基于异常点检测的心理健康辅助诊断方法

doi:10.6040/j.issn.1672-3961.0.2024.057

摘要/Abstract

摘要： 采用异常点检测算法研究心理健康辅助诊断任务,提出并设计一种基于异常点检测的心理健康辅助诊断方法,有效识别心理沙盘数据中的异常样本。在构建心理健康辅助诊断模型过程中,分析数据特性,提取与用户心理健康状况高度相关的特征,构建虚拟心理沙盘数据集;使用4种传统异常点检测算法,识别沙盘数据集中异常样本,设计融合策略,集成不同算法检测结果,提高异常样本检测精准性和效率,辅助人类专家进行精确诊断;对模型预测性能和结果进行详细分析,结合基线模型进行对比评价。试验结果表明,基于异常点检测的心理健康辅助诊断方法在沙具使用相似度、距离度量、聚类性能等3项指标上获得较好性能。

关键词: 心理健康辅助诊断, 虚拟心理沙盘, 机器学习, 异常点检测, 心理健康

中图分类号:

TP391

乔慧妍,段学龙,解驰皓,赵冬慧,马玉玲. 基于异常点检测的心理健康辅助诊断方法[J]. 山东大学学报 (工学版), 2024, 54(4): 76-85.

QIAO Huiyan, DUAN Xuelong, XIE Chihao, ZHAO Donghui, MA Yuling. Approach of assisted diagnosis for mental health based on outlier detection[J]. Journal of Shandong University(Engineering Science), 2024, 54(4): 76-85.

参考文献

[1] World Health Organization. Depression and other common mental disorders: global health estimates[R]. Geneva, Switzerland: World Health Organi-zation, 2017.
[2] 靳宇倡, 张政, 郑佩璇, 等. 远程心理健康服务:应用、优势及挑战[J]. 心理科学进展, 2022, 30(1):141-156. JIN Yuchang, ZHANG Zheng, ZHENG Peixuan, et al. Tele-mental health services: applications, benefits and challenges[J]. Advances in Psychological Science, 2022, 30(1):141-156.
[3] 刘媛媛. 基于SCL-90量表的中国人群心理健康现状及30年变化特征分析[D]. 西安: 中国人民解放军空军军医大学, 2018. LIU Yuanyuan. Analysis of the current situation and 30-year change characteristics of the mental health of the Chinese population based on the SCL-90 scale[D]. Xi'an: Chinese People's Liberation Army Air Force Military Medical University, 2018.
[4] 林仲贤, 丁锦红. 心理测验的含义及其应用[J]. 中国临床康复, 2004(3):522-523. LIN Zhongxian, DING Jinhong. The meaning and application of mental test[J]. Clinical Rehabilitation in China, 2004(3):522-523.
[5] 张雯, 张日昇, 姜智玲. 强迫症状大学生的箱庭作品特征研究[J]. 中国临床心理学杂志, 2011, 19(4):553-557. ZHANG Wen, ZHANG Risheng, JIANG Zhiling. A study on the characteristics of obsessions in college students with obsessive symptoms[J]. Chinese Journal of Clinical Psychology, 2011, 19(4):553-557.
[6] EVANS T M, BIRA L, GASTELUM J B, et al. Evidence for a mental health crisis in graduate education[J]. Nature Biotechnology, 2018, 36(3): 282-284.
[7] 昌敬惠, 袁愈新, 王冬. 新型冠状病毒肺炎疫情下大学生心理健康状况及影响因素分析[J]. 南方医科大学学报, 2020, 40(2):171-176. CHANG Jinghui, YUAN Yuxin, WANG Dong. Analysis of mental health status and influencing factors of college students under novel coronavirus pneumonia epidemic[J]. Journal of Southern Medical University, 2020, 40(2):171-176.
[8] 聂敏. 高校学生行为分析及应用研究[D]. 成都: 电子科技大学, 2020. NIE Min. College student behavior analysis and application research[D]. Chengdu: University of Electronic Science and Technology, 2020.
[9] 江光荣, 李丹阳, 任志洪, 等. 中国国民心理健康素养的现状与特点[J]. 心理学报, 2021, 53(2):182-201. JIANG Guangrong, LI Danyang, REN Zhihong, et al. The current situation and characteristics of Chinese national mental health literacy[J]. Acta Psychologica, 2021, 53(2):182-201.
[10] NAYAK M, NARAYAN K A. Strengths and weaknesses of online surveys[J]. Technology, 2019, 6(7):0837-2405053138.
[11] HAMES J L, BELL D J, PEREZ-LIMA L M, et al. Navigating uncharted waters: considerations for training clinics in the rapid transition to telepsychology and telesupervision during COVID-19[J]. Journal of Psychotherapy Integration, 2020, 30(2): 348.
[12] INCHAUSTI F, MACBETH A, HASSON-OHAYON I, et al. Telepsychotherapy in the age of COVID-19: a commentary[J]. 2020, 30(2):394-405.
[13] 陈红, 汪卫华, 袁水平, 等. 远程心理咨询与面对面咨询的对比研究[J]. 精神医学杂志, 2010, 23(2):128-129. CHEN Hong, WANG Weihua, YUAN Shuiping, et al. A comparative study of remote psychological counseling and face-to-face counseling[J]. Military Medical Journal, 2010, 23(2):128-129.
[14] SUN P, QU Y X, WU J, et al. Improving Chinese teachers' stress coping ability through group sandplay[J]. The Spanish Journal of Psychology, 2018: 65-72.
[15] ROESLER C. Sandplay therapy: an overview of theory, applications and evidence base[J]. The Arts in Psychotherapy, 2019, 64: 84-94.
[16] GUO J, LI D. Effects of image-sandplay therapy on the mental health and subjective well-being of children with autism[J]. Iranian Journal of Public Health, 2021, 50(10): 2046-2054.
[17] 张伯全, 乔冬冬, 王汝展, 等. VR沙盘与实体沙盘用于大学新生初始心理测查自身对照研究[J]. 精神医学杂志, 2018, 31(5):359-362. ZHANG Boquan, QIAO Dongdong, WANG Ruzhan, et al. Self-contrast study of VR sand table and physical sand table used in the initial psychological test of college freshmen[J]. Journal of Psychiatry, 2018, 31(5): 359-362.
[18] 韦玉. 面向广泛型焦虑群体的虚拟沙盘自检系统设计研究[D]. 广州: 华南理工大学, 2021. WEI Yu. Research on the design of virtual sand table self-inspection system for general anxiety groups[D]. Guangzhou: South China University of Technology, 2021.
[19] DOOSHIMA M P, CHIDOZIE E N, ADEMOLA B J, et al. A predictive model for the risk of mental illness in Nigeria using data mining[J]. International Journal of Immunology, 2018, 6(1): 5-16.
[20] 孙伟平. 决策树技术在大学生心理健康测评中的应用研究[D]. 郑州: 郑州大学, 2020. SUN Weiping. Research on the application of decision tree technology in the evaluation of mental health of college students[D]. Zhengzhou: Zhengzhou Univer-sity, 2020.
[21] 林靖怡, 黎大坤, 吴平鑫, 等. 基于社交数据挖掘的心理健康预警建模与分析[J]. 电子技术与软件工程, 2020(8):172-173. LIN Jingyi, LI Dakun, WU Pingxin, et al, Modeling and analysis of mental health early warning based on social data mining[J]. Electronic Technology and Software Engineering, 2020(8):172-173.
[22] 赵丹. 基于决策树的大学生心理危机预警模型研究及应用[D]. 北京: 北京林业大学, 2020. ZHAO Dan. Research and application of college students' psychological crisis early warning model based on decision tree[D]. Beijing: Beijing Forestry University, 2020.
[23] 吴婷. 基于k-means聚类算法的大学生心理管理系统研究[D]. 武汉: 湖北工业大学, 2017. WU Ting. Research on psychological management system of college students based on k-means clustering algorithm[D]. Wuhan: Hubei University of Technology, 2017.
[24] 王震震. 心理云大数据平台中用户心理画像的研究与应用[D]. 北京: 北京邮电大学, 2021. WANG Zhenzhen. Research and application of user psychological portrait in psychological cloud big data platform[D]. Beijing: Beijing University of Posts and Telecommunications, 2021.
[25] 赵向兵, 白栋. 基于Python的学生健康数据聚类分析系统[J]. 电子技术与软件工程, 2021(14):183-185. ZHAO Xiangbing, BAI Dong. Student health data cluster analysis system based on Python[J]. Electronic Technology and Software Engineering, 2021(14):183-185.
[26] 梁娟, 罗海据. 大数据挖掘方法在大学生心理预警系统中的应用[J]. 中国学校卫生, 2018, 39(12):1821-1824. LIANG Juan, LUO Haiju. Application of big data mining method in college students' psychological early warning system[J]. Chinese School Hygiene, 2018, 39(12):1821-1824.
[27] 侯震. 基于数据挖掘的高校学生心理测评与辅导系统的设计与实现[D]. 西安: 西安电子科技大学, 2020. HOU Zhen. Design and implementation of college students' psychological assessment and counseling system based on data mining[D]. Xi'an: Xidian Univer-sity, 2020.
[28] 刘红红.基于数据挖掘的心理疾病预警分析技术研究[J].电子设计工程, 2021, 29(15):31-35. LIU Honghong. Research on early warning analysis technology of mental illness based on data mining[J]. Electronic Design Engineering, 2021, 29(15):31-35.
[29] 祝彦森. 基于改进iForest的学生异常行为检测及分析系统研究[D]. 南京: 南京信息工程大学, 2019. ZHU Yansen. Research on abnormal behavior detection and analysis system of students based on improved iforest[D]. Nanjing: Nanjing University of Information Science and Technology, 2019.
[30] 林少武, 冯春苗, 梁茵, 等. 初始沙盘特征在沙盘心理评估中的应用与发展[J]. 中国健康心理学杂志, 2019, 27(5):788-792. LIN Shaowu, FENG Chunmiao, LIANG Yin, et al. Application and development of initial sand table characteristics in psychological evaluation of sand table[J]. Chinese Journal of Health Psychology, 2019, 27(5):788-792.
[31] LIU F T, TING K M, ZHOU Z H. Isolation forest[C] //2008 Eighth IEEE International Conference on Data Mining. Pisa, Italy: IEEE Xplore, 2008: 413-422.
[32] BREUNIG M M, KRIEGEL H P, NG R T, et al. LOF: Identifying density-based local outliers[C] //Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data. New York, USA: Association for Computing Machinery, 2000: 93-104.
[33] WANG X, WANG X L, MA Y, et al. A fast MST-inspired kNN-based outlier detection method[J]. Information Systems, 2015, 48: 89-112.
[34] DUAN L, XU L, LIU Y, et al. Cluster-based outlier detection[J]. Annals of Operations Research, 2009, 168: 151-168.
[35] DAVIES D L, BOULDIN D W. A cluster separation measure[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1979(2): 224-227.
[36] ZHAO Y, NASRULLAH Z, HRYNIEWICKI M K, et al. LSCP: Locally selective combination in parallel outlier ensembles[C] //Proceedings of the 2019 SIAM International Conference on Data Mining. Alberta, Canda: SIAM International Conference on Data-BMining, 2019: 585-593.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed