随机森林算法在产后抑郁风险预测中的应用

肖美丽; 晏春丽; 付冰; 杨淑平; 朱姝娟; 杨东琪; 雷倍美; 黄瑞瑞; 雷俊

doi:10.11817/j.issn.1672-7347.2020.190655

您当前的位置：

首页 >

文章列表页 >

随机森林算法在产后抑郁风险预测中的应用

扫描看全文

文章被引用时，请邮件提醒。

提交

论著 | 更新时间：2022-05-10

随机森林算法在产后抑郁风险预测中的应用
Risk prediction for postpartum depression based on random forest
中南大学学报(医学版) 中南大学学报(医学版) 2020年45卷第10期页码：1215-1222
作者机构：

1.中南大学湘雅护理学院，长沙 410013
2.中南大学湘雅三医院肿瘤科，长沙 410013
3.中南大学湘雅三医院妇产科，长沙 410013
4.中南大学数学与统计学院，长沙 410083
5.河南省人民医院妇科，郑州 450000
6.中南大学湘雅医院耳鼻喉科，长沙 410008
7.湖南省医药学院护理学院，湖南怀化 418000
作者简介：

肖美丽，Email: 786001878@qq.com, ORCID: 0000-0001-9756-5400
雷俊，Email: leijunbao@126.com, ORCID: 0000-0002-0430-4672
基金信息：

国家自然科学基金(81874267);湖南省重点研发计划项目(2018SK2068);中南大学湘雅三医院“新湘雅”人才工程项目(20170305)
DOI：10.11817/j.issn.1672-7347.2020.190655
中图分类号：
CSTR：

肖美丽, 晏春丽, 付冰, 等. 随机森林算法在产后抑郁风险预测中的应用[J]. 中南大学学报(医学版), 2020,45(10):1215-1222.

Meili XIAO, Chunli YAN, Bing FU, et al. Risk prediction for postpartum depression based on random forest[J]. Journal of Central South University. Medical Science, 2020,45(10):1215-1222.
肖美丽, 晏春丽, 付冰, 等. 随机森林算法在产后抑郁风险预测中的应用[J]. 中南大学学报(医学版), 2020,45(10):1215-1222. DOI： 10.11817/j.issn.1672-7347.2020.190655.

Meili XIAO, Chunli YAN, Bing FU, et al. Risk prediction for postpartum depression based on random forest[J]. Journal of Central South University. Medical Science, 2020,45(10):1215-1222. DOI： 10.11817/j.issn.1672-7347.2020.190655.

摘要

目的,2,探讨随机森林算法在产后抑郁影响因素的筛选和风险预测中的应用效果。,方法,2,选取2017年6月至2018年6月在湖南省长沙市某三甲医院接受产前检查并在该医院分娩，符合纳入和排除标准的孕早期妇女为研究对象。入组时，使用自编的调查问卷、中文版爱丁堡产后抑郁量表(Edinburgh Postnatal Depression Scale，EPDS)调查研究对象的人口经济学、心理社会学、生物学和产科及其他特征；产后4~6周内，采用中文版EPDS进行抑郁评分和自编的产后资料问卷收集分娩和产后资料。采用R软件在训练数据集上建立产后抑郁风险预测的随机森林模型，在验证数据集上采用预测准确率、灵敏度、特异度、阳性预测值、阴性预测值和曲线下面积(area under curve，AUC)评价模型的预测效果。,结果,2,共调查406例研究对象，其中150例的EPDS得分≥9，产后抑郁的发生率为36.9%。通过随机森林算法对训练集建立的模型在验证集上验证，得出预测准确度为80.10%，灵敏度为61.40%，特异度为89.10%，阳性预测值为73.00%，阴性预测值为82.80%，AUC值0.833。采用随机森林算法通过变量重要性评分对产后抑郁影响因素的重要程度进行排序，得出排名前10位的重要预测变量为产前抑郁、产后经济担忧程度、产后工作担忧程度、孕早期血清游离三碘甲腺原氨酸、孕晚期高密度脂蛋白、向婴幼儿发脾气、孕早期血清总胆固醇、孕早期三酰甘油、孕晚期血细胞比容和三酰甘油。,结论,2,随机森林算法在产后抑郁的风险预测中具有较大优势，通过综合评价机制能从复杂的多因素中识别出产后抑郁的重要影响因素，并进行定量分析。这对识别产后抑郁关键因素，进行及时、有效干预具有重要意义。

Abstract

Objective,2,To explore the application of random forest algorithm in screening the risk factors and predictive values for postpartum depression.,Methods,2,We recruited the participants from a tertiary hospital between June 2017 and June 2018 in Changsha City, and followed up from pregnancy up to 4-6 weeks postpartum.Demographic economics, psychosocial, biological, obstetric, and other factors were assessed at first trimesters with self-designed obstetric information questionnaire and the Chinese version of Edinburgh Postnatal Depression Scale (EPDS). During 4-6 weeks after delivery, the Chinese version of EPDS was used to score depression and self-designed questionnaire to collect data of delivery and postpartum. The data of subjects were randomly divided into the training data set and the verification data set according to the ratio of 3꞉1. The training data set was used to establish the random forest model of postpartum depression, and the verification data set was used to verify the predictive effects via the accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and AUC index.,Results,2,A total of 406 participants were in final analysis. Among them, 150 of whom had EPDS score ≥9, and the incidence of postpartum depression was 36.9%. The predictive effects of random forest model in the verification data set were at accuracy of 80.10%, sensitivity of 61.40%, specificity of 89.10%, positive predictive value of 73.00%, negative predictive value of 82.80%, and AUC index of 0.833. The top 10 predictive influential factors that screening by the variable importance measure in random forest model was antenatal depression, economic worries after delivery, work worries after delivery, free triiodothyronine in first trimesters, high-density lipoprotein in third trimester, venting temper to infants, total serum cholesterol and serum triglyceride in first trimester, hematocrit and serum triglyceride in third trimester.,Conclusion,2,Random forest has a great advantage in risk prediction for postpartum depression. Through comprehensive evaluation mechanism, it can identify the important influential factors for postpartum depression from complex multi-factors and conduct quantitative analysis, which is of great significance to identify the key factors for postpartum depression and carry out timely and effective intervention.

关键词

随机森林产后抑郁影响因素风险预测

Keywords

random forestpostpartum depressioninfluencing factorsrisk prediction

references

Norhayati MN, Hazlina NHN, Asrenee AR, et al. Magnitude and risk factors for postpartum symptoms: a literature review[J]. J Affect Disord, 2015, 175: 32-34.

蔡飞亚, 况利, 王我, 等. 基于社会心理因素的产后抑郁症模型的建立和评价[J]. 第二军医大学学报, 2017, 38(4): 476-481.

CAI Feiya, KUANG Li, WANG Wo, et al. Prediction model for postpartum depression based on social psychological factors: establishment and evaluation[J]. Academic Journal of Second Military Medical University, 2017, 38(4): 476-481.

尹航. 孕中、孕晚期单胺类神经递质水平与产后抑郁的关系研究[D]. 长沙: 中南大学, 2018.

YIN Hang. The levels of monoamine neurotransmitters in the second and third trimester of pregnancy and postpartum depression[D]. Changsha: Central South University, 2018.

韩玉, 施海龙, 曲波, 等. 随机森林方法在医学中的应用[J]. 中国预防医学杂志, 2014, 15(1): 79-81.

HAN Yu, SHI Hailong, QU Bo, et al. Application of random forest method in medicine[J]. China Preventive Medicine, 2014, 15(1): 79-81.

方匡南, 吴见彬, 朱建平, 等. 随机森林方法研究综述[J]. 统计与信息论坛, 2011, 26(3): 32-38.

FANG Kuangnan, WU Jianbin, ZHU Jianping, et al. A review of technologies on random forests[J].Statistics Information Forum, 2011, 26(3): 32-38.

Huang L, Jin Y, Gao Y, et al. Longitudinal clinical score prediction in Alzheimer’s disease with soft-split sparse regression based random forest[J]. Neurobiol Aging, 2016, 46: 180-191.

于建民. 老年人抑郁症患病风险评估方法研究[D]. 北京: 北京理工大学, 2016.

YU Jianmin. The research on risk assessment method of elderly depression[D]. Beijing: Beijing Institute of Technology, 2016.

Lee DTS, Yip SK, Chiu HFK, et al. Detecting postnatal depression in Chinese women[J]. Br J Psychiatry, 1998, 172(5): 433-437.

Wang Y, Guo X, Lau Y, et al. Psychometric evaluation of the Mainland Chinese version of the Edinburgh Postnatal Depression Scale[J]. Inter J Nursg Stud, 2009, 46(6): 813-823.

张慧琳, 李乐之. 三种国外产后抑郁量表应用的比较分析[J]. 中华护理杂志, 2007, 42(2): 186-188.

ZHANG Huilin, LI Lezhi. Comparative analysis of 3 postpartum depression scales abroad[J]. Chinese Journal of Nursing, 2007, 42(2): 186-188.

姚登举. 面向医学数据的随机森林特征选择及分类方法研究[D]. 哈尔滨: 哈尔滨工程大学, 2016.

YAO Dengju. Research on feature selection and classification method based on random forest for medical datasets[D]. Harbin: Harbin Engineering University, 2016.

Klainin P, Arthur DG. Postpartum depression in Asian cultures: A literature review[J]. Int J Nurs Stud, 2009, 46(10): 1355-1373.

钱耀荣, 晏晓颖. 中国产后抑郁发生率的系统分析[J]. 中国实用护理杂志, 2013, 29(12): 1-3.

QIAN Yaorong, YAN Xiaoying. Prevalence of postpartum depression in China: a systematic analysis[J]. Chinese Journal of Practical Nursing, 2013, 29(12): 1-3.

龙周婷. 产后抑郁预测因素的纵向研究[D]. 济南: 山东大学, 2014.

LONG Zhouting. Predictors of postpartum depression: A longitudinal research[D]. Jinan: Shandong University, 2014.

李华丽, 李维玲, 刘冬红. 西安某医院1 994名产妇产后抑郁发生的相关因素分析[J]. 中国妇幼健康研究, 2017, 28(11): 1374-1376.

LI Huali, LI Weiling, LIU Donghong. Related factors of postpartum depression in 1 994 cases in a hospital in Xi’an[J]. Chinese Journal of Woman and Child Health Research, 2017, 28(11): 1374-1376.

武晓岩, 李康. 随机森林方法在基因表达数据分析中的应用及研究进展[J]. 中国卫生统计, 2009, 26(4): 437-440.

WU Xiaoyan, LI Kang. Application and research progress of random forest method in gene expression data analysis[J]. Chinese Journal of Health Statistics, 2009, 26(4): 437-440.

Yim IS,Tanner SL, Guardino CM,et al. Biological and psychosocial predictors of postpartum depression: systematic review and call for integration[J]. Annu Rev Clin Psychol, 2015, 11: 99-137.

Pampaka D, Papatheodorou SI, Alseaidan M, et al. Postnatal depressive symptoms in women with and without antenatal depressive symptoms: results from a prospective cohort study[J]. Arch Womens Ment Health, 2019, 22(1): 93-103.

浏览量

下载量

CSCD

工具集

关联资源

基于社会生态理论模型的急性缺血性脑卒中患者早期活动影响因素的质性研究

老年患者住院相关性失能的研究进展

妊娠期血栓弹力图参数的影响因素

机器学习模型预测开放手术修复腹主动脉瘤后急性肾损伤的发生

宫颈癌复发的影响因素及风险预测模型