{"title":"Concise multi-class anxiety disorder risk assessment: A novel advanced machine learning approach","authors":"Haochong Yang , Yuan Hong Sun , Kang Lee","doi":"10.1016/j.janxdis.2025.103018","DOIUrl":null,"url":null,"abstract":"<div><div>Rapidly assessing anxiety disorder risk is crucial for effective mental health screen and intervention. However, traditional survey tools such as DASS-42 are time-consuming in responding and scoring. We used a novel advanced machine learning approach to create a concise anxiety disorder scale based on DASS-42. By applying advanced ML techniques and feature selection, we created a concise version of the anxiety risk scale while maintaining high validity. The resulting model requires fewer questions to predict anxiety risk levels effectively. This optimized scale was implemented in an online tool for quick self-screening and clinical use. This innovation holds significant societal implications, offering scalable, efficient, and accurate methods that facilitate faster and earlier anxiety disorder detection and intervention, especially among underserved and high-risk populations. The study highlights how machine learning can create practical, accessible mental health assessment tools, contributing to improved well-being outcomes.</div></div>","PeriodicalId":48390,"journal":{"name":"Journal of Anxiety Disorders","volume":"112 ","pages":"Article 103018"},"PeriodicalIF":4.8000,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Anxiety Disorders","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0887618525000544","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PSYCHIATRY","Score":null,"Total":0}
引用次数: 0
Abstract
Rapidly assessing anxiety disorder risk is crucial for effective mental health screen and intervention. However, traditional survey tools such as DASS-42 are time-consuming in responding and scoring. We used a novel advanced machine learning approach to create a concise anxiety disorder scale based on DASS-42. By applying advanced ML techniques and feature selection, we created a concise version of the anxiety risk scale while maintaining high validity. The resulting model requires fewer questions to predict anxiety risk levels effectively. This optimized scale was implemented in an online tool for quick self-screening and clinical use. This innovation holds significant societal implications, offering scalable, efficient, and accurate methods that facilitate faster and earlier anxiety disorder detection and intervention, especially among underserved and high-risk populations. The study highlights how machine learning can create practical, accessible mental health assessment tools, contributing to improved well-being outcomes.
期刊介绍:
The Journal of Anxiety Disorders is an interdisciplinary journal that publishes research papers on all aspects of anxiety disorders for individuals of all age groups, including children, adolescents, adults, and the elderly. Manuscripts that focus on disorders previously classified as anxiety disorders such as obsessive-compulsive disorder and posttraumatic stress disorder, as well as the new category of illness anxiety disorder, are also within the scope of the journal. The research areas of focus include traditional, behavioral, cognitive, and biological assessment; diagnosis and classification; psychosocial and psychopharmacological treatment; genetics; epidemiology; and prevention. The journal welcomes theoretical and review articles that significantly contribute to current knowledge in the field. It is abstracted and indexed in various databases such as Elsevier, BIOBASE, PubMed/Medline, PsycINFO, BIOSIS Citation Index, BRS Data, Current Contents - Social & Behavioral Sciences, Pascal Francis, Scopus, and Google Scholar.