Objective  To identify risk factors for perimenopausal syndrome (PMS) among perimenopausal women using machine learning algorithms, and to construct a predictive model for the risk of developing moderate to severe PMS in perimenopausal women.  

Methods  Perimenopausal women from 48 communites in Pudong New Area, Shanghai were selected as the study subjects. Based on the Kupperman index, participants were divided into the normal or mild PMS group and the moderate to severe PMS group. The data was randomly divided into training set and testing set, and feature selection was performed using the Boruta algorithm and SHAP algorithm. Logistic regression (LR), random forest (RF), support vector machine (SVM), and gradient boosting decision tree (GBDT) were constructed, and model performances were evaluated using accuracy, precision, recall, area under curve(AUC) of the receiver operating characteristic curve, and F1-score.

Results  A total of 856 perimenopausal women were included in the study, of which 557 were in the normal or mild PMS group and 299 were in the moderate to severe PMS group; 599 were in the training set and 257 were in the testing set. 9 features (employment status, exercise, age, menstrual condition, medical history, obesity, residence area, history of health education, household register) were selected as predictors for the final model using the Boruta algorithm and SHAP analysis. After parameter tuning, the 10-fold cross-validation AUC of LR, RF, SVM, and GBDT models based on the training set were 0.64, 0.77, 0.74, and 0.77, respectively. The AUC of the LR, RF, SVM, and GBDT models based on the testing set were 0.63, 0.69, 0.69, and 0.73, respectively, with recall rates of 0.59, 0.55, 0.55, and 0.62.

Conclusion  Among the constructed predictive models for the risk of developing moderate to severe PMS in perimenopausal women, the GBDT model demonstrated the best predictive performance and has potential clinical value. This study provides a new approach for the early identification and intervention of moderate to severe PMS in perimenopausal women.

1.郭丽, 刘春, 巩爱玲.更年期综合征的研究进展[J]. 中国当代医药, 2019, 26(33): 21-23. [Guo L, Liu C, Gong AL. Research progress of climacteric syndrome[J]. China Modern Medicine, 2019, 26(33): 21-23.] DOI: 10.3969/j.issn.1674-4721.2019.33.007.

2.Zeng M, Li M, Li M, et al. 2-Phenylacetamide isolated from the seeds of lepidium apetalum and its estrogen-like effects in vitro and in vivo[J]. Molecules, 2018, 23(9): 2293. DOI: 10.3390/molecules23092293.

3.Xu HW, Du W, He L, et al. Effectiveness and safety of warm needle acupuncture on insomnia in climacteric women: protocol for a systematic review and Meta-analysis[J]. Medicine (Baltimore), 2019, 98(20): e15637.DOI: 10.1097/MD.0000000000015637.

4.Xue B, Chen X, Wang X, et al. Application of multivariate statistical analysis and network pharmacology to explore the mechanism of Danggui Liuhuang Tang in treating perimenopausal syndrome[J]. J Ethnopharmacol, 2022, 284: 114543. DOI: 10.1016/j.jep.2021.114543.

5.Kargozar R, Azizi H, Salari R. A review of effective herbal medicines in controlling menopausal symptoms[J]. Electron Physician, 2017, 9(11): 5826-5833. DOI: 10.19082/5826.

6.冯华. 健康教育对围绝经期综合征妇女的生活质量和心理状态的影响[J]. 世界最新医学信息文摘(连续型电子期刊), 2020, 20(41): 248, 250. [Feng H. The impact of health education on the quality of life and psychological status of women with perimenopausal syndrome[J]. World Latest Medicine Information (Electronic version), 2020, 20(41): 248, 250.] DOI: 10.13429/j.cnki.cjcr.2015.06.048.

7.Qin XY, Niu ZC, Han XL, et al. Anti-perimenopausal osteoporosis effects of Erzhi formula via regulation of bone resorption through osteoclast differentiation: a network pharmacology-integrated experimental study[J]. J Ethnopharmacol, 2021, 270: 113815. DOI: 10.1016/j.jep.2021.113815.

8.李文先, 曹秀菁. 中国妇幼健康的进展与成效[J]. 中华疾病控制杂志, 2022, 26(9): 993-995, 1107. [Li WX, Cao  XJ. Progress and effects of women and children's health in China[J]. Chinese Journal of Disease Control & Prevention, 2022, 26(9): 993-995, 1107.] DOI: 10.16462/j.cnki.zhjbkz. 2022.09.001.

9.Jordan MI, Mitchell TM. Machine learning: trends, perspectives, and prospects[J]. Science, 2015, 349(6245): 255-260. DOI: 10.1126/science.aaa8415.

10.Wang XX, Wang ZJ, Chen SC, et al. Risk prediction model of metabolic syndrome in perimenopausal women based on machine learning[J]. Int J Med Inform, 2024, 188: 105480. DOI: 10.1016/j.ijmedinf.2024.105480.

11.Ali MM, Algashamy HAA, Alzidi E, et al. Development and performance analysis of machine learning methods for predicting depression among menopausal women[J]. Healthcare Analytics, 2023, 3: 100202. DOI: 10.1016/j.health.2023.100202.

12.刘成伟, 徐黎贤, 朱其舟, 等. 南昌地区围绝经期女性健康状况与需求调查[J]. 江西医药, 2020, 55(7): 804-806. [Liu CW, Xu LX, Zhu QZ, et al. Health status and demand of perimenopausal women in Nanchang[J]. Jiangxi Medical Journal, 2020, 55(7): 804-806.] DOI: 10.3969/j.issn.1006-2238.2020.07.003.

13.中国医师协会全科医师分会, 北京妇产学会社区与基层分会. 更年期妇女健康管理专家共识(基层版)[J]. 中国全科医学, 2021, 24(11): 1317-1324. [Chinese Medical Doctor Association (CMDA)'s General Practitioners Sub-association, The Primary Care Branch of Beijing Institute of Obstetrics & Gynecology. Consensus on health management of climacteric women in primary medical institutions edition[J]. Chinese General Practice, 2021, 24(11): 1317-1324.] DOI: 10.12114/j.issn.1007- 9572.2021.00.402.

14.Tao MF, Shao HF, Li CB, et al. Correlation between the modified Kupperman index and the menopause rating scale in Chinese women[J]. Patient Prefer Adherence, 2013: 223-229. DOI: 10.2147/PPA.S42852.

15.国家药品监督管理局. 关于印发中药、天然药物治疗冠心病心绞痛和女性更年期综合征临床研究技术指导原则的通知[EB/OL]. (2011-07-08) [2024-08-01]. https://www.nmpa.gov.cn/directory/web/nmpa/xxgk/fgwj/gzwj/gzwjyp/20110708113101528_13.html.

16.Chawla NV, Bowyer KW, Hall LO, et al. SMOTE: synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research, 2002, 16: 341-378. DOI: 10.1613/jair.953.

17.Kursa MB, Jankowski A, Rudnicki WR. Boruta-a system for feature selection[J]. Fundam Informaticae, 2010, 101: 271-285. DOI: 10.3233/FI-2010-288.

18.Fryer D, Strümke I, Nguyen H. Shapley values for feature selection: the good, the bad, and the axioms[J]. IEEE Access, 2021, 9: 144352-144360. DOI: 10.1109/ACCESS.2021.3119110.

19.张倩, 刘筱茂, 张梅奎. 围绝经期失眠的发生机制与治疗进展[J]. 解放军医学院学报, 2023, 44(9): 1056-1059. [Zhang Q, Liu XM, Zhang MK. Pathogenesis and treatment progress of perimenopausal insomnia[J]. Academic Journal of Chinese PLA Medical School, 2023, 44(9): 1056-1059.] DOI: 10.12435/j.issn.2095-5227.2023.049.

20.胡波, 汤洪, 张新平. 围绝经期女性抑郁情绪与围绝经期症状的相关性研究[J]. 中国妇幼保健, 2020, 35(21): 4042-4045. [Hu B, Tang H, Zhang XP. Study on the correlation between depression and menopausal symptoms in menopausal women[J]. Maternal and Child Health Care of China, 2020, 35(21): 4042-4045.] DOI: 10.19829/j.zgfybj.issn.1001-4411.2020.21.045.

21.王洪雪, 王杰琼, 高杰. 中药治疗围绝经期综合征的机制研究[J]. 世界科学技术: 中医药现代化, 2020, 22(6): 1822-1827. [Wang HX, Wang JQ, Gao J. Study on the mechanism of Chinese medicine in treating perimenopausal syndrome[J]. Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology, 2020, 22(6): 1822-1827.] DOI: 10.11842/wst.20191010005.

22.Modzelewski S, Oracz A, Żukow X, et al. Premenstrual syndrome: new insights into etiology and review of treatment methods[J]. Front Psychiatry, 2024, 15: 1363875. DOI: 10.3389/fpsyt.2024.1363875.

23.叶萍萍. 运用"治未病"思想防治妇科病症经验举隅 [J]. 临床合理用药杂志, 2022, 15(8): 171-173, 177. [Ye PP. Examples of applying the concept of "treating before illness" to prevent and treat gynecological conditions[J]. Chinese Journal of Clinical Rational Drug Use, 2022, 15(8): 171-173, 177.] DOI: 10.15887/j.cnki. 13-1389/r.2022.08.053.

24.张竞, 阿地拉·阿里木, 郭艳英, 等. 乌鲁木齐市天山区维吾尔族女性围绝经期和绝经后期代谢综合征现况及危险因素分析[J]. 中华全科医学, 2023, 21(1): 73-76. [Zhang J, Adila A, Guo YY, et al. Prevalence and risk factors of metabolic syndrome among pre-menopausal and post-menopausal women of Uygur in Tianshan district of Urumqi[J]. Chinese Journal of General Practice, 2023, 21(1): 73-76.] DOI: 10.16766/j.cnki.issn.1674-4152. 002815.

25.刘红雪,郑建华,郁琦. 哈尔滨地区围绝经期女性健康现状及保健需求分析[J]. 现代生物医学进展, 2012, 12(21): 4065-4068, 4078. [Liu HX, Zheng JH, Yu  Q. Analysis of healthy conditions and healthcare service demand of perimenopausal women in Harbin[J]. Progress in Modern Biomedicine, 2012, 12(21): 4065-4068, 4078.] DOI: 10.13241/j.cnki.pmb.2012.21.026.

26.方梦辰, 张培珍. 运动对围绝经期和绝经后妇女心率变异性的调节[J]. 中南大学学报（医学版）, 2024, 49(4): 516-525. [Fang MC, Zhang PZ. Regulation of exercise on heart rate variability in perimenopausal and postmenopausal women[J]. Journal of Central South University (Medical Science), 2024, 49(4): 516-525.] DOI: 10.11817/j.issn.1672-7347.2024.230399.

27.江雪芳,田丰莲,黄晓晖,等. 围绝经期妇女运动对预防围绝经期综合征的影响[J]. 中国临床医学, 2004, 11(6): 1091-1092. [Jiang XF, Tian FL, Huang XH, et al. The study of the relationship between athletics and perimenopausal syndrome in Guangdong[J]. Chinese Journal of Clinical Medicine, 2004, 11(6): 1091-1092.] DOI: 10.3969/j.issn.1008-6358.2004.06.064.

28.李青,王艳娜,杨娜,等. 运动对女性围绝经期综合征影响的系统评价[J]. 中国老年学杂志, 2017, 37(19): 4875-4878. [Li Q, Wang YN, Yang N, et al. A systematic review of the effects of exercise on menopausal symptoms in women[J]. Chinese Journal of Gerontology, 2017, 37(19): 4875-4878.] DOI: 10.3969/j.issn.1005-9202.2017. 19.085.