据《精神疾病诊断与统计手册》第五版（DSM-5）标准诊断自闭症谱系障碍的比率。
Pediatr Neurol. 2016 Apr;57:34-8. doi: 10.1016/j.pediatrneurol.2016.01.012. Epub 2016 Jan 18.
6
Concordance of DSM-5 and DSM-IV-TR classifications for autism spectrum disorder.《精神疾病诊断与统计手册》第五版（DSM-5）与《精神疾病诊断与统计手册》第四版修订版（DSM-IV-TR）对自闭症谱系障碍分类的一致性。
Pediatr Int. 2015 Dec;57(6):1097-100. doi: 10.1111/ped.12704. Epub 2015 Sep 10.
7
Early identification of autism spectrum disorder based on machine learning with eye-tracking data.基于眼动追踪数据的机器学习对自闭症谱系障碍的早期识别。
J Affect Disord. 2024 Aug 1;358:326-334. doi: 10.1016/j.jad.2024.04.049. Epub 2024 Apr 12.
8
Machine learning based on eye-tracking data to identify Autism Spectrum Disorder: A systematic review and meta-analysis.基于眼动追踪数据的机器学习用于识别自闭症谱系障碍：一项系统综述和荟萃分析。
J Biomed Inform. 2023 Jan;137:104254. doi: 10.1016/j.jbi.2022.104254. Epub 2022 Dec 9.
9
Identifying children with autism spectrum disorder based on their face processing abnormality: A machine learning framework.基于面部处理异常识别自闭症谱系障碍儿童：一个机器学习框架。
Autism Res. 2016 Aug;9(8):888-98. doi: 10.1002/aur.1615. Epub 2016 Apr 1.
10
Overall prognosis of preschool autism spectrum disorder diagnoses.学龄前自闭症谱系障碍诊断的总体预后。
Cochrane Database Syst Rev. 2022 Sep 28;9(9):CD012749. doi: 10.1002/14651858.CD012749.pub2.

引用本文的文献

1
Machine learning to evaluate the effects of non-clinical social determinant features in predicting colorectal Cancer mortality in a medically underserved Appalachian population.机器学习用于评估非临床社会决定因素特征在预测医疗服务不足的阿巴拉契亚人群结直肠癌死亡率中的作用。
Sci Rep. 2025 Jul 16;15(1):25781. doi: 10.1038/s41598-025-11074-y.
2
Parent-Led Applied Behavior Analysis to Impact Clinical Outcomes for Individuals on the Autism Spectrum: Retrospective Chart Review.家长主导的应用行为分析对自闭症谱系个体临床结果的影响：回顾性病历审查
JMIR Pediatr Parent. 2024 Oct 30;7:e62878. doi: 10.2196/62878.
3
Family-Centric Applied Behavior Analysis Promotes Sustained Treatment Utilization and Attainment of Patient Goals.

本文引用的文献

1
Prevalence and Characteristics of Autism Spectrum Disorder Among Children Aged 8 Years - Autism and Developmental Disabilities Monitoring Network, 11 Sites, United States, 2020.2020 年，美国 11 个监测点自闭症和发育障碍监测网络 8 岁儿童自闭症谱系障碍的流行率和特征。
MMWR Surveill Summ. 2023 Mar 24;72(2):1-14. doi: 10.15585/mmwr.ss7202a1.
2
Machine learning determination of applied behavioral analysis treatment plan type.应用行为分析治疗计划类型的机器学习判定
Brain Inform. 2023 Mar 2;10(1):7. doi: 10.1186/s40708-023-00186-8.
3
Machine learning early prediction of respiratory syncytial virus in pediatric hospitalized patients.
以家庭为中心的应用行为分析促进持续的治疗利用和患者目标的实现。
Cureus. 2024 Jun 14;16(6):e62377. doi: 10.7759/cureus.62377. eCollection 2024 Jun.
4
Machine Learning Approach with Harmonized Multinational Datasets for Enhanced Prediction of Hypothyroidism in Patients with Type 2 Diabetes.利用多民族统一数据集的机器学习方法增强对2型糖尿病患者甲状腺功能减退症的预测
Diagnostics (Basel). 2024 May 31;14(11):1152. doi: 10.3390/diagnostics14111152.
5
Machine Learning Approach for Improved Longitudinal Prediction of Progression from Mild Cognitive Impairment to Alzheimer's Disease.用于改善从轻度认知障碍到阿尔茨海默病进展的纵向预测的机器学习方法
Diagnostics (Basel). 2023 Dec 20;14(1):13. doi: 10.3390/diagnostics14010013.
儿科住院患者呼吸道合胞病毒的机器学习早期预测
Front Pediatr. 2022 Aug 4;10:886212. doi: 10.3389/fped.2022.886212. eCollection 2022.
4
Early prediction of prostate cancer risk in younger men using polygenic risk scores and electronic health records.利用多基因风险评分和电子健康记录提前预测年轻男性的前列腺癌风险。
Cancer Med. 2023 Jan;12(1):379-386. doi: 10.1002/cam4.4934. Epub 2022 Jun 25.
5
Multitask Learning With Recurrent Neural Networks for Acute Respiratory Distress Syndrome Prediction Using Only Electronic Health Record Data: Model Development and Validation Study.仅使用电子健康记录数据的急性呼吸窘迫综合征预测的递归神经网络多任务学习：模型开发与验证研究
JMIR Med Inform. 2022 Jun 15;10(6):e36202. doi: 10.2196/36202.
6
Innovations in Genomics and Big Data Analytics for Personalized Medicine and Health Care: A Review.基因组学和大数据分析在个性化医疗和医疗保健中的创新：综述。
Int J Mol Sci. 2022 Apr 22;23(9):4645. doi: 10.3390/ijms23094645.
7
Contributing factors to healthcare costs in individuals with autism spectrum disorder: a systematic review.自闭症谱系障碍患者医疗费用的影响因素：系统评价。
BMC Health Serv Res. 2022 May 6;22(1):604. doi: 10.1186/s12913-022-07932-4.
8
Evaluation of an artificial intelligence-based medical device for diagnosis of autism spectrum disorder.一种基于人工智能的用于诊断自闭症谱系障碍的医疗设备的评估。
NPJ Digit Med. 2022 May 5;5(1):57. doi: 10.1038/s41746-022-00598-6.
9
rs-fMRI and machine learning for ASD diagnosis: a systematic review and meta-analysis.rs-fMRI 和机器学习在 ASD 诊断中的应用：系统评价和荟萃分析。
Sci Rep. 2022 Apr 11;12(1):6030. doi: 10.1038/s41598-022-09821-6.
10
Predicting Falls in Long-term Care Facilities: Machine Learning Study.预测长期护理机构中的跌倒：机器学习研究。
JMIR Aging. 2022 Apr 1;5(2):e35373. doi: 10.2196/35373.