机器学习和深度学习在注意缺陷多动障碍诊断中的应用

doi:10.11852/zgetbjzz2024-0510

中国儿童保健杂志 ›› 2025, Vol. 33 ›› Issue (4): 426-430.DOI: 10.11852/zgetbjzz2024-0510

机器学习和深度学习在注意缺陷多动障碍诊断中的应用

谭静, 陈立

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

收稿日期:2024-05-07 修回日期:2024-11-06 发布日期:2025-04-10 出版日期:2025-04-10
通讯作者: 陈立,E-mail:chenli@cqmu.edu.cn
作者简介:谭静(1998—),女,硕士研究生,主要研究方向为注意缺陷多动障碍。
基金资助:
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)

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

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

Received:2024-05-07 Revised:2024-11-06 Online:2025-04-10 Published:2025-04-10
Contact: CHEN Li, E-mail: chenli@cqmu.edu.cn

摘要/Abstract

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。

关键词: 注意缺陷多动障碍, 诊断, 机器学习, 深度学习

Abstract: 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.

Key words: attention deficit hyperactivity disorder, diagnosis, machine learning, deep learning

中图分类号:

TP18
R749.94

谭静, 陈立. 机器学习和深度学习在注意缺陷多动障碍诊断中的应用[J]. 中国儿童保健杂志, 2025, 33(4): 426-430.

TAN Jing, CHEN Li. Application of machine learning and deep learning in the diagnosis of attention deficit hyperactivity disorder[J]. Chinese Journal of Child Health Care, 2025, 33(4): 426-430.

参考文献

[1] Wolraich ML, Hagan JF, Allan C, et al. Clinical practice guideline for the diagnosis, evaluation, and treatment of attention-deficit/hyperactivity disorder in children and adolescents[J]. Pediatrics, 2019, 144(4): e20192528.
[2] Liu A, Xu Y, Yan Q, et al. The prevalence of attention deficit/hyperactivity disorder among Chinese children and adolescents[J]. Sci Rep, 2018, 8(1): 11169.
[3] Faraone SV, Biederman J, Mick E. The age-dependent decline of attention deficit hyperactivity disorder: A Meta-analysis of follow-up studies[J]. Psychol Med, 2006, 36(2): 159-165.
[4] Faraone SV, Bellgrove MA, Brikell I, et al. Attention-deficit/hyperactivity disorder[J]. Nat Rev Dis Primers, 2024, 10(1): 11.
[5] Halperin JM, Bédard AC, Curchack-Lichtin JT. Preventive interventions for ADHD: A neurodevelopmental perspective[J]. Neurotherapeutics, 2012, 9(3): 531-41.
[6] Loh HW, Ooi CP, Barua PD, et al. Automated detection of ADHD: Current trends and future perspective[J]. Comput Biol Med, 2022, 146: 105525.
[7] Mikolas P, Vahid A, Bernardoni F, et al. Training a machine learning classifier to identify ADHD based on real-world clinical data from medical records[J]. Sci Rep, 2022, 12(1): 12934.
[8] Emser TS, Johnston BA, Steele JD, et al. Assessing ADHD symptoms in children and adults: Evaluating the role of objective measures[J]. Behav Brain Funct, 2018, 14(1): 11.
[9] Lin IC, Chang SC, Huang YJ, et al. Distinguishing different types of attention deficit hyperactivity disorder in children using artificial neural network with clinical intelligent test[J]. Front Psychol, 2022, 13: 1067771.
[10] Zhang-James Y, Chen Q, Kuja-Halkola R, et al. Machine-learning prediction of comorbid substance use disorders in ADHD youth using Swedish registry data[J]. J Child Psychol Psychiatry, 2020, 61(12): 1370-1379.
[11] Phyo Wai AA, Dou M, Guan C. Generalizability of EEG-based mental attention modeling with multiple cognitive tasks[J]. Annu Int Conf IEEE Eng Med Biol Soc, 2020, 2020: 2959-2962.
[12] Öztoprak H, Toycan M, Alp YK, et al. Machine-based classification of ADHD and nonADHD participants using time/frequency features of event-related neuroelectric activity[J]. Clin Neurophysiol, 2017, 128(12): 2400-2410.
[13] Moghaddari M, Lighvan MZ, Danishvar S. Diagnose ADHD disorder in children using convolutional neural network based on continuous mental task EEG[J]. Comput Methods Programs Biomed, 2020, 197: 105738.
[14] Zhang Y, Cai H, Nie L, et al. An end-to-end 3D convolutional neural network for decoding attentive mental state[J]. Neural Netw, 2021, 144: 129-137.
[15] Loh HW, Ooi CP, Oh SL, et al. Deep neural network technique for automated detection of ADHD and CD using ECG signal[J]. Comput Methods Programs Biomed, 2023, 241: 107775.
[16] Pereira-Sanchez V, Castellanos FX. Neuroimaging in attention-deficit/hyperactivity disorder[J]. Curr Opin Psychiatry, 2021, 34(2): 105-111.
[17] Zhang-James Y, Razavi AS, Hoogman M, et al. Machine learning and MRI-based diagnostic models for ADHD: Are we there yet?[J]. J Atten Disord, 2023, 27(4): 335-353.
[18] Uyulan C, Erguzel TT, Turk O, et al. A class activation map-based interpretable transfer learning model for automated detection of ADHD from fMRI data[J]. Clin EEG Neurosci, 2023, 54(2): 151-159.
[19] Wang Z, Zhu Y, Shi H, et al. A 3D multiscale view convolutional neural network with attention for mental disease diagnosis on MRI images[J]. Math Biosci Eng, 2021, 18(5): 6978-6994.
[20] Yang CM, Shin J, Kim JI, et al. Classifying children with ADHD based on prefrontal functional near-infrared spectroscopy using machine learning[J]. Clin Psychopharmacol Neurosci, 2023, 21(4): 693-700.
[21] Muñoz-Organero M, Powell L, Heller B, et al. Automatic extraction and detection of characteristic movement patterns in children with ADHD based on a convolutional neural network (CNN) and acceleration images[J]. Sensors (Basel), 2018, 18(11): 3924.
[22] Amado-Caballero P, Casaseca-De-La-Higuera P, Alberola-Lopez S, et al. Objective ADHD diagnosis using convolutional neural networks over daily-life activity records[J]. IEEE J Biomed Health Inform, 2020, 24(9): 2690-2700.
[23] Chen X, Wang S, Yang X, et al. Utilizing artificial intelligence-based eye tracking technology for screening ADHD symptoms in children[J]. Front Psychiatry, 2023, 14: 1260031.
[24] Wiguna T, Wigantara NA, Ismail RI, et al. A four-step method for the development of an ADHD-VR digital game diagnostic tool prototype for children using a DL model[J]. Front Psychiatry, 2020, 11: 829.
[25] Liu Y, Qu HQ, Chang X, et al. Deep learning prediction of attention-deficit hyperactivity disorder in African Americans by copy number variation[J]. Exp Biol Med (Maywood), 2021, 246(21): 2317-2323.
[26] Liu L, Feng X, Li H, et al. Deep learning model reveals potential risk genes for ADHD, especially Ephrin receptor gene EPHA5[J]. Brief Bioinform, 2021, 22(6): bbab207.
[27] Vasilchenko KF, Chumakov EM. Current status, challenges and future prospects in computational psychiatry: A narrative review[J]. Consort Psychiatr, 2023, 4(3): 33-42.
[28] Yoo JH, Kim JI, Kim BN, et al. Exploring characteristic features of attention-deficit/hyperactivity disorder: Findings from multi-modal MRI and candidate genetic data[J]. Brain Imaging Behav, 2020, 14(6): 2132-2147.
[29] Kautzky A, Vanicek T, Philippe C, et al. Machine learning classification of ADHD and HC by multimodal serotonergic data[J]. Transl Psychiatry, 2020, 10(1): 104.
[30] Iyortsuun NK, Kim SH, Jhon M, et al. A review of machine learning and deep learning approaches on mental health diagnosis[J]. Healthcare (Basel), 2023, 11(3): 285.
[31] Sun J, Dong QX, Wang SW, et al. Artificial intelligence in psychiatry research, diagnosis, and therapy[J]. Asian J Psychiatr, 2023, 87: 103705.
[32] Pulini AA, Kerr WT, Loo SK, et al. Classification accuracy of neuroimaging biomarkers in attention-deficit/hyperactivity disorder:Effects of sample size and circular analysis[J]. Biol Psychiatry Cogn Neurosci Neuroimaging, 2019, 4(2): 108-120.
[33] Musolf AM, Holzinger ER, Malley JD, et al. What makes a good prediction? Feature importance and beginning to open the black box of machine learning in genetics[J]. Hum Genet, 2022, 141(9): 1515-1528.
[34] Cao M, Martin E, Li X. Machine learning in attention-deficit/hyperactivity disorder: New approaches toward understanding the neural mechanisms[J]. Transl Psychiatry, 2023, 13(1): 236.
[35] Ngiam KY, Khor IW. Big data and machine learning algorithms for health-care delivery[J]. Lancet Oncol, 2019, 20(5): e262-e273.

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

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	张茜, 任姣姣, 高红, 白瑞北, 王朝晖. 近红外脑功能成像技术结合行为评估在注意缺陷多动障碍诊断中的效能分析[J]. 中国儿童保健杂志, 2025, 33(4): 402-408.
[2]	毛广惠, 王丹, 李丽丽, 季忆婷, 王琪玉, 冯晨霞, 赵晓燕, 何璐, 蔡世忠, 陈艳. 学龄期注意缺陷多动障碍儿童的人体成分分析[J]. 中国儿童保健杂志, 2024, 32(9): 1029-1033.
[3]	邓梁琼, 梁媛媛, 岑诗, 胡敏, 李红辉, 曾烜, 廖林燕. 新森林教养方案对注意缺陷多动障碍儿童干预疗效的研究[J]. 中国儿童保健杂志, 2024, 32(8): 856-861.
[4]	章依文. 注意缺陷多动障碍共病智力障碍的诊治挑战[J]. 中国儿童保健杂志, 2024, 32(6): 581-585.
[5]	冯廷勇, 王雪珂. 注意缺陷多动障碍儿童多模态评估的现状与建议[J]. 中国儿童保健杂志, 2024, 32(6): 586-590.
[6]	刘子奇, 刘思奇, 陶梦娇, 任永颖, 李冠男, 孙静, 王昕, 张建昭, 杨健. 不同注意力、控制力水平注意缺陷多动障碍儿童认知功能特点[J]. 中国儿童保健杂志, 2024, 32(6): 591-596.
[7]	张琳琳, 吴赵敏, 王鹏, 操小兰, 刘娟, 王玉凤, 杨斌让. 高焦虑水平注意缺陷多动障碍儿童社会功能损害特征[J]. 中国儿童保健杂志, 2024, 32(6): 597-601.
[8]	郭春燕, 宋丽, 王亚哲, 于茹梦, 张定方, 殷梦华. 注意缺陷多动障碍共患学习障碍儿童的执行功能研究[J]. 中国儿童保健杂志, 2024, 32(6): 602-607.
[9]	刘畅, 张立琴, 杜玮, 刘婷廷. 2023年美国儿科学会先天性甲状腺功能减低症筛查与管理指南解读[J]. 中国儿童保健杂志, 2024, 32(6): 637-642.
[10]	卢鋆锋, 李甦. 注意缺陷多动障碍儿童语用性语言障碍研究进展[J]. 中国儿童保健杂志, 2024, 32(6): 643-647.
[11]	胡旖婷, 江克文. 注意缺陷多动障碍儿童执行功能性别差异及机制研究进展[J]. 中国儿童保健杂志, 2024, 32(6): 648-652.
[12]	吴泳华, 于敬龙, 周康宁, 王俊宏. 基于CiteSpace的近十年国内外注意缺陷多动障碍认知功能的可视化分析[J]. 中国儿童保健杂志, 2024, 32(6): 661-667.
[13]	任苗苗, 陈立. 药物遗传学对注意缺陷多动障碍儿童盐酸哌甲酯治疗的影响[J]. 中国儿童保健杂志, 2024, 32(3): 296-300.
[14]	李梦滔, 代梦琴, 罗尧竞, 赵小燕. 学龄期注意缺陷多动障碍儿童社交焦虑现状及影响因素[J]. 中国儿童保健杂志, 2024, 32(3): 344-348.
[15]	黄美琳, 王海霏, 杜亚松. 注意缺陷多动障碍家庭治疗研究进展[J]. 中国儿童保健杂志, 2024, 32(12): 1328-1332.