Using Machine Learning to Identify the Dynamic Evolution Patterns of Negative Emotions in Perinatal Women: A Longitudinal Study in Southwest China

Abstract

Paying attention to the mental health of perinatal women is helpful in improving their quality of life. However, the existing research pays less attention to the heterogeneity of its negative emotional trajectory and the identification of high-risk groups. This study recruited 860 perinatal women from four large hospitals in Chongqing from March 2018 to January 2019. They were followed up by structured questionnaires in the first trimester, second trimester, third trimester, and about 6 weeks after delivery. The growth mixture model was used to analyze the developmental trajectory of negative emotions, and six machine learning algorithms were used to establish a high-risk negative emotion recognition model. The performance of the model was comprehensively evaluated by five performance indicators. The SHAP algorithm was used to explain the model. Negative emotional trajectories were divided into four categories: low-stable anxiety group, gradually increasing high-anxiety group, mild sustained depression group, and high-progressive depression group. The extreme gradient boosting model performed best, with the highest prediction performance score (24 points). In summary, the negative emotional trajectory of perinatal women is dynamic and heterogeneous, and the prediction model based on machine learning may play an important role in identifying high-risk negative emotions.

Keywords

longitudinal trajectory / machine learning / negative emotions / perinatal women / prediction

References

[1] Q. Shen, M. Xiao, B. Wang, T. He, J. Zhao, J. Lei, “Comorbid Anxiety and Depression Among Pregnant and Postpartum Women: A Longitudinal Population-Based Study,” Depression and Anxiety 2024 (2024): 7802142.

[2] J. Phillips, L. Sharpe, S. Matthey, “Rates of Depressive and Anxiety Disorders in a Residential Mother-Infant Unit for Unsettled Infants,” Australian and New Zealand Journal of Psychiatry 41, no. 10 (2007): 836-842.

[3] R. C. Kessler, N. A. Sampson, P. Berglund, et al., “Anxious and Non-Anxious Major Depressive Disorder in the World Health Organization World Mental Health Surveys,” Epidemiology Psychiatry Science 24, no. 3 (2015): 210-226.

[4] C. L. Dennis, K. Falah-Hassani, R. Shiri, “Prevalence of Antenatal and Postnatal Anxiety: Systematic Review and Meta-Analysis,” British Journal of Psychiatry 210, no. 5 (2017): 315-323.

[5] A. Roddy Mitchell, H. Gordon, J. Atkinson, “Prevalence of Perinatal Anxiety and Related Disorders in Low- and Middle-Income Countries: A Systematic Review and Meta-Analysis,” JAMA Network Open 6, no. 11 (2023): e2343711.

[6] X. Liu, S. Wang, G. Wang, “Prevalence and Risk Factors of Postpartum Depression in Women: A Systematic Review and Meta-analysis,” Journal of Clinical Nursing 31, no. 19-20 (2022): 2665-2677.

[7] A. Nisar, J. Yin, A. Waqas, et al., “Prevalence of Perinatal Depression and its Determinants in Mainland China: A Systematic Review and Meta-Analysis,” Journal of Affective Disorders 277 (2020): 1022-1037.

[8] Y. Zeng, “Exploration of Dance Function Under the Background of ‘Healthy China 2030’ -Taking Pregnant and Lying-in Women as an Example,” Chinese Dance Studies, no. 02 (2023): 211-25+352-53.

[9] C. E. Schwarze, S. von der Heiden, S. Wallwiener, S. Pauen, “The role of Perinatal Maternal Symptoms of Depression, Anxiety and Pregnancy-Specific Anxiety for Infant's Self-Regulation: A Prospective Longitudinal Study,” Journal of Affective Disorders 346 (2024): 144-153.

[10] R. G. Shah, C. M. Salafia, T. Girardi, et al., “Maternal Affective Symptoms and Sleep Quality have Sex-Specific Associations with Placental Topography,” Journal of Affective Disorders 360 (2024): 62-70.

[11] A. Sakowicz, E. Allen, M. Alvarado-Goldberg, W. A. Grobman, E. S. Miller, “Association Between Antenatal Depression Symptom Trajectories and Preterm Birth,” Obstetrics and Gynecology 141, no. 4 (2023): 810-817.

[12] J. Zhang, H. Lu, Q. Sheng, et al., “The Influence of Perinatal Psychological Changes on Infant Neurodevelopment in Shanghai, China: A Longitudinal Group-Based Trajectory Analysis,” Journal of Affective Disorders 361 (2024): 291-298.

[13] R. Feng, L. Liu. “Analysis of Anxiety and Depression Status and Influencing Factors of Women in Different Stages of Pregnancy,” Chinese Community Physicians 37, no.03: (2021): 38-39.

[14] S. Sade, E. Sheiner, I. Reuveni, G. Pariente, “Perinatal Outcome of Women With Maternal Antenatal Anxiety Hospitalized at High-Risk Pregnancy Departments,” American Journal of Obstetrics and Gynecology 226, no. 1 (2022): S119.

[15] J. S. McCall-Hosenfeld, K. Phiri, E. Schaefer, J. Zhu, K. Kjerulff, “Trajectories of Depressive Symptoms Throughout the Peri- and Postpartum Period: Results From the First Baby Study,” Journal of Women's Health (2002) 25, no. 11 (2016): 1112-1121.

[16] H. Lee, K. E. Kim, M. Y. Kim, C. G. Park, J. Y. Han, E. J. Choi, “Trajectories of Depressive Symptoms and Anxiety During Pregnancy and Associations With Pregnancy Stress,” International Journal of Environmental Research and Public Health 18, no. 5 (2021): 2733.

[17] L. M. Tomfohr, E. Buliga, N. L. Letourneau, T. S. Campbell, G. F. Giesbrecht. Trajectories of Sleep Quality and Associations with Mood During the Perinatal Period. Sleep 2015; 38(8): 1237-1245.

[18] Y. Gao, X. Tang, R. Deng, J. Liu, X. Zhong, “Latent Trajectories and Risk Factors of Prenatal Stress, Anxiety, and Depression in Southwestern China-A Longitudinal Study,” International Journal of Environmental Research and Public Health 20, no. 5 (2023): 3818.

[19] J. Yang, Y. Qu, Y. Zhan, et al., “Trajectories of Antepartum Depressive Symptoms and Birthweight: A Multicenter and Prospective Cohort Study,” Psychiatry and Clinical Neurosciences 77, no. 12 (2023): 631-637.

[20] A. Konnopka, H. König, “Economic Burden of Anxiety Disorders: A Systematic Review and Meta-Analysis,” Pharmacoeconomics 38, no. 1 (2020): 25-37.

[21] J. K. Hohls, H. H. König, Y. I. Raynik, A. Hajek, “A systematic Review of the Association of Anxiety with Health Care Utilization and Costs in People Aged 65 Years and Older,” Journal of Affective Disorders 232 (2018): 163-176.

[22] P. J. Tully, N. J. Harrison, P. Cheung, S. Cosh, “Anxiety and Cardiovascular Disease Risk: A Review,” Current Cardiology Reports 18, no. 12 (2016): 120.

[23] J. M. Rubio, M. Olfson, L. Villegas, G. Pérez-Fuentes, S. Wang, C. Blanco, “Quality of Life Following Remission of Mental Disorders: Findings from the National Epidemiologic Survey on Alcohol and Related Conditions,” Journal of Clinical Psychiatry 74, no. 5 (2013): e445-450.

[24] J. S. Comer, C. Blanco, D. S. Hasin, et al., “Health-Related Quality of Life Across the Anxiety Disorders: Results from the National Epidemiologic Survey on Alcohol and Related Conditions (NESARC),” Journal of Clinical Psychiatry 72, no. 1 (2011): 43-50.

[25] M. A. Hauken, M. Senneseth, A. Dyregrov, K. Dyregrov, “Anxiety and the Quality of Life of Children Living with Parental Cancer,” Cancer Nursing 41, no. 1 (2018): E19-e27.

[26] L. Zhang, X. Yang, J. Zhao, et al., “Prevalence of Prenatal Depression Among Pregnant Women and the Importance of Resilience: A Multi-Site Questionnaire-Based Survey in Mainland China,” Frontiers in Psychiatry 11 (2020): 374.

[27] L. Hong, T. Le, Y. Lu, et al., “Distinct Trajectories of Perinatal Depression in Chinese Women: Application of Latent Growth Mixture Modelling,” BMC Pregnancy Childbirth 22, no. 1 (2022): 24.

[28] A. C. Huizink, D. Lammassaari, S. Nolvi, et al., “Antecedents of Maternal Pregnancy-Related Anxiety Trajectories: The FinnBrain Birth Cohort Study,” Acta Psychiatrica Scandinavica 150, no. 5 (2024): 334-343.

[29] H. Bayrampour, S. McDonald, S. Tough, “Risk Factors of Transient and Persistent Anxiety During Pregnancy,” Midwifery 31, no. 6 (2015): 582-9.

[30] S. Y. Kuo, S. R. Chen, Y. L. Tzeng, “Depression and Anxiety Trajectories Among Women Who Undergo an Elective Cesarean Section,” PLoS ONE 9, no. 1 (2014): e86653.

[31] P. A. Mora, I. M. Bennett, I. T. Elo, L. Mathew, J. C. Coyne, J. F. Culhane, “Distinct Trajectories of Perinatal Depressive Symptomatology: Evidence from Growth Mixture Modeling,” American Journal of Epidemiology 169, no. 1 (2009): 24-32.

[32] A. L. Sutter-Dallay, O. Cosnefroy, E. Glatigny-Dallay, H. Verdoux, N. Rascle, “Evolution of Perinatal Depressive Symptoms from Pregnancy to Two Years Postpartum in a Low-Risk Sample: The MATQUID Cohort,” Journal of Affective Disorders 139, no. 1 (2012): 23-29.

[33] A. Ahmed, C. Feng, A. Bowen, N. Muhajarine, “Latent Trajectory Groups of Perinatal Depressive and Anxiety Symptoms from Pregnancy to Early Postpartum and Their Antenatal Risk Factors,” Archives of Women's Mental Health 21, no. 6 (2018): 689-698.

[34] X. Tang, Z. Lu, D. Hu, X. Zhong, “Influencing Factors for Prenatal Stress, Anxiety and Depression in Early Pregnancy Among Women in Chongqing, China,” Journal of Affective Disorders 253 (2019): 292-302.

[35] K. M. Krysko, A. Anderson, J. Singh, et al., “Risk Factors for Peripartum Depression in Women with Multiple Sclerosis,” Multiple Sclerosis 28, no. 6 (2022): 970-979.

[36] C. Garbazza, F. Mangili, T. A. D'Onofrio, “A Machine Learning Model to Predict the Risk of Perinatal Depression: Psychosocial and Sleep-Related Factors in the Life-ON Study Cohort,” Psychiatry Research 337 (2024): 115957.

[37] S. Yue, S. Li, X. Huang, et al., “Machine Learning for the Prediction of Acute Kidney Injury in Patients with Sepsis,” Journal of Translational Medicine 20, no. 1 (2022): 215.

[38] G. Castillo-Sánchez, G. Marques, E. Dorronzoro, O. Rivera-Romero, M. Franco-Martín, I. De la Torre-Díez, “Suicide Risk Assessment Using Machine Learning and Social Networks: A Scoping Review,” Journal of Medical Systems 44, no. 12 (2020): 205.

[39] X. Zhao, Y. Wang, J. Li, et al., “A Machine-Learning-Derived Online Prediction Model for Depression Risk in COPD Patients: A Retrospective Cohort Study from CHARLS,” Journal of Affective Disorders 377 (2025): 284-293.

[40] E. Hochman, B. Feldman, A. Weizman, et al., “Development and Validation of a Machine Learning-Based Postpartum Depression Prediction Model: A Nationwide Cohort Study,” Depression and Anxiety 38, no. 4 (2021): 400-411.

[41] S. Rallis, H. Skouteris, M. McCabe, J. Milgrom, “A Prospective Examination of Depression, Anxiety and Stress Throughout Pregnancy,” Women Birth 27, no. 4 (2014): e36-42.

[42] A. Hemmatipour, A. Honarmandpour, S. Asadi Chenareh, et al., “The Relationship of Health Literacy With General Health in Iranian Patients With Heart Disease Using the Structural Equation Modeling,” Journal of Preventive Medicine 10, no. 4 (2024): 374-85.

[43] H. G. Jeong, J. S. Lim, M. S. Lee, S. H. Kim, I. K. Jung, S. H. Joe, “The Association of Psychosocial Factors and Obstetric History with Depression in Pregnant Women: Focus on the Role of Emotional Support,” General Hospital Psychiatry 35, no. 4 (2013): 354-8.

[44] L. Giardinelli, A. Innocenti, L. Benni, et al., “Depression and Anxiety in Perinatal Period: Prevalence and Risk Factors in an Italian Sample,” Archives of Women's Mental Health 15, no. 1 (2012): 21-30.

[45] Ş. Kurtuluş, R. Can, Z. H. A. Sak, “Assessment of the Relationship Between Smoking and Depression in Pregnant Women,” Journal of Immigrant or Minority Health 23, no. 3 (2021): 536-546.

[46] R. P. Kolko, R. L. Emery, Y. Cheng, M. D. Levine, “Do Psychiatric Disorders or Measures of Distress Moderate Response to Postpartum Relapse Prevention Interventions?,” Nicotine & Tobacco Research 19, no. 5 (2017): 615-622.

[47] M. Hamilton, “The Assessment of Anxiety States by rating,” British Journal of Medical Psychology 32, no. 1 (1959): 50-55.

[48] W. W. Zung, “A Self-Rating Depression Scale,” Archives of General Psychiatry 12 (1965): 63-70.

[49] S. M. Coyne, L. M. Padilla-Walker, H. G. Holmgren, “A Six-Year Longitudinal Study of Texting Trajectories During Adolescence,” Child Development 89, no. 1 (2018): 58-65.

[50] N. Peiffer-Smadja, T. M. Rawson, R. Ahmad, et al., “Machine Learning for Clinical Decision Support in Infectious Diseases: A Narrative Review of Current Applications,” Clinical Microbiology and Infection 26, no. 5 (2020): 584-595.

[51] X. Bai, X. Luan, L. He, Y. Bi, T. Zhang, C. Sun, “Missing Value Interpolation of Medical Big Data Based on Missing Forest,” Journal of Jilin University 40, no. 04 (2022): 616-20.

[52] D. Dablain, B. Krawczyk, N. V. Chawla, “DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data,” IEEE Transactions on Neural Networks and Learning Systems 34, no. 9 (2023): 6390-6404.

[53] Y. Gao, Study on the Trajectory and Prediction Model of Prenatal Psychological Disorders in Pregnant Women (Chongqing Medical University, 2021).

[54] Y. Cui, X. Shi, S. Wang, et al. “Machine Learning Approaches for Prediction of Early Death among Lung Cancer Patients with Bone Metastases Using Routine Clinical Characteristics: An Analysis of 19,887 Patients,” Frontiers in Public Health 10, (2022): 1019168.

[55] M. Lei, B. Wu, Z. Zhang, et al., “A Web-Based Calculator to Predict Early Death Among Patients With Bone Metastasis Using Machine Learning Techniques: Development and Validation Study,” Journal of Medical Internet Research [Electronic Resource] 25 (2023): e47590.

RIGHTS & PERMISSIONS

2025 The Author(s). MedComm published by Sichuan International Medical Exchange & Promotion Association (SCIMEA) and John Wiley & Sons Australia, Ltd.