机器学习和深度学习在注意缺陷多动障碍诊断中的应用  

Application of machine learning and deep learning in the diagnosis of attention deficit hyperactivity disorder

作　　者：谭静 陈立[1] TAN Jing;CHEN Li(Growth,Development and Mental Health Center of Children and Adolescents,Children's Hospital of Chongqing Medical University,Chongqing Key Laboratory of Child Neurodevelopment and Cognitive Disorders,National Clinical Research Center for Child Health and Disorders,Ministry of Education Key Laboratory of Child Development and Disorders,Chongqing 401146,China)

机构地区：[1]重庆医科大学附属儿童医院儿童青少年生长发育与心理健康中心,儿童神经发育与认知障碍重庆市重点实验室,国家儿童健康与疾病临床医学研究中心,儿童发育疾病研究教育部重点实验室,重庆401146

出　　处：《中国儿童保健杂志》2025年第4期426-430,共5页Chinese Journal of Child Health Care

基　　金：国家重点研发计划项目生育健康及妇女儿童健康保障专项(2022YFC2705201)。

摘　　要：注意缺陷多动障碍(ADHD)是一种常见的儿童神经发育障碍性疾病,缺乏客观检测、检验指标且诊断困难。本文综述了机器学习和深度学习在ADHD诊断中的应用及辅助诊断价值。研究集中在几个关键领域:文本分析、电生理检测、神经影像学、行为数据分析、基因组学以及多组学研究。尽管机器学习和深度学习在ADHD诊断中展现了显著潜力,但仍面临数据质量、过度拟合、模型可解释性和伦理问题等挑战。未来的研究需进一步集中在改善算法性能、提高模型的解释能力、确保数据隐私和安全性领域,并在更多的临床研究中进一步验证。Attention deficit hyperactivity disorder(ADHD)is a common neurodevelopmental disorder in children,which lacks objective tests and is difficult to diagnose.This paper reviews the application of machine learning and deep learning in ADHD diagnosis and the value of assisted diagnosis.Research in this field focuses on several key areas:text analysis,electrophysiological testing,neuroimaging,behavioral data analysis,genomics,and multi-omics studies.Despite the significant potential demonstrated by machine learning and deep learning in diagnosing ADHD,challenges such as data quality,overfitting,model interpretability,and ethical issues remain.Future research needs to be focused in the areas of improving algorithm performance,enhancing model interpretability,ensuring data privacy and security,and validating on a broader range of clinical samples.

关 键 词：注意缺陷多动障碍 诊断 机器学习 深度学习 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] R749.94[自动化与计算机技术—控制科学与工程]