Construction of a predictive model for auxiliary diagnosis of perinatal depression and screening of machine learning algorithm

WANG Yu; CHU Jiadong; SUN Na; HAN Qiang; SHEN Yueping; ZHOU Lei; ZHU Xinping; ZHANG Xiaobin; YANG Yong

doi:10.7619/jcmp.20232044

Journal of Clinical Medicine in Practice > 2023 > 27(18): 93-99. > DOI: 10.7619/jcmp.20232044

WANG Yu, CHU Jiadong, SUN Na, HAN Qiang, SHEN Yueping, ZHOU Lei, ZHU Xinping, ZHANG Xiaobin, YANG Yong. Construction of a predictive model for auxiliary diagnosis of perinatal depression and screening of machine learning algorithm[J]. Journal of Clinical Medicine in Practice, 2023, 27(18): 93-99. DOI: 10.7619/jcmp.20232044

Citation:

PDF (2859 KB)

Construction of a predictive model for auxiliary diagnosis of perinatal depression and screening of machine learning algorithm

1.
Department of Epidemiology and Biostatistics, School of Public Health of Suzhou Medical College of Soochow University, Suzhou, Jiangsu, 215123
2.
Jiangsu Smart Intelligence Software Technical Company Limited, Taizhou, Jiangsu, 225300
3.
Smart Intelligence Software Technical Company Limited(Hunan), Xiangtan, Hunan, 411100
4.
Suzhou Guangji Hospital of Jiangsu Province, Guangji Hospital Affiliated to Soochow University, Suzhou, Jiangsu, 215137

More Information

Received Date: June 26, 2023
Revised Date: August 01, 2023
Available Online: October 08, 2023

Graphical Abstract

Abstract

Abstract

Objective
To construct a predictive model for assisted diagnosis of maternal perinatal depression (PND) based on machine learning (ML) algorithms and to evaluate the performance of different ML algorithm models.
Methods
A total of 5 814 pregnant women (4 665 prenatal study subjects and 1 149 postnatal study subjects) were evaluated using the 9-item Patient Health Questionnaire Depression Scale (PHQ-9). A total of 19 scale dimension variables of 7 Scales and demographic characteristics were collected as observation variables. Prenatal and postnatal subjects were matched at a 1∶1 ratio propensity score according to age. The feature selection variables were determined by single factor analysis and Pearson correlation coefficient. A diagnostic model for prenatal and postnatal depression was constructed based on five ML algorithm, including Logistic regression model, Random Forest (RF), support vector machine (SVM), Limit Gradient Lift Tree (XGBoost) and Backpropagation (BP) neural network. A 5-fold cross-validation method was used to evaluate thepredictive performance of the model, including sensitivity, specificity and area under the curve (AUC).
Results
When different variables were included, the sensitivity, specificity and AUC of the prediction model constructed by five ML algorithms based on prenatal and postnatal subjects were all within the range of 0.600 to 0.900. RF algorithm was the optimal algorithm in the construction of both prenatal prediction model(when all variables were included, the AUC was 0.834; when the feature selection variable set was included, the AUC was 0.849) and postnatal prediction model(when all variables were included, the AUC was 0.873; when the feature selection variable set was included, the AUC was 0.864).
Conclusion
The prediction model based on five ML algorithms can effectively predict the risk of PND in pregnant women, and the performance of RF algorithm is the best, which provides a reference for the development of auxiliary tools for rapid screening and diagnosis of PND.
- perinatal depression,
- artificial intelligence,
- machine learning algorithm,
- predictive mode,
- random forest,
- auxiliary diagnosis

FullText(HTML)

References (20)

References

[1]	O'HARA M W, WISNER K L. Perinatal mental illness: definition, description and aetiology[J]. Best Pract Res Clin Obstet Gynaecol, 2014, 28(1): 3-12. doi: 10.1016/j.bpobgyn.2013.09.002
[2]	DOSANI A, ARORA H, MAZMUDAR S. mHealth and perinatal depression in low-and middle-income countries: a scoping review of the literature[J]. Int J Environ Res Public Health, 2020, 17(20): 7679. doi: 10.3390/ijerph17207679
[3]	NISAR A, YIN J, WAQAS A, et al. Prevalence of perinatal depression and its determinants in Mainland China: a systematic review and meta-analysis[J]. J Affect Disord, 2020, 277: 1022-1037. doi: 10.1016/j.jad.2020.07.046
[4]	ZHANG Z Y, YU J J, ZENG W T, et al. Association between antenatal depression and adverse perinatal outcomes: a prospective cohort study[J]. J Affect Disord, 2023, 323: 490-495. doi: 10.1016/j.jad.2022.12.008
[5]	王嘉旭, 薛鹏, 江宇, 等. 基于机器学习算法的宫颈癌辅助诊断模型[J]. 中华肿瘤防治杂志, 2023, 30(1): 48-53. https://www.cnki.com.cn/Article/CJFDTOTAL-QLZL202301008.htm
[6]	王艺任, 刘艾艾, 詹翔, 等. 基于机器学习算法筛选鼻咽癌诊断基因标志物的研究[J]. 实用临床医药杂志, 2023, 27(7): 6-11. doi: 10.7619/jcmp.20230091
[7]	周华, 唐剑叶, 秦志强, 等. 网络平台应用对产后抑郁筛查及干预效果的探析[J]. 现代预防医学, 2018, 45(20): 3719-3722. https://www.cnki.com.cn/Article/CJFDTOTAL-XDYF201820019.htm
[8]	钟雨婷, 刘月月, 左莹莹, 等. 基于Android平台的产后抑郁心理护理干预系统研究[J]. 电脑知识与技术, 2021, 17(16): 58-60. https://www.cnki.com.cn/Article/CJFDTOTAL-DNZS202116022.htm
[9]	SPITZER R L, KROENKE K, WILLIAMS J B. Validation and utility of a self-report version of PRIME-MD: the PHQ primary care study. Primary Care Evaluation of Mental Disorders. Patient Health Questionnaire[J]. JAMA, 1999, 282(18): 1737-1744. doi: 10.1001/jama.282.18.1737
[10]	秦泽慧, 梁列新. 中文版PHQ-9在不同人群筛查抑郁症的最佳截止值的研究分析[J]. 临床消化病杂志, 2019, 31(5): 333-336. https://www.cnki.com.cn/Article/CJFDTOTAL-LCXH201905022.htm
[11]	尹畅. 基于机器学习的癌症辅助诊断应用研究[D]. 成都: 电子科技大学, 2020.
[12]	BRÄNN E, FRANSSON E, WIKMAN A, et al. Who do we miss when screening for postpartum depression A population-based study in a Swedish region[J]. J Affect Disord, 2021, 287: 165-173.
[13]	MATSUO S, USHIDA T, EMOTO R, et al. Machine learning prediction models for postpartum depression: a multicenter study in Japan[J]. J Obstet Gynaecol Res, 2022, 48(7): 1775-1785.
[14]	ZHONG M H, ZHANG H, YU C, et al. Application of machine learning in predicting the risk of postpartum depression: a systematic review[J]. J Affect Disord, 2022, 318: 364-379.
[15]	李磊磊. 基于随机森林算法的IVF-ET治疗结局预测模型建立及预测特征分析研究[D]. 长春: 吉林大学, 2022.
[16]	DOLBIER C L, RUSH T E, SAHADEO L S, et al. Relationships of race and socioeconomic status to postpartum depressive symptoms in rural African American and non-Hispanic white women[J]. Matern Child Health J, 2013, 17(7): 1277-1287.
[17]	KETTUNEN P, HINTIKKA J. Psychosocial risk factors and treatment of new onset and recurrent depression during the post-partum period[J]. Nord J Psychiatry, 2017, 71(5): 355-361.
[18]	张雪莲, 汪燕妮, 李英, 等. 正念与情绪调节对孕产妇亚临床抑郁症状的影响[J]. 中国健康教育, 2022, 38(12): 1072-1076. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGJK202212003.htm
[19]	李洋, 赵斌, 袁佳英, 等. 依托孕产妇心身健康服务新模式的孕期抑郁情绪影响因素研究[J]. 中国卫生标准管理, 2023, 14(7): 17-21. https://www.cnki.com.cn/Article/CJFDTOTAL-WSBZ202307004.htm
[20]	KJELDSEN M Z, BRICCA A, LIU X Q, et al. Family history of psychiatric disorders as a risk factor for maternal postpartum depression: a systematic review protocol[J]. Syst Rev, 2022, 11(1): 68.

Cited By

Cited by

Periodical cited type(8)

1.	张雯舒，王宇，吴玉丽，欧晓凤，徐亚林，孙明英. 针刺联合穴位贴敷对缺血性脑卒中后吞咽障碍患者吞咽功能、生活质量的影响. 新中医. 2025(05): 113-119 .
2.	王俊涛，吕文亮. 针刺治疗卒中后吞咽障碍的研究进展. 中国中医急症. 2024(08): 1501-1504 .
3.	焦书佳，宋雯，彭秀娟，张晋，裴久国. 从带病延年论老年病的中医治疗思路. 中国民间疗法. 2024(20): 122-125 .
4.	姚娟娟，曹丽萍，林淑芳，黄超，王舰. 脐针结合康复训练治疗缺血性脑卒中吞咽障碍的疗效分析. 中外医疗. 2024(29): 50-54 .
5.	吴柯玫，秦鹏，韩江秦，李缓，张家馨，程港晨，尹丽丽，牛博真. 风池穴治疗缺血性卒中后吞咽障碍的研究进展. 上海针灸杂志. 2024(12): 1403-1409 .
6.	丁学慧，胡新宇. 普通针刺联合中医康复训练治疗缺血性脑卒中后吞咽障碍的临床效果. 中国医药指南. 2023(18): 57-60 .
7.	赵鸿龙，赵剑锋，屈玉明. 针刺联合督脉灸治疗脑卒中吞咽障碍的效果研究. 山西卫生健康职业学院学报. 2023(03): 70-72 .
8.	程永. 中医“神主导气”作用途径探究. 中医药信息. 2023(11): 63-70 .

Other cited types(4)

Get Citation

PDF

XML

Article views (186) PDF downloads (21) Cited by(12)

Turn off MathJax

Article Contents

Abstract

References

Construction of a predictive model for auxiliary diagnosis of perinatal depression and screening of machine learning algorithm

Abstract

References

Cited by

Periodical cited type(8)

Other cited types(4)

Catalog

Export File

Citation

Format

Content