人工智能在儿童青少年焦虑和抑郁中应用的Scoping综述

doi:10.3969/j.issn.1006-9771.2024.05.003

《中国康复理论与实践》 ›› 2024, Vol. 30 ›› Issue (5): 513-519.doi: 10.3969/j.issn.1006-9771.2024.05.003

人工智能在儿童青少年焦虑和抑郁中应用的Scoping综述

苏如峰¹, 钟晓珂², 高晓妍³, 蒋长好³()

1.首都体育学院体育人工智能研究院，北京市 100191
2.福建师范大学体育科学学院，福建福州市 350108
3.首都体育学院运动脑成像研究中心，北京市 100089

收稿日期:2024-04-07 出版日期:2024-05-25 发布日期:2024-06-12
通讯作者: 蒋长好(1966-)，男，汉族，安徽巢湖市人，博士，教授，主要研究方向：脑科学与运动认知。E-mail： jiangchanghao@cupes.edu.cn
作者简介:苏如峰(1979-)，男，汉族，河南安阳市人，博士，讲师，主要研究方向：体育文化、人工智能与体育运动。
基金资助:
1.北京市社会科学基金项目(19YTA001);2.首都体育学院体育医学工程学新兴交叉学科平台研究项目(20230929);3.国家自然科学基金项目(32371132)

Application of artificial intelligence in anxiety and depression among children and adolescents: a scoping review

SU Rufeng¹, ZHONG Xiaoke², GAO Xiaoyan³, JIANG Changhao³()

1. Institute of Artificial Intelligence in Sports, Capital University of Physical Education and Sports, Beijing 100191, China
2. School of Physical Education and Sport Science, Fujian Normal University, Fuzhou, Fujian 350108, China
3. The Center of Neuroscience and Sports, Capital University of Physical Education and Sports, Beijing 100089, China

Received:2024-04-07 Published:2024-05-25 Online:2024-06-12
Contact: JIANG Changhao, E-mail: jiangchanghao@cupes.edu.cn
Supported by:
Beijing Key Project of Philosophy and Social Sciences(19YTA001);Emerging Interdisciplinary Platform for Medicine and Engineering in Sports(20230929);National Natural Science Foundation(32371132)

摘要/Abstract

摘要：

目的系统综述人工智能在儿童青少年焦虑和抑郁中的应用。

方法检索2014年1月至2024年1月PubMed、Web of Science、中国知网和万方数据库中人工智能与儿童青少年焦虑和抑郁相关文献，进行Scoping综述。

结果最终纳入10篇文献，来自美国、中国、澳大利亚和法国，主要来源于心理学、公共卫生、临床医学、神经科学、康复等领域的期刊，涉及6项横断面研究、3项纵向研究和1项访谈研究，包括10 880例参与者，年龄3~18岁。数据类型主要包括问卷/量表、访谈数据和脑成像数据。从数据中提取与焦虑、抑郁相关的特征，使用人工智能技术建立模型，以识别或预测儿童青少年焦虑和抑郁。

结论人工智能在识别或预测儿童和青少年焦虑和抑郁方面具有潜在的价值和应用前景。

关键词: 儿童, 青少年, 人工智能, 焦虑, 抑郁, Scoping综述

Abstract:

Objective To review the application of artificial intelligence in anxiety and depression among children and adolescents.

Methods PubMed, Web of Science, CNKI and Wanfang data were searched for literature related to artificial intelligence applied in of anxiety and depression among children and adolescents from January, 2014 to January, 2024, and a scoping review was conducted.

Results A total of ten papers were included, originating from the United States, China, Australia and France. These researches were primarily published in journals related to psychology, public health, clinical medicine, neuroscience and rehabilitation, involving six cross-sectional researches, three longitudinal researches and one interview, including 10 880 participants aged from three to 18 years. The types of data mainly included questionnaires/scales, interview data and brain imaging data. Features related to anxiety and depression were extracted from the data, and artificial intelligence were employed to develop models for the identification or prediction of anxiety and depression in children and adolescents.

Conclusion Artificial intelligence is potential for identifying or predicting anxiety and depression in children and adolescents.

Key words: children, adolescents, artificial intelligence, anxiety, depression, scoping review

中图分类号:

R749.7

苏如峰, 钟晓珂, 高晓妍, 蒋长好. 人工智能在儿童青少年焦虑和抑郁中应用的Scoping综述[J]. 《中国康复理论与实践》, 2024, 30(5): 513-519.

SU Rufeng, ZHONG Xiaoke, GAO Xiaoyan, JIANG Changhao. Application of artificial intelligence in anxiety and depression among children and adolescents: a scoping review[J]. Chinese Journal of Rehabilitation Theory and Practice, 2024, 30(5): 513-519.

图/表 2

图1

表1

纳入文献基本特征"

纳入文献	国家	年龄/岁	被试数量/人	方法与工具	预测指标	结局指标	人工智能模型/算法
Haque等^[18](2021)	澳大利亚	14~17	n = 6310 训练集 = 4417 测试集 = 1893	横断面研究：从Young Minds Matter数据库筛选出与抑郁最相关的11个特征，使用4种模型评估预测效果	抑郁	准确率随机森林：95% GNB：94% 决策树：95% XGBoost：95%	随机森林 GNB 决策树 XGBoot
Zhao等^[19](2021)	中国	15~18	n = 1029 训练集 = 728 测试集 = 301	横断面研究；人口学特征、PPS; 10i-CDRS; FFMQ; GSES; BFPI; LOT; PHQ-9数据，人工神经网络建立识别模型	抑郁	准确率抑郁：81.06%	人工神经网络
Zhang等^[20](2022)	中国	12~18	n = 56 E = 18 C = 38	访谈：通过面对面访谈收集数据，通过MINI进行抑郁评估，提取全局和局部特征并构建模型	抑郁	准确率融合模型：73.1% 细粒度融合模型：71.75% 粗粒度融合模型：69.59%	粗粒度融合细粒度融合
Jin等^[21](2020)	美国	13~15.5	n = 348 训练集 = 174 测试集 = 174	纵向研究；被试先进行RSFC扫描，然后使用IDAS-II评估被试当时和18个月后的抑郁	抑郁	AUC 内部连接模型：0.78 扩展连接模型：0.72 整脑模型：0.69	神经网络模型
Zhou等^[22](2021)	中国	E1=16.22 E2=16.02 C=16.32	n = 300 训练集 = 150 测试集 = 150	横断面研究；所有被试完成结构性磁共振成像扫描，提取68个脑区皮质厚度作为特征，建立分类模型进行区分	抑郁	准确率 MDD vs. 对照：79.21% SCZ vs. 对照：69.88% MDD vs. SCZ：62.93%	支持向量机
Hawes等^[23](2023)	美国	3~15	n = 748 训练集 = 374 测试集 = 374	纵向研究；从3~15岁，每3年进行一次生理和心理的评估，在15岁时进行抑郁和焦虑的识别	焦虑、抑郁	AUC 抑郁：0.669~0.751 焦虑：0.621-0.788	逻辑回归模型
Xiong等^[24](2021)	澳大利亚	6~16	n = 297 将数据集随机分成5个组，依次作为训练集	横断面研究；通过YODA收集被试的焦虑数据，然后用贝叶斯神经网络方法预测青少年的焦虑	焦虑	AUC 分离焦虑：0.8683 社交焦虑：0.9091 广泛性焦虑：0.8769	贝叶斯神经网络机器学习分类器深度学习分类器特征选择器
Sawalha等^[25](2021)	美国	5.5~9.5	n = 45 训练集n = 36 测试集n = 9	横断面研究：焦虑、非焦虑儿童完成情绪面孔处理任务，进行fMRI扫描，比较焦虑与非焦虑儿童颞极区的神经活动差异	焦虑	准确率右侧颞极区可以最准确地区分焦虑儿童和非焦虑儿童(分类准确率81%)	AdaBoost模型
Haque等^[26](2023)	澳大利亚	4~17	n = 1011 训练集 = 708 测试集 = 303	横断面研究；根据澳大利亚青少年心理健康调查的数据库，用3种机器学习模型检测OCD、SAD和ADHD	OCD、SAD、ADHD	准确率 GNB(OCD)：91% GNB(SAD)：79% 随机森林(ADHD)：91%	机器学习随机森林 GNB
Chavanne等^[27](2023)	法国	14~23	n = 736 训练集 = 580 测试集 = 156	纵向研究：测量14岁时的灰质体积，完成DAWBA、GAD、mAD、SURPS、SDQ、LEQ、NEO-FFI和TCI-R，对18~23岁的焦虑进行预测	GAD、mAD、焦虑	AUC GAD：0.6 mAD：0.52 总体焦虑：0.68	随机森林支持向量机逻辑回归

表1

参考文献 36

[1]	BENNETT K, COURTNEY D, DUDA S, et al. An appraisal of the trustworthiness of practice guidelines for depression and anxiety in children and youth[J]. Depress Anxiety, 2018, 35(6): 530-540. doi: 10.1002/da.22752 pmid: 29697887
[2]	CAMPISI S C, ATAULLAHJAN A, BAXTER J A B, et al. Mental health interventions in adolescence[J]. Curr Opin Psychol, 2022, 48: 101492.
[3]	ZHOU Y, CHEN X, GU R, et al. Personalized identification and intervention of depression in adolescents: a tertiary-level framework[J]. Sci Bull, 2024, 69(7): 867-871.
[4]	莫大明, 闫军伟, 李欣, 等. 新冠肺炎疫情下儿童青少年焦虑症状检出率及影响因素[J]. 四川精神卫生, 2020, 33(3): 202-206.
	MO D M, YAN J W, LI X, et al. Prevalence rate and related influencing factors of anxiety disorder in children and adolescents during the outbreak of COVID-19[J]. Sichuan Ment Health, 2020, 33(3): 202-206.
[5]	BHATTACHARYA R, SHEN C, SAMBAMOORTHI U. Excess risk of chronic physical conditions associated with depression and anxiety[J]. BMC Psychiatry, 2014, 14: 1-10.
[6]	CHENG W, ROLLS E, GONG W, et al. Sleep duration, brain structure, and psychiatric and cognitive problems in children[J]. Mol Psychiatry, 2021, 26(8): 3992-4003.
[7]	YUAN W, CHEN L, WU Y, et al. Sleep time and quality associated with depression and social anxiety among children and adolescents aged 6-18 years, stratified by body composition[J]. J Affect Disord, 2023, 338: 321-328.
[8]	苏志强, 王钢, 刘传星, 等. 童年中晚期抑郁的发展及其与问题行为的并发:一项两年追踪研究[J]. 心理发展与教育, 2018, 34(2): 200-209.
	SU Z Q, WANG G, LIU C X, et al. The development trend of depression and its concurrency with problem behaviors during middle and late childhood: a two-year longitudinal study[J]. Psychol Dev Educ, 2018, 34(2): 200-209.
[9]	张婧雅, 邹敏, 孙宏伟, 等. 听障儿童青少年焦虑或抑郁情绪心理干预效果的系统综述[J]. 中国康复理论与实践, 2023, 29(9): 1004-1011. doi: 10.3969/j.issn.1006-9771.2023.09.002
	ZHANG J Y, ZOU M, SUN H W, et al. Effect of psychological intervention on anxiety or depression in children and adolescents with hearing impairment: a systematic review[J]. Chin J Rehabil Theory Pract, 2023, 29(9): 1004-1011.
[10]	GROSS J J. Emotion regulation: affective, cognitive, and social consequences[J]. Psychophysiology, 2002, 39(3): 281-291. doi: 10.1017/s0048577201393198 pmid: 12212647
[11]	GHANDOUR R M, SHERMAN L J, VLADUTIU C J, et al. Prevalence and treatment of depression, anxiety, and conduct problems in US children[J]. J Pediatr, 2019, 206: 256-267. e3.
[12]	THAPAR A, COLLISHAW S, PINE D S, et al. Depression in adolescence[J]. Lancet, 2012, 379(9820): 1056-1067. doi: 10.1016/S0140-6736(11)60871-4 pmid: 22305766
[13]	KIELING C, ADEWUYA A, FISHER H L, et al. Identifying depression early in adolescence[J]. Lancet Child Adolesc Health, 2019, 3(4): 211-213. doi: S2352-4642(19)30059-8 pmid: 30878111
[14]	PATTON G C, COFFEY C, ROMANIUK H, et al. The prognosis of common mental disorders in adolescents: a 14-year prospective cohort study[J]. Lancet, 2014, 383(9926): 1404-1411. doi: 10.1016/S0140-6736(13)62116-9 pmid: 24439298
[15]	CALDWELL D M, DAVIES S R, HETRICK S E, et al. School-based interventions to prevent anxiety and depression in children and young people: a systematic review and network meta-analysis[J]. Lancet Psychiatry, 2019, 6(12): 1011-1020. doi: S2215-0366(19)30403-1 pmid: 31734106
[16]	SHATTE A B R, HUTCHINSON D M, TEAGUE S J. Machine learning in mental health: a scoping review of methods and applications[J]. Psychol Med, 2019, 49(9): 1426-1448. doi: 10.1017/S0033291719000151 pmid: 30744717
[17]	TRICCO A C, LILLIE E, ZARIN W, et al. PRISMA extension for scoping reviews (PRISMA-ScR): checklist and explanation[J]. Ann Intern Med, 2018, 169(7): 467-473. doi: 10.7326/M18-0850 pmid: 30178033
[18]	HAQUE U M, KABIR E, KHANAM R. Detection of child depression using machine learning methods[J]. PLoS One, 2021, 16(12): e0261131.
[19]	ZHAO F F. Artificial neural network application for identifying risk of depression in high school students: a cross-sectional study[J]. BMC Psychiatry, 2021, 21: 1-13.
[20]	ZHANG L, FAN Y, JIANG J, et al. Adolescent depression detection model based on multimodal data of interview audio and text[J]. Int J Neural Syst, 2022, 32(11): 2250045.
[21]	JIN J, VAN SNELLENBERG J X, PERLMAN G, et al. Intrinsic neural circuitry of depression in adolescent females[J]. J Child Psychol Psychiatry, 2020, 61(4): 480-491. doi: 10.1111/jcpp.13123 pmid: 31512744
[22]	ZHOU Z, WANG K, TANG J, et al. Cortical thickness distinguishes between major depression and schizophrenia in adolescents[J]. BMC Psychiatry, 2021, 21(1): 361. doi: 10.1186/s12888-021-03373-1 pmid: 34284747
[23]	HAWES M T, SCHWARTZ H A, SON Y, et al. Predicting adolescent depression and anxiety from multi-wave longitudinal data using machine learning[J]. Psychol Med, 2023, 53(13): 6205-6211.
[24]	XIONG H, BERKOVSKY S, ROMANO M, et al. Prediction of anxiety disorders using a feature ensemble based bayesian neural network[J]. J Biomed Inform, 2021, 123: 103921.
[25]	SAWALHA J, YOUSEFNEZHAD M, SELVITELLA A M, et al. Predicting pediatric anxiety from the temporal pole using neural responses to emotional faces[J]. Sci Rep, 2021, 11(1): 16723. doi: 10.1038/s41598-021-95987-4 pmid: 34408203
[26]	HAQUE U M, KABIR E, KHANAM R. Early detection of paediatric and adolescent obsessive: compulsive, separation anxiety and attention deficit hyperactivity disorder using machine learning algorithms[J]. Health Inf Sci Syst, 2023, 11(1): 31.
[27]	CHAVANNE A V, PAILLÈRE MARTINOT M L, PENTTILÄ J, et al. Anxiety onset in adolescents: a machine-learning prediction[J]. Mol Psychiatry, 2023, 28(2): 639-646.
[28]	MEIER S M, DECKERT J. Genetics of anxiety disorders[J]. Curr Psychiatry Rep, 2019, 21(3): 16.
[29]	LUSSIER A A, HAWRILENKO M, WANG M J, et al. Genetic susceptibility for major depressive disorder associates with trajectories of depressive symptoms across childhood and adolescence[J]. J Child Psychol Psychiatry, 2021, 62(7): 895-904.
[30]	WEN L, YANG K, CHEN J, et al. Associations between resilience and symptoms of depression and anxiety among adolescents: examining the moderating effects of family environment[J]. J Affect Disord, 2023, 340: 703-710.
[31]	HAMILTON J L, SHAPERO B G, STANGE J P, et al. Emotional maltreatment, peer victimization, and depressive versus anxiety symptoms during adolescence: hopelessness as a mediator[J]. J Clin Child Adolesc, 2013, 42(3): 332-347.
[32]	STEARE T, MUÑOZ C G, SULLIVAN A, et al. The association between academic pressure and adolescent mental health problems: a systematic review[J]. J Affect Disord, 2023, 339: 302-317.
[33]	HALFON S, DOYRAN M, TÜRKMEN B, et al. Multimodal affect analysis of psychodynamic play therapy[J]. Psychother Res, 2021, 31(3): 313-328.
[34]	WANG Y, WANG J, LIU X, et al. Detecting depression through gait data: examining the contribution of gait features in recognizing depression[J]. Front Psychiatry, 2021, 12: 661213.
[35]	ACHARYA U R, SUDARSHAN V K, ADELI H, et al. A novel depression diagnosis index using nonlinear features in EEG signals[J]. Eur Neurol, 2015, 74(1-2): 79-83. doi: 10.1159/000438457 pmid: 26303033
[36]	ABD-ALRAZAQ A, ALSAAD R, AZIZ S, et al. Wearable artificial intelligence for anxiety and depression: scoping review[J]. J Med Internet Res, 2023, 25: e42672.

人工智能在儿童青少年焦虑和抑郁中应用的Scoping综述

Application of artificial intelligence in anxiety and depression among children and adolescents: a scoping review

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 2

参考文献 36

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	魏晓微. 数字赋能技术促进智力与发展性残疾儿童身体活动和健康的系统综述[J]. 《中国康复理论与实践》, 2024, 30(5): 497-504.
[2]	王红志, 杨剑. 虚拟现实技术在脑性瘫痪儿童青少年身体活动和健康中的应用：系统综述的系统综述[J]. 《中国康复理论与实践》, 2024, 30(5): 505-512.
[3]	钟晓珂, 王琦, 昌思琴, 蒋长好. 长期身体活动对孤独症谱系障碍儿童执行功能效果的系统综述[J]. 《中国康复理论与实践》, 2024, 30(5): 535-542.
[4]	吴佳洺, 张青, 武爱红. 智力与发展性残疾儿童青少年音乐干预的功能、健康和发展效益：系统综述的系统综述[J]. 《中国康复理论与实践》, 2024, 30(5): 543-553.
[5]	卫宁, 曾艳玲, 蒋娜, 张倩, 益筱哲, 王建云, 王登廷, 张艳, 裴泓波, 黄朝荣. 家长医患沟通效能对孤独症谱系障碍儿童康复效果的影响[J]. 《中国康复理论与实践》, 2024, 30(5): 577-585.
[6]	魏晓微. 数字赋能残疾儿童身体活动与健康：国际政策架构与核心内容及行动战略研究[J]. 《中国康复理论与实践》, 2024, 30(4): 381-388.
[7]	王振洲, 张杨. 近20年国际人工智能赋能特殊儿童诊断及干预研究的可视化分析[J]. 《中国康复理论与实践》, 2024, 30(4): 404-415.
[8]	陆恺, 柳宇鑫, 王素娟, 陈伟明, 许业涛, 周昊, 姚叶林, 尹欢欢, 张铮铮, 杜岩. 英国医学研究理事会肌力测试在重症监护室患儿中的评定者间信度[J]. 《中国康复理论与实践》, 2024, 30(4): 493-496.
[9]	王馨婷, 杨剑. 基于ICF的儿童运动功能和活动能力测量工具的内容和心理测量特性研究[J]. 《中国康复理论与实践》, 2024, 30(3): 265-272.
[10]	张青, 武爱红, 武砀, 石彩秀. 基于ICF构建特殊儿童融合教育导向多元安置服务：政策和理论架构与方法体系[J]. 《中国康复理论与实践》, 2024, 30(2): 141-147.
[11]	喜悦, 杨剑. 不同身体活动对脑性瘫痪儿童青少年健康效益的系统综述[J]. 《中国康复理论与实践》, 2024, 30(2): 157-167.
[12]	吴进龙, 任占兵, 易子珍, 彭莉. 孤独症谱系障碍个体互动期间脑间同步特点的Scoping综述[J]. 《中国康复理论与实践》, 2024, 30(2): 168-175.
[13]	李芳, 刘慧珍, 梅利平, 张通, 张豪杰, 李冰洁, 赵军. 脑梗死患者康复科住院期间卒中后抑郁程度的相关因素[J]. 《中国康复理论与实践》, 2024, 30(2): 217-222.
[14]	张明兰, 张玲玲, 王丽莎, 刘莉, 高润, 饶江, 刘婉, 夏子安, 张传文, 程欣欣. 自主神经功能对卒中后抑郁患者运动功能的影响[J]. 《中国康复理论与实践》, 2024, 30(2): 223-231.
[15]	宋以玲, 任园春, 朱飞龙, 匡冬青, 曹庆久, 林杨, 王芳. 注意缺陷多动障碍儿童粗大动作技能与执行功能发展的特点及关系[J]. 《中国康复理论与实践》, 2024, 30(1): 1-9.