基于机器学习的单相抑郁与双相抑郁鉴别的脉图参数分类模型

doi:10.3969/j.issn.1006-7795.2022.03.013

首都医科大学学报 ›› 2022, Vol. 43 ›› Issue (3): 407-414.doi: 10.3969/j.issn.1006-7795.2022.03.013

• 精神疾病中西医结合诊疗 • 上一篇下一篇

基于机器学习的单相抑郁与双相抑郁鉴别的脉图参数分类模型

刘鑫子^1,2, 李自艳^1,2, 郑思思^1,2, 朱虹^1,2, 尹冬青^1,2, 贾竑晓^1,2*

1.首都医科大学附属北京安定医院国家精神心理疾病临床医学研究中心精神疾病诊断与治疗北京市重点实验室,北京 100088;
2.人脑保护高精尖创新中心首都医科大学,北京 100069

收稿日期:2022-02-20 出版日期:2022-06-21 发布日期:2022-06-01
基金资助:
首都卫生发展科研专项(2020-4-2123),北京市医院管理中心临床医学发展专项经费资助(ZYLX202129),北京医院管理中心登峰人才(DFL20191901)。

Classification model of pulse parameters of unipolar depression and bipolar depression based on machine learning

Liu Xinzi^1,2, Li Ziyan^1,2, Zheng Sisi^1,2, Zhu Hong^1,2, Yin Dongqing^1,2, Jia Hongxiao^1,2*

1. The National Clinical Research Center for Mental Disorders & Beijing Key Laboratory of Mental Disorders, Beijing Anding Hospital, Capital Medical University, Beijing 100088, China;
2. Advanced Innovation Center for Human Brain Protection, Capital Medical University, Beijing 100069, China

Received:2022-02-20 Online:2022-06-21 Published:2022-06-01
Contact: *E-mail:jhxlj@ccmu.edu.cn
Supported by:
Capital's Funds for Health Improvement and Research (2020-4-2123),Beijing Hospitals Authority Clinical Medicine Development of Special Funding Support (ZYLX202129),Beijing Hospitals Authority's Ascent Plan (DFL20191901).

摘要/Abstract

摘要： 目的基于机器学习方法研究针对单相抑郁与双相抑郁脉图参数的特征差异。方法采用道生中医四诊仪DS01-A信息采集系统,对31名单相抑郁患者与57名双相抑郁患者分别采集脉图信息,应用SPSS 26进行脉图参数比较,应用R 4.0.5 建立向量机算法(support vector machines,SVM)与随机森林算法(random forest,RF)模型,评估模型性能并获得模型特征重要性排序。结果单相抑郁与双相抑郁脉图参数在脉力、脉率、AD、T1/T4、H1、H3/H1、(H3-H1)/H1共7个变量差异具有统计学意义(P<0.05);SVM模型与RF的鉴别模型都具有较好的鉴别准确率和稳定性。SVM模型鉴别准确率为80.56%,曲线下面积( area under curve,AUC )值为83.04%;RF模型鉴别准确率为80.56%,AUC值为84.62%。模型特征重要性前5位分别为H4、H2、AD、AGE、(T4-T1)/T与H3、H4、AD、AGE、H2。结论单相抑郁与双相抑郁在脉图参数上具有明显差异特征,可辅助临床医生进行单双相抑郁鉴别。

关键词: 单相抑郁, 双相抑郁, 脉图参数, 机器学习

Abstract: Objective To study the characteristic difference of pulse parameters between unipolar depression and bipolar depression based on machine learning method. Methods Thirty-one patients with unipolar depression and 57 patients with bipolar depression were collected with Daosheng DS01-A TCM four diagnostic instruments, and the pulse parameters were compared with SPSS 26. The models of support vector machines (SVM) and random forest (RF) were established with R 4.0.5. We evaluated the model performance and obtained the importance ranking of model features. Results There were significant differences in pulse force, pulse rate, AD, T1/ T4, H1, H3/ H1, and (H3-H1)/ H1 between unipolar depression and bipolar depression (P<0.05). Both SVM model and RF model have good accuracy and stability. The accuracy of SVM model is 80.56%, area under curve (AUC) value is 83.04%. The accuracy of RF model is 80.56%, AUC value is 84.62%. The top 5 importance of model features are H4, H2, AD, AGE, (T4-T1)/T and H3, H4, AD, AGE, H2 respectively. Conclusion Unipolar depression and bipolar depression have obvious differences in pulse parameters, which can assist clinicians in the differentiation of unipolar and bipolar depression.

Key words: unipolar depression, bipolar depression, pulse parameters, machine learning

中图分类号:

R749

刘鑫子, 李自艳, 郑思思, 朱虹, 尹冬青, 贾竑晓. 基于机器学习的单相抑郁与双相抑郁鉴别的脉图参数分类模型[J]. 首都医科大学学报, 2022, 43(3): 407-414.

Liu Xinzi, Li Ziyan, Zheng Sisi, Zhu Hong, Yin Dongqing, Jia Hongxiao. Classification model of pulse parameters of unipolar depression and bipolar depression based on machine learning[J]. Journal of Capital Medical University, 2022, 43(3): 407-414.

参考文献

[1] Grassi-Oliveira R, Cogo-Moreira H, Salum G A, et al. Childhood Trauma Questionnaire (CTQ) in Brazilian samples of different age groups: findings from confirmatory factor analysis[J]. PLoS One, 2014, 9(1): e87118.
[2] 徐贵云, 唐牟尼, 党亚梅. 双相抑郁障碍的临床特征研究进展(上)[J]. 中国神经精神疾病杂志, 2008, 34(11): 697-699.
[3] Fritz K, Russell A M T, Allwang C, et al. Is a delay in the diagnosis of bipolar disorder inevitable?[J]. Bipolar Disord, 2017, 19(5): 396-400.
[4] 马瑞华, 王志仁, 王帆, 等. 单相抑郁与双相抑郁差异的研究进展[J]. 神经疾病与精神卫生, 2020, 20(2): 137-141.
[5] 尹冬青, 贾竑晓, 周方, 等. 内生火热与双相情感障碍发病的关系探讨[J]. 中华中医药学刊, 2017, 35(2): 482-484.
[6] 曹欣冬, 王伟. 单相抑郁发作与双相抑郁发作中医证候学比较[J]. 四川中医, 2008, 26(7): 18-21.
[7] 燕海霞, 王忆勤. 中医脉诊研究与临床应用[M]. 上海: 上海科学技术出版社, 2016.
[8] 丁世飞, 齐丙娟, 谭红艳. 支持向量机理论与算法研究综述[J]. 电子科技大学学报, 2011, 40(1): 1-10.
[9] 美国精神医学学会. 精神障碍诊断与统计手册[M]. 5版. 张道龙, 译. 北京: 北京大学出版社, 2016.
[10] Van Buuren S, Groothuis-Oudshoorn K. MICE: multivariate imputation by chained equations in R[J]. J Stat Softw, 2011, 45(3): 1-67.
[11] Lang M, Binder M, Richter J, et al. mlr3: a modern object-oriented machine learning framework in R[J]. J Open Source Softw, 2019, 4(44): 1903.
[12] Lantz B. Machine learning with R: expert techniques for predictive modeling to solve all your data analysis problems[M]. 2nd ed. Birmingham: Packt Publishing, 2015.
[13] Becker M, Schratz P, Lang M ,et al. mlr3fselect: feature Selection for ‘mlr3’[CP /OL].[2022-01-03]. https://mlr3fselect.mlr-org.com/, https://github.com/mlr-org/mlr3fselect/.
[14] Becker M, Lang M, Richter L, et al. mlr3tuning: tuning for ‘mlr3’. R package version 0.9.0[CP /OL] .[2022-01-03]. https://CRAN.R-project.org/package=mlr3tuning.
[15] Molnar C. Interpretable machine learning: a guide for making black box models explainable[CP/OL]. (2021-12-19)[2022-01-04]. https://christophm.github.io/interpretable-ml-book/.
[16] Wollenhaupt-Aguiar B, Librenza-Garcia D, Bristot G, et al. Differential biomarker signatures in unipolar and bipolar depression: a machine learning approach[J]. Aust N Z J Psychiatry, 2020, 54(4): 393-401.
[17] 赵倩倩, 李媛媛, 钱鹏, 等. 原发性高血压病人脉图参数与肾功能指标的相关性[J]. 中西医结合心脑血管病杂志, 2020, 18(24): 4116-4120.
[18] 乔丽杰, 张志枫, 许家佗, 等. 高血压病人中医脉图参数与超声心动图参数的相关性分析[J]. 中西医结合心脑血管病杂志, 2020, 18(4): 549-553.
[19] 刘璐, 张春柯, 陈瑞, 等. 冠心病合并慢性心力衰竭患者心功能状态与脉图时域特征的关联研究[J]. 世界科学技术-中医药现代化, 2020, 22(9): 3301-3305.
[20] Hasin D S, Goodwin R D, Stinson F S, et al. Epidemiology of major depressive disorder: results from the National Epidemiologic Survey on Alcoholism and Related Conditions[J]. Arch Gen Psychiatry, 2005, 62(10): 1097-1106.
[21] 许明智, 杨程甲. 2015年AHA关于重度抑郁症和双相障碍加速青年动脉粥样硬化和早期心血管病的科学声明[J]. 中国循环杂志, 2016, 31(Z2): 148-155.
[22] 尚倩倩, 王蕾, 陈兆善, 等. 159例原发性高血压病合并靶器官损害患者脉图参数分析[J]. 世界科学技术:中医药现代化, 2016, 18(6): 1033-1039.
[23] 彭清华, 谢梦洲. 中医脉诊临床图解[M]. 北京: 化学工业出版社, 2019.
[24] 鉏桂祥, 陈清光, 许家佗, 等. 亚健康状态人群的脉象图特征分析[J]. 中西医结合学报, 2012, 10(10): 1099-1105.
[25] 李自艳, 曹龑, 贾竑晓. 贾竑晓以养阴调阳法治疗双相情感障碍的临床经验[J]. 中华中医药杂志, 2019, 34(7): 3087-3090.
[26] 武学润, 于志峰. 抑郁症患者治疗前后脉图参数变化的研究[J]. 云南中医中药杂志, 2018, 39(6): 31-32.

基于机器学习的单相抑郁与双相抑郁鉴别的脉图参数分类模型

Classification model of pulse parameters of unipolar depression and bipolar depression based on machine learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	邬金鸣, 孙海霞, 王嘉阳, 钱庆. 基于电子病历的重症老年患者急性肾损伤连续风险预测研究[J]. 首都医科大学学报, 2022, 43(4): 600-609.
[2]	杨丰春, 郑思, 李姣. 可解释机器学习方法在疾病预测中的应用:脓毒血症患者死亡风险研究[J]. 首都医科大学学报, 2022, 43(4): 610-617.
[3]	冷菲, 李巍. 基于XGBoost对肺鳞癌和肺腺癌的分类预测[J]. 首都医科大学学报, 2019, 40(6): 889-893.