Analysis of the Factors Influencing Postpartum Depression via Logistic Regression and Decision Tree Models

Analysis of the Factors Influencing Postpartum Depression via Logistic Regression and Decision Tree Models | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Analysis of the Factors Influencing Postpartum Depression via Logistic Regression and Decision Tree Models Xin He, Bahedana Sailike, Xiaoting Wang, Sufeila Shalayiding, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7282695/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background To study the status of postpartum depression and its main influencing factors by using logistic regression and a decision tree model and to understand the psychological characteristics of puerperae to take targeted measures to improve their mental health level. Methods A general demographic data questionnaire, the Edinburgh Postnatal Depression Scale (EPDS), the Connor-Davidson Resilience Scale (CD-RISC), and the Perceived Social Support Scale (PSSS) were used to investigate 1536 parturients who came to the Child Health Care Department of a tertiary hospital in Urumqi for physical examination. Using binary classification and a logistic regression model based on the classification of the decision tree analysis of postpartum women, the CHAID algorithm was used to compare the factors influencing PPD and the differences between the two models. Results The results of the logistic regression analysis model and decision tree model revealed that the level of resilience, degree of social support, and pregnancy complications were the influencing factors of PPD ( P < 0. 05), among which resilience was the most important influencing factor. Conclusion Both models have predictive value for classification, and the logistic regression model is superior to the decision tree model in predicting PPD. However, both models have advantages and disadvantages and can complement each other to make the analysis results more practical. postpartum depression resilience social support logistic regression decision tree Figures Figure 1 Figure 2 Figure 3 Introduction Postpartum depression (PPD) is a serious perinatal mental health problem that has a profound impact [ 1 , 2 ]. The prevalence of PPD is estimated to be approximately 10–20% [ 3 , 4 ]. At present, the prevalence of PPD is gradually increasing [ 5 , 6 ]. The occurrence of postpartum depression is multifactorial and multifaceted, involving biology, psychology, social culture and other aspects [ 7 ]. Prenatal depression, childbirth experience, family support, the social environment, and other factors are closely related [ 8 , 9 ]. However, the mechanism of postpartum depression is not completely clear, and further research is needed to explore it in depth. PPD is different from other forms of depression and may affect a woman's mental status [ 10 ]. Postpartum, women experience great changes [ 11 ]. PPD not only poses a threat to maternal physical and mental health but also may have a long-term impact [ 12 , 13 ]. Pregnant women who have experienced PPD for a long time often suffer from periodic distress of depression, which has adverse effects [ 14 , 15 ], even leading to self-harm, suicide or infanticide. Therefore, the postpartum period needs to receive increased attention. Therefore, identifying the risk factors for postpartum depression is highly important for the prevention and intervention of this disease. With the development of big data and machine learning technology, statistical and machine learning methods such as logistic regression and decision tree models have been widely used in the field of medical research, especially in the analysis of disease risk factors, which have shown their unique advantages [ 16 ]. Logistic regression models are widely used in binary classification problems because of their simplicity and ease of interpretation. However, the decision tree model has strong prediction performance in classification problems because of its intuitive dendrogram structure and nonlinear processing ability. Therefore, this study plans to use a logistic regression model and a classification decision tree model to explore the risk factors for postpartum depression and integrate the analysis results of the two models to provide a theoretical basis for improving the mental health status and quality of life of postpartum women. Methods Sample From August 2023 to August 2024, convenience sampling was used to enroll newborns and their mothers for physical examination in the Department of Child Health Care of a Class ⅲ Grade A hospital in Urumqi for a questionnaire survey. The inclusion criteria were as follows: offspring aged ≤ 1 year; maternal age ≥ 18 years; ability to understand the content of the questionnaire correctly and complete it independently; and informed consent and willingness to coopera with all respondents. The exclusion criteria were as follows: severe mental disorders, cognitive impairment, hearing impairment, language communication disorders, and limited ability to understand who could not complete the survey; refusal to cooperate with the investigation after explanation; and incomplete data collection. An onsite questionnaire survey was conducted by the investigators with the parturients who met the inclusion and exclusion criteria, and the parturients were instructed to complete the questionnaire independently. In this study, a total of 1635 parturients were investigated. After all the questionnaires were checked, unqualified questionnaires, such as irregular questionnaires and incorrect questionnaires, were excluded. Finally, 1536 valid questionnaires were collected, for an effective response rate of 94%. This study was approved by the Ethics Committee of Xinjiang Medical University (Ethics approval number: XJYKDXR20230303023). Measurement tools Questionnaire on maternal and neonatal general conditions A self-designed general information questionnaire was used. Maternal general demographic characteristics (age, education level, occupation, etc.), maternal delivery history (gestational age, delivery mode, postpartum hemorrhage, pregnancy complications, etc.), living environment, and neonatal general demographic characteristics (neonatal sex, birth weight, birth asphyxia, birth diseases, etc.) were collected. Edinburgh Postnatal Depression Scale (EPDS) The EPDS was developed by Cox et al [ 17 ]. The EPDS consists of 10 items and is scored on a four-point Likert scale, with higher scores indicating more clinically severe depressive symptoms. In this study, an EPDS score ≥ 9 was used as the criterion [ 18 ]. The scale has good reliability and validity [ 19 ] in the evaluation of postpartum depression in pregnant women. The Cronbach's α coefficient of the scale in this study was 0.881. Connor-Davidson Resilience Scale (CD-RISC) The Chinese version of the CD-RISC was translated and revised by Xiao Nan and Zhang Jianxin [ 20 ]. The scale consists of three dimensions, which are scored from 0 to 4. The total score on the scale is 100, and the higher the score is, the stronger the psychological resilience is. The Cronbach's α coefficient of the scale in this study was 0.968. Perceived Social Support Scale (PSSS) The scale was developed by Zimet [ 21 ]. The Cronbach's α coefficient of the scale in this study was 0.97. Statistical analysis In this study, the data were analysed via SPSS 26.0. The normally distributed data are described as ± s, and the nonnormally distributed data are expressed as medians (quartiles). Two independent sample \(\:\stackrel{-}{\text{x}}\) t tests were used to compare the means of the two groups of normally distributed and homogeneous variance data, and nonparametric tests were used for statistical analysis. The count data are presented as frequencies and constituent ratios, and the chi-square test was used for statistical analysis. All significant factors in the univariate analysis were included in the logistic regression model. The CHAID algorithm was used to construct a classification decision tree model to screen variables. A decision tree is a classification and regression method with a tree structure that is composed of decision nodes, branches, and leaves. The top node is the root node. Each branch is a new decision node or a leaf of the tree, representing a test output, and each leaf represents a possible classification result. Each branch is a new decision node or leaf, which represents a test output, and each leaf node represents a possible classification result. Since the sample size decreases with the growth of the decision tree, the prepruning technique is used to control the sufficient growth of the decision tree: the minimum sample contents in the parent node and child node are 100 and 50, respectively, and the maximum tree depth is 3. The ROC curve was drawn according to the prediction results of the two models, and the differences between the two models were analysed and compared. The test level was α = 0.05. Results Maternal and newborn general demographic data A total of 1536 puerperae participated in the survey, and 527 puerperae were diagnosed with PPD, for a detection rate of 34.31%. Among the enrolled women, 54.69% (840) were undergraduates, 83.79% (1287) were 25–35 years old, and 94.27% (1448) were urban residents. The group with a household income above 8001 yuan accounted for the highest proportion, accounting for 42.45% (652), and the group with a household income between 5001 and 8000 yuan accounted for 33.53% (515). Working women accounted for 77.41% (1189) of the sample. The reproductive history revealed that the primipara accounted for 65.43% (1005) of the population, and the cesarean section rate was 71.09% (1092). The highest proportion of newborns with weights in the range of 2.5–4 kg was 84.64% (1300 cases), and boys accounted for 53.06% (815 cases). The results of the univariate analysis revealed that maternal depression differed with gestational age, delivery mode, living environment, pregnancy complications, neonatal birth weight, delivery type, neonatal asphyxia, neonatal diseases, psychological resilience, and social support (P < 0.05). Table 1 is shown. Table 1 Univariate analysis of risk factors for PPD [n = 1536,n(%)]. Project Whether PPD(%) χ 2 value P- value Normal Depression Age groups 35 147 (14.57) 67 (12.71) Level of education Less than high school 45 (4.46) 31 (5.88) 5.649 0.130 High school and junior college 258 (25.57) 157 (29.79) Undergraduate 571 (56.59) 269 (51.04) Master's degree or above 135 (13.38) 70 (13.28) Place to live Rural 59 (5.85) 29 (5.50) 0.076 0.783 City 950 (94.15) 498 (94.50) Total monthly household income Under 3,000 50 (4.96) 25 (4.74) 5.667 0.129 30001 − 5000 179 (17.74) 115 (21.82) 5001–8000 333 (33.00) 182 (34.54) 8001 + 447 (44.30) 205 (38.90) Occupation Career women 792 (78.49) 397 (75.33) 1.979 0.160 Unemployed or unemployed 217 (21.51) 130 (24.67) Gestational age at delivery = 38 782 (77.50) 377 (71.54) Mode of delivery Natural birth 312 (30.92) 132 (25.05) 5.813 0.016 Cesarean section 697 (69.08) 395 (74.95) Living environment Good 795 (78.79) 382 (72.49) 9.208 0.010 Average 209 (20.71) 144 (27.32) poor 5 (0.50) 1 (0.19) Number of pregnancies 1 pregnancy 653 (64.72) 352 (66.79) 0.763 0.683 2 pregnancies 241 (23.89) 116 (22.01) More than 3 pregnancies 115 (11.40) 59 (11.20) Presence or absence of pregnancy complications yes 766 (75.92) 353 (66.98) 13.970 < 0.001 no 243 (24.08) 174 (33.02) Newborn birth weight < 2.5 kg 67 (6.64) 69 (13.09) 19.196 4 kg 62 (6.14) 38 (7.21) Type of delivery Full term delivery 898 (89.00) 430 (81.59) 16.363 < 0.001 Premature birth 98 (9.71) 84 (15.94) Expired production 13 (1.29) 13 (2.47) Whether there is neonatal asphyxia yes 30 (2.97) 34 (6.45) 10.490 < 0.001 no 979 (97.03) 493 (93.55) Presence of birth defects no 1002 (99.31) 518 (98.29) 3.453 0.063 yes 7 (0.69) 9 (1.71) Presence or absence of a neonatal illness no 987 (97.82) 503 (95.45) 6.714 0.010 yes 22 (2.18) 24 (4.55) Degree of mental resilience Low level 114 (11.30) 187 (35.48) 230.385 < 0.001 Medium level 193 (19.13) 180 (34.16) High level 702 (69.57) 160 (30.36) Degree of social support Low level 9 (0.89) 10 (1.90) 121.965 < 0.001 Medium level 173 (17.15) 224 (42.50) High level 827 (81.96) 293 (55.60) Logistic regression analysis of influencing factors of postpartum depression With the presence of PPD (0 = no, 1 = yes) as the dependent variable, according to the results of univariate analysis, the living environment, gestational age at delivery, delivery mode, pregnancy complications, neonatal birth weight, delivery type, neonatal asphyxia, neonatal diseases, psychological resilience, and social support were included in logistic regression analysis. The results revealed that the lower the level of social support was (compared with the high level of social support, the OR value of the middle level of social support was 1.949), the lower the level of psychological resilience was (compared with the high level of psychological resilience, the lower the level of psychological resilience was, the lower the level of psychological resilience was, the lower the level of social support was, and the higher the level of psychological resilience was, the lower the level of psychological resilience was). The OR values of the low and medium levels of psychological resilience were 5.091 and 3.595, respectively. Pregnancy complications (OR = 1.356) and cesarean section (OR = 1.406) were risk factors for PDD. No neonatal asphyxia (OR = 0.524) or birth weight of 2.5–4 kg (OR = 0.593) were protective factors against PPD. The living environment, gestational age at delivery, mode of delivery, type of delivery, and presence of neonatal diseases did not affect the occurrence of PPD. See Fig. 1 . Decision tree analysis of influencing factors of postpartum depression In this study, the decision tree was grown into three levels and a total of seven end nodes. A total of four influencing factors were identified, including psychological resilience, social support, pregnancy complications and delivery mode. The root node was psychological resilience, which showed that psychological resilience had the highest correlation with PPD in perinatal women. With the decrease in psychological resilience, the rate of postpartum depression tended to increase. See Fig. 2 . Comparison of the analysis results of the two models The results of the two models revealed that psychological resilience, social support, and pregnancy complications were the influencing factors of PPD. There were no significant differences in living environment, gestational age at delivery, mode of delivery, birth weight, type of delivery, neonatal asphyxia, or neonatal diseases. The receiver operating characteristic (ROC) curves of the two models were plotted. The AUC of the two models was > 0.5, indicating that the models had a good prediction effect. The ROC curves of the two models were similar, indicating that the classification effects of the two models were similar, but there were also some differences between the two models. The influencing factors of the logistic regression model, birth weight and the presence of neonatal asphyxia, were excluded from the classification decision tree model. See Fig. 3 . The AUC of the logistic regression model was 0.754 (95% CI: 0.728–0.780), the specificity was 72%, and the sensitivity was 70.2%. The AUC of the classification decision tree model was 0.738 (95% CI: 0.711–0.765), the specificity was 69.6%, and the sensitivity was 69.6%. Both P values of the two models were < 0.001, indicating that the classification effects of the two models were of practical significance. The AUC values of the two models were greater than 0.7, indicating that the classification prediction results of the two models had a certain accuracy. In general, although the classification performance of the two models was similar, the classification decision tree model had lower specificity and sensitivity than did the logistic regression model, and the prediction performance of the logistic regression model was better than that of the classification decision tree model.See Table 2 . Table 2 Comparison of the classification effects of the logistic regression model and classification decision tree model Models AUC Standard error 95% CI Sensitivity (%) Specificity (%) Youden index Logistic regression 0.754 0.013 [0.728, 0.780] 0.702 0.720 0.470 Classification decision tree 0.738 0.014 [0.711, 0.765] 0.696 0.696 0.439 Discussion With the increasing importance of mental health in society, postpartum depression has become a common concern [ 22 ]. Postpartum depression is a common and serious psychological disorder [ 23 – 25 ]. Domestic and foreign scholars have performed many studies [ 26 ], It has been shown to be closely related to a variety of factors, including physiological changes after childbirth [ 27 ]、 rapid change of role [ 28 ] 、parenting stress, inadequate family support, past history of mental illness, and socioeconomic status [ 29 ]. Therefore, for postpartum depression, we need to take comprehensive intervention measures, including strengthening the popularization of postpartum mental health knowledge, providing personalized psychological counselling services, strengthening the family and social support system, identifying and treating potential mental health problems in time, and optimizing the postpartum medical service process, to effectively reduce the incidence of postpartum depression. To protect maternal mental health, the healthy development of mother–infant relationships should be promoted, and a more harmonious family and social environment should be built. The detection rate of PPD was 34.31% among 1536 pregnant women, which was higher than the average level [ 30 ]. This difference may be due to differences in culture, economy, customs, lifestyle, and medical conditions across regions, which may affect the psychological state [ 31 ]. At the same time, families facing greater economic pressure may face more life troubles [ 32 ], such as child care costs, career development and other issues, thus increasing the psychological burden on parturients. Postpartum depression not only is a serious threat to maternal physical and mental health but also may have adverse effects [ 33 ] on the growth environment of infants, the family atmosphere, and even wider society. The results of this study revealed that the detection rate of PPD differed across the different resilience groups, that the level of resilience group was greater than the high level of resilience group was, and that resilience had the greatest influence on PPD, which was consistent [ 34 ] with the positive psychological traits of individuals in the face of adversity. Psychological resilience is a protective factor [ 35 ]. Resilience partially mediates [ 36 ] the relationship between postpartum negative life events and postpartum depression. Women with a greater degree of psychological resilience are better able to effectively buffer the adverse effects of postpartum negative life events and highlight and strengthen their advantages to avoid negative emotions. The results of this study suggest that the impact of postpartum negative life events can be reduced by increasing the level of psychological resilience of parturients and improving their adaptability to cope with adverse life events. To stimulate positive emotions in parturients and actively face postpartum personal and environmental changes, the incidence of PPD should be reduced. In addition, this study revealed that social support was also an important protective factor for maternal mental health, suggesting that providing adequate social support for women during puerperium helps them relieve stress and reduce its occurrence [ 37 , 38 ]. During puerperium, family members, especially husbands, should provide more care and support to puerperae, understand their physical and mental changes after childbirth, and shoulder the responsibility of parenting together. The ability of a puerpera to find a sense of belonging to the family during the puerpera can enhance the anti-stress ability of the puerpera to relieve their negative mood [ 39 ]. Social support plays an important role in preventing and treating postpartum depression [ 40 ]. Therefore, measures such as strengthening family support, establishing a community support network, providing professional psychological support, and improving the social security system can effectively improve the level of social support and reduce the risk of postpartum depression. The effect of delivery mode on the development of PPD has been widely studied [ 41 , 42 ]. The results of this study revealed that the incidence of PPD in this study was as high as 36.17%, and CS was a risk factor for PPD. Although this delivery method can reduce pain during childbirth, it is difficult to recover quickly after the operation because of the high degree of psychological pressure and the difficulty of movement and feeding, which increases the possibility of postpartum depression. The release of cortisol (a stress hormone) is greater during cesarean section, and the stress of cesarean section is more likely to induce mild or moderate PPD [ 30 ]. One study suggested that the link between high cortisol levels caused by surgical stress and PPD may be related [ 43 , 44 ]. To ensure that women with C-sections have rapid access to mental health care, the progression of postpartum mental disorders should be carefully monitored; therefore, comprehensive maternal interventions should be intensified to reduce the likelihood of postpartum depression. This study also revealed that the presence of pregnancy complications is a risk factor for PPD, and women with pregnancy complications are more likely to have depression. The results of Zhang Yan et al [ 45 ] suggested that attention should be given to screening for depression in the process of perinatal health care, and women with high-risk factors should be guided to correctly view the impact of high-risk factors to prevent or reduce the occurrence of depression. Limitations First, some statistically significant factors in the logistic regression model were not included in the decision tree model, which may be due to the limitation of sample size, especially the sample size at each node and the depth of the decision tree. The influence of these variables on PPD may not be revealed until later in the decision tree. In addition, although these variables have a certain influence on postpartum depression in perinatal women, their effect may be relatively weak compared with that of other variables, and they may be misjudged as interfering factors and excluded from the data analysis. Second, the measurement of postpartum depression relied only on scales and did not involve professional psychiatric interviews, so the outcome measures reflected only maternal depressive emotional problems rather than formal psychiatric diagnoses of depression or anxiety. These data were obtained through self-report questionnaires and may be subject to recall bias, which may affect the accuracy of the results. Moreover, this study used a cross-sectional study design, which makes it difficult to accurately determine causality compared with a cohort study design. Finally, this study used a convenient sampling method, which may cause sample bias, resulting in underrepresentation of the sample size. In conclusion, future studies should design larger-scale and more complete research protocols to assess the influencing factors of PPD more accurately and provide a solid theoretical basis for improving the adverse mood of parturients. Declarations Acknowledgements We are grateful to all the families and pregnant women for their participation. Author contributions Study design and manuscript drafting by Xin He. Data collection by Bahedana Sailike, Xiaoting Wang, Sufeila Shalayiding, and Meng Weicui. Data analysis and interpretation: Xin He, Bahedana Sailike, Xiaoting Wang, Sufeila Shalayiding, and Meng Weicui. Critical revision of the manuscript by Ting Jiang. All the authors approved the final version for publication. Funding This study was supported by the Xinjiang Uygur Autonomous Region “14th Five-Year Plan” Higher Education School Characteristic Discipline of Public Health and Preventive Medicine, the National Natural Science Foundation of China (82360669) and the Key Laboratory of Population Health and Eugenics of Anhui Province (JKYS20231). Data availability Thank you very much for the editor’s attention and recognition of our research work. We appreciate the BMC Public Health journal’s requirements for data sharing; however, because our data involve the privacy of maternal and we have entered into a relevant confidentiality agreement, we may not be able to provide the raw data. We have fully described the study design, analyses and results, as well as the process of data analysis and processing. Researchers seeking access to anonymous portions of the data may contact the corresponding author, Ting Jiang (Email: [email protected] ). Requests will be reviewed on a case-by-case basis, and approved applicants will receive data in accordance with the terms of the ethical approval and confidentiality agreements. Human ethics and consent to participate Informed consent was obtained from each participant. In accordance with the principles of the Declaration of Helsinki, this study was approved by the Ethics Committee of Xinjiang Medical University (approval number: XJYKDXR20230303023). Consent for publication Not applicable. Competing interests The authors declare that they have no competing interests. References Byatt N, Brenckle L, Sankaran P, et al. Effectiveness of two systems-level interventions to address perinatal depression in obstetric settings (PRISM): An active-controlled cluster-randomised trial. Lancet Public Health. 2024;9:e35–46. Hu N, Luo J, Xiang W, et al. The relationship between postpartum negative life events and postpartum depression: A moderated mediation model of neuroticism and psychological flexibility. BMC Psychiatry. 2024;24:147. Underwood L, Waldie K, D’Souza S, et al. A review of longitudinal studies on antenatal and postnatal depression. Arch Womens Ment Health. 2016;19:711–20. Rogers A, Obst S, Teague SJ, et al. Association between maternal perinatal depression and anxiety and child and adolescent development: A meta-analysis. JAMA Pediatr. 2020;174:1082–92. Kuehner C. Why is depression more common among women than among men? Lancet Psychiatry. 2017;4:146–58. McHenry J, Carrier N, Hull E, et al. Sex differences in anxiety and depression: Role of testosterone. Front Neuroendocrinol. 2014;35:42–57. Lamus MN, Pabon S, MPoca C, et al. Giving women WOICE postpartum: Prevalence of maternal morbidity in high-risk pregnancies using the WHO-WOICE instrument. BMC PREGNANCY CHILDBIRTH. 2021;21:357. Payne JL, Maguire J. Pathophysiological mechanisms implicated in postpartum depression. Front Neuroendocrinol. 2019;52:165–80. Obrochta CA, Chambers C, Bandoli G. Psychological distress in pregnancy and postpartum. Women Birth J Aust Coll Midwives. 2020;33:583–91. Yaqoob H, Ju X-D, Bibi M, et al. a systematic review of risk factors of postpartum depression. Evidence from asian culture . Acta Psychol (Amst). 2024;249:104436. Hagatulah N, Bränn E, Oberg AS, et al. Perinatal depression and risk of mortality: Nationwide, register based study in sweden. BMJ. 2024;384:e075462. Gopalan P, Spada ML, Shenai N, et al. Postpartum depression-identifying risk and access to intervention. Curr Psychiatry Rep. 2022;24:889–96. Grissette BG, Spratling R, Aycock DM. Barriers to help-seeking behavior among women with postpartum depression. J Obstet Gynecol Neonatal Nurs JOGNN. 2018;47:812–9. Pugliese V, Bruni A, Carbone EA, et al. Maternal stress, prenatal medical illnesses and obstetric complications: Risk factors for schizophrenia spectrum disorder, bipolar disorder and major depressive disorder. Psychiatry Res. 2019;271:23–30. Moore Simas TA, Flynn MP, Kroll-Desrosiers AR, et al. A systematic review of integrated care interventions addressing perinatal depression care in ambulatory obstetric care settings. Clin Obstet Gynecol. 2018;61:573–90. Kim K-M, Kim J-H, Rhee H-S, et al. Development of a prediction model for the depression level of the elderly in low-income households: Using decision trees, logistic regression, neural networks, and random forest. Sci Rep. 2023;13:11473. Cox JL, Holden JM, Sagovsky R. Detection of postnatal depression. Development of the 10-item edinburgh postnatal depression scale. Br J Psychiatry J Ment Sci. 1987;150:782–6. Gibson J, McKenzie-McHarg K, Shakespeare J, et al. A systematic review of studies validating the edinburgh postnatal depression scale in antepartum and postpartum women. Acta Psychiatr Scand. 2009;119:350–64. Xiao Julan, Wen Yi, Luo Weixiang, et al. Reliability and validity test of the Chinese version of the Edinburgh Postpartum Depression Scale in pregnant women. Modern Preventive Medicine. 2022; 49:3320–5. Yu X, Zhang J. Factor analysis and psychometric evaluation of the connor-davidson resilience scale (cd-risc) with Chinese people. Soc Behav Personal Int J. 2007;35:19–30. SCohen S, Matthews KA. Social support, type a behavior, and coronary artery disease. Psychosom Med. 1987;49:325–30. Hou Juan, Jia Keke, Fang Xiaoyi. The development trend and social changes of marital satisfaction between Chinese couples in the past 20 years. Acta Psychologica Sinica. 2024; 56:895–915. Chen Q, Li W, Xiong J, et al. Prevalence and risk factors associated with postpartum depression during the COVID-19 pandemic: A literature review and meta-analysis. Int J Environ Res Public Health. 2022;19:2219. Sun R, Zhao M, Ma L, et al. High psychological stress levels related to delivery can increase the occurrence of postpartum mental disorders. Front Psychiatry. 2023;14:1273647. Pearlstein T, Howard M, Salisbury A, et al. Postpartum depression. Am J Obstet Gynecol. 2009;200:357–64. Hirose A, Terauchi M, Odai T, et al. Postpartum hair loss is associated with anxiety. J Obstet Gynaecol Res. 2024;50:2239–45. Paria A, Atallah A, Nourredine M, et al. Early detection of perinatal depression in couples: A single-center prospective study. Eur Psychiatry J Assoc Eur Psychiatr. 2024;67:e48. Garnacho-Garnacho VE, Rodríguez-López ES, Oliva-Pascual-Vaca Á, et al. Maternal psychological well-being as a protector in infantile colic. Nutrients. 2024;16:2342. Stewart DE, Vigod SN. Postpartum depression: Pathophysiology, treatment, and emerging therapeutics. Annu Rev Med. 2019;70:183–96. Dai Xuemei. Postpartum depression is associated with different modes of delivery. Journal of Mudanjiang Medical College. 2019; 40:75–6, 150. Thornton BM. The effects of spiritual, religious, and psychological coping during pregnancy on post-pregnancy health outcomes. 2024. Hahn-Holbrook J, Cornwell-Hinrichs T, Anaya I. Economic and health predictors of national postpartum depression prevalence: A systematic review, meta-analysis, and meta-regression of 291 studies from 56 countries. Front Psychiatry. 2017;8:248. Matsunaga M, Okajima J, Furutani K, et al. Associations of rumination, behavioral activation, and perceived reward with mothers’ postpartum depression during the COVID-19 pandemic: A cross-sectional study. Front Psychiatry. 2024;15:1295988. Baattaiah BA, Alharbi MD, Babteen NM, et al. The relationship between fatigue, sleep quality, resilience, and the risk of postpartum depression: An emphasis on maternal mental health. BMC Psychol. 2023;11:10. Yuping Zhou, Fanyan Huang, Yuqi Chen, et al. Postpartum depression and psychological resilience in women and their spouses are subject-object interdependent. Military nursing. 2023; 40:10–3. Shumin Zhang, Qian Wei, Yunhui Zhang, et al. Mediating and moderating effects of maternal resilience of postpartum depression symptoms on parent-child interaction in early infancy. Chinese Journal of Public Health. 2023; 39:212–8. Zhuang Youqing, Jiang Cuiting, Zeng Liling, et al. The mediating effect of maternal resilience on the relationship between postpartum negative life events and postpartum depression. PLA Journal of Nursing. 2021; 38:18–21. Zhang Y, Jin S. The impact of social support on postpartum depression: The mediator role of self-efficacy. J Health Psychol. 2016;21:720–6. Cho H, Lee K, Choi E, et al. Association between social support and postpartum depression. Sci Rep. 2022;12:3128. Dagher RK, Bruckheim HE, Colpe LJ, et al. Perinatal depression: Challenges and opportunities. J Womens Health 2002. 2021;30:154–9. Van Sieleghem S, Danckaerts M, Rieken R, et al. Childbirth related PTSD and its association with infant outcome: A systematic review. Early Hum Dev. 2022;174:105667. Rauh C, Beetz A, Burger P, et al. Delivery mode and the course of pre- and postpartum depression. Arch Gynecol Obstet. 2012;286:1407–12. Dinan TG. Glucocorticoids and the genesis of depressive illness. A psychobiological model. Br J Psychiatry J Ment Sci. 1994;164:365–71. Edwards DR, Porter SA, Stein GS. A pilot study of postnatal depression following caesarean section using two retrospective self-rating instruments. J Psychosom Res. 1994;38:111–7. Zhang Yan, Weng Xueling, Qi Xiaochen. Research on the application effect of clinical pathways in the nursing of gestational diabetes mellitus. Journal of Practical Gynecologic Endocrinology (electronic version). 2018; 5:109–10. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7282695","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":502710608,"identity":"8467a1ea-49f7-40a7-b359-5dd67cd36a69","order_by":0,"name":"Xin He","email":"","orcid":"","institution":"Xinjiang Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"He","suffix":""},{"id":502710609,"identity":"9c54b742-7f1d-4b33-9f0a-178fa0917046","order_by":1,"name":"Bahedana Sailike","email":"","orcid":"","institution":"Xinjiang Medical University","correspondingAuthor":false,"prefix":"","firstName":"Bahedana","middleName":"","lastName":"Sailike","suffix":""},{"id":502710610,"identity":"efcb5848-9922-4e3f-8c5a-e49b5b45872f","order_by":2,"name":"Xiaoting Wang","email":"","orcid":"","institution":"Xinjiang Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xiaoting","middleName":"","lastName":"Wang","suffix":""},{"id":502710611,"identity":"dcd2bde1-4631-47a2-b2d1-c397d701b8db","order_by":3,"name":"Sufeila Shalayiding","email":"","orcid":"","institution":"Xinjiang Medical University","correspondingAuthor":false,"prefix":"","firstName":"Sufeila","middleName":"","lastName":"Shalayiding","suffix":""},{"id":502710612,"identity":"f0399b00-50c5-443d-8869-ca91c526b891","order_by":4,"name":"Weicui Meng","email":"","orcid":"","institution":"Xinjiang Medical University","correspondingAuthor":false,"prefix":"","firstName":"Weicui","middleName":"","lastName":"Meng","suffix":""},{"id":502710613,"identity":"0770a836-7a07-4a81-aa3f-8eeaabe4b323","order_by":5,"name":"Ting Jiang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAtklEQVRIiWNgGAWjYBACxgb+5x8+/LDh4WdvIFZLGw8b48yeNBnJngPEWsPGw8bMw3bYxuCGA5E6mOf3Hns4g+c8D8MNBsYPH3OIchhfusEHi9s8jLMbmCVnbiNKC4OB5Aye2zzMMgfYmHmJ1SLNw3aOh00igWgtPGZALQd4eEjQkpZsOLMnmUeC52AzcX4xbD588MGHH3b29sebD374SJSWBoSFDThVoQB54pSNglEwCkbBiAYAw4s0ORPFoHEAAAAASUVORK5CYII=","orcid":"","institution":"Xinjiang Medical University","correspondingAuthor":true,"prefix":"","firstName":"Ting","middleName":"","lastName":"Jiang","suffix":""}],"badges":[],"createdAt":"2025-08-03 10:23:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7282695/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7282695/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":89566365,"identity":"7f8ef62d-1f8b-42fc-b0d8-bb47f572cdc4","added_by":"auto","created_at":"2025-08-21 10:59:08","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":45879,"visible":true,"origin":"","legend":"\u003cp\u003eForest plot of logistic regression analysis of influencing factors for postpartum depression\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7282695/v1/feae55ace8bfb12c45ac1ee0.png"},{"id":89566366,"identity":"ffa66941-f508-470b-9f7c-5621cee6fa72","added_by":"auto","created_at":"2025-08-21 10:59:08","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":15125,"visible":true,"origin":"","legend":"\u003cp\u003eDecision tree analysis of influencing factors for postpartum depression\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7282695/v1/d09e77f6c8288b6f9e85a0fc.png"},{"id":89566370,"identity":"0cc6c5d0-c590-4d98-a06a-821ed27c1cb6","added_by":"auto","created_at":"2025-08-21 10:59:08","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":259344,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eROC curves of the logistic regression model and the classification decision tree model\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7282695/v1/ac31f235a1e0ac580eb7a391.png"},{"id":98779063,"identity":"ce8c27a2-c4f5-4ec7-b6ca-0a8a443d39ed","added_by":"auto","created_at":"2025-12-22 12:29:56","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1158541,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7282695/v1/bb4def89-5085-4c08-90e5-a070f55bff6c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Analysis of the Factors Influencing Postpartum Depression via Logistic Regression and Decision Tree Models","fulltext":[{"header":"Introduction","content":"\u003cp\u003ePostpartum depression (PPD) is a serious perinatal mental health problem that has a profound impact [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. The prevalence of PPD is estimated to be approximately 10\u0026ndash;20% [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e, \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. At present, the prevalence of PPD is gradually increasing [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. The occurrence of postpartum depression is multifactorial and multifaceted, involving biology, psychology, social culture and other aspects [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. Prenatal depression, childbirth experience, family support, the social environment, and other factors are closely related [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e, \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. However, the mechanism of postpartum depression is not completely clear, and further research is needed to explore it in depth.\u003c/p\u003e\u003cp\u003ePPD is different from other forms of depression and may affect a woman's mental status [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. Postpartum, women experience great changes [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. PPD not only poses a threat to maternal physical and mental health but also may have a long-term impact [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e, \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. Pregnant women who have experienced PPD for a long time often suffer from periodic distress of depression, which has adverse effects [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e, \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e], even leading to self-harm, suicide or infanticide. Therefore, the postpartum period needs to receive increased attention. Therefore, identifying the risk factors for postpartum depression is highly important for the prevention and intervention of this disease.\u003c/p\u003e\u003cp\u003eWith the development of big data and machine learning technology, statistical and machine learning methods such as logistic regression and decision tree models have been widely used in the field of medical research, especially in the analysis of disease risk factors, which have shown their unique advantages [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. Logistic regression models are widely used in binary classification problems because of their simplicity and ease of interpretation. However, the decision tree model has strong prediction performance in classification problems because of its intuitive dendrogram structure and nonlinear processing ability. Therefore, this study plans to use a logistic regression model and a classification decision tree model to explore the risk factors for postpartum depression and integrate the analysis results of the two models to provide a theoretical basis for improving the mental health status and quality of life of postpartum women.\u003c/p\u003e"},{"header":"Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003eSample\u003c/h2\u003e\u003cp\u003eFrom August 2023 to August 2024, convenience sampling was used to enroll newborns and their mothers for physical examination in the Department of Child Health Care of a Class ⅲ Grade A hospital in Urumqi for a questionnaire survey. The inclusion criteria were as follows: offspring aged\u0026thinsp;\u0026le;\u0026thinsp;1 year; maternal age\u0026thinsp;\u0026ge;\u0026thinsp;18 years; ability to understand the content of the questionnaire correctly and complete it independently; and informed consent and willingness to coopera with all respondents. The exclusion criteria were as follows: severe mental disorders, cognitive impairment, hearing impairment, language communication disorders, and limited ability to understand who could not complete the survey; refusal to cooperate with the investigation after explanation; and incomplete data collection. An onsite questionnaire survey was conducted by the investigators with the parturients who met the inclusion and exclusion criteria, and the parturients were instructed to complete the questionnaire independently. In this study, a total of 1635 parturients were investigated. After all the questionnaires were checked, unqualified questionnaires, such as irregular questionnaires and incorrect questionnaires, were excluded. Finally, 1536 valid questionnaires were collected, for an effective response rate of 94%. This study was approved by the Ethics Committee of Xinjiang Medical University (Ethics approval number: XJYKDXR20230303023).\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eMeasurement tools\u003c/h3\u003e\n\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\u003ch2\u003eQuestionnaire on maternal and neonatal general conditions\u003c/h2\u003e\u003cp\u003eA self-designed general information questionnaire was used. Maternal general demographic characteristics (age, education level, occupation, etc.), maternal delivery history (gestational age, delivery mode, postpartum hemorrhage, pregnancy complications, etc.), living environment, and neonatal general demographic characteristics (neonatal sex, birth weight, birth asphyxia, birth diseases, etc.) were collected.\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eEdinburgh Postnatal Depression Scale (EPDS)\u003c/h3\u003e\n\u003cp\u003eThe EPDS was developed by Cox et al [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]. The EPDS consists of 10 items and is scored on a four-point Likert scale, with higher scores indicating more clinically severe depressive symptoms. In this study, an EPDS score\u0026thinsp;\u0026ge;\u0026thinsp;9 was used as the criterion [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. The scale has good reliability and validity [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e] in the evaluation of postpartum depression in pregnant women. The Cronbach's α coefficient of the scale in this study was 0.881.\u003c/p\u003e\n\u003ch3\u003eConnor-Davidson Resilience Scale (CD-RISC)\u003c/h3\u003e\n\u003cp\u003eThe Chinese version of the CD-RISC was translated and revised by Xiao Nan and Zhang Jianxin [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. The scale consists of three dimensions, which are scored from 0 to 4. The total score on the scale is 100, and the higher the score is, the stronger the psychological resilience is. The Cronbach's α coefficient of the scale in this study was 0.968.\u003c/p\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003ePerceived Social Support Scale (PSSS)\u003c/h2\u003e\u003cp\u003eThe scale was developed by Zimet [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. The Cronbach's α coefficient of the scale in this study was 0.97.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e\u003ch2\u003eStatistical analysis\u003c/h2\u003e\u003cp\u003eIn this study, the data were analysed via SPSS 26.0. The normally distributed data are described as \u0026plusmn;\u0026thinsp;s, and the nonnormally distributed data are expressed as medians (quartiles). Two independent sample \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:\\stackrel{-}{\\text{x}}\\)\u003c/span\u003e\u003c/span\u003e\u003cem\u003et\u003c/em\u003e tests were used to compare the means of the two groups of normally distributed and homogeneous variance data, and nonparametric tests were used for statistical analysis. The count data are presented as frequencies and constituent ratios, and the chi-square test was used for statistical analysis. All significant factors in the univariate analysis were included in the logistic regression model. The CHAID algorithm was used to construct a classification decision tree model to screen variables. A decision tree is a classification and regression method with a tree structure that is composed of decision nodes, branches, and leaves. The top node is the root node. Each branch is a new decision node or a leaf of the tree, representing a test output, and each leaf represents a possible classification result. Each branch is a new decision node or leaf, which represents a test output, and each leaf node represents a possible classification result. Since the sample size decreases with the growth of the decision tree, the prepruning technique is used to control the sufficient growth of the decision tree: the minimum sample contents in the parent node and child node are 100 and 50, respectively, and the maximum tree depth is 3. The ROC curve was drawn according to the prediction results of the two models, and the differences between the two models were analysed and compared. The test level was α\u0026thinsp;=\u0026thinsp;0.05.\u003c/p\u003e\u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\u003ch2\u003eMaternal and newborn general demographic data\u003c/h2\u003e\u003cp\u003eA total of 1536 puerperae participated in the survey, and 527 puerperae were diagnosed with PPD, for a detection rate of 34.31%. Among the enrolled women, 54.69% (840) were undergraduates, 83.79% (1287) were 25\u0026ndash;35 years old, and 94.27% (1448) were urban residents. The group with a household income above 8001 yuan accounted for the highest proportion, accounting for 42.45% (652), and the group with a household income between 5001 and 8000 yuan accounted for 33.53% (515). Working women accounted for 77.41% (1189) of the sample. The reproductive history revealed that the primipara accounted for 65.43% (1005) of the population, and the cesarean section rate was 71.09% (1092). The highest proportion of newborns with weights in the range of 2.5\u0026ndash;4 kg was 84.64% (1300 cases), and boys accounted for 53.06% (815 cases). The results of the univariate analysis revealed that maternal depression differed with gestational age, delivery mode, living environment, pregnancy complications, neonatal birth weight, delivery type, neonatal asphyxia, neonatal diseases, psychological resilience, and social support (P\u0026thinsp;\u0026lt;\u0026thinsp;0.05). Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e is shown.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eUnivariate analysis of risk factors for PPD [n\u0026thinsp;=\u0026thinsp;1536,n(%)].\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"6\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eProject\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e\u003cp\u003eWhether PPD(%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e\u003cem\u003eχ\u003c/em\u003e\u003csup\u003e\u003cem\u003e2\u003c/em\u003e\u003c/sup\u003e value\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e\u003cem\u003eP-\u003c/em\u003evalue\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eNormal\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eDepression\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003eAge groups\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;25\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e22 (2.18)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e13 (2.47)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003e1.082\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003e0.582\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e25 to 35\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e840 (83.25)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e447 (84.82)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026gt;\u0026thinsp;35\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e147 (14.57)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e67 (12.71)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e\u003cp\u003eLevel of education\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLess than high school\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e45 (4.46)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e31 (5.88)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"3\" rowspan=\"4\"\u003e\u003cp\u003e5.649\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"3\" rowspan=\"4\"\u003e\u003cp\u003e0.130\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eHigh school and junior college\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e258 (25.57)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e157 (29.79)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eUndergraduate\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e571 (56.59)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e269 (51.04)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMaster's degree or above\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e135 (13.38)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e70 (13.28)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003ePlace to live\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRural\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e59 (5.85)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e29 (5.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e0.076\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e0.783\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eCity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e950 (94.15)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e498 (94.50)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e\u003cp\u003eTotal monthly household income\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eUnder 3,000\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e50 (4.96)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e25 (4.74)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"3\" rowspan=\"4\"\u003e\u003cp\u003e5.667\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"3\" rowspan=\"4\"\u003e\u003cp\u003e0.129\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e30001\u0026thinsp;\u0026minus;\u0026thinsp;5000\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e179 (17.74)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e115 (21.82)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e5001\u0026ndash;8000\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e333 (33.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e182 (34.54)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e8001 +\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e447 (44.30)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e205 (38.90)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eOccupation\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eCareer women\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e792 (78.49)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e397 (75.33)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e1.979\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e0.160\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eUnemployed or unemployed\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e217 (21.51)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e130 (24.67)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eGestational age at delivery\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;38 weeks\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e227 (22.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e150 (28.46)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e6.652\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e0.010\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026gt;= 38\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e782 (77.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e377 (71.54)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eMode of delivery\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNatural birth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e312 (30.92)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e132 (25.05)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e5.813\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e0.016\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eCesarean section\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e697 (69.08)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e395 (74.95)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003eLiving environment\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eGood\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e795 (78.79)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e382 (72.49)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003e9.208\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003e0.010\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAverage\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e209 (20.71)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e144 (27.32)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003epoor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e5 (0.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1 (0.19)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003eNumber of pregnancies\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1 pregnancy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e653 (64.72)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e352 (66.79)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003e0.763\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003e0.683\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2 pregnancies\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e241 (23.89)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e116 (22.01)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMore than 3 pregnancies\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e115 (11.40)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e59 (11.20)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003ePresence or absence of pregnancy complications\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eyes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e766 (75.92)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e353 (66.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e13.970\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eno\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e243 (24.08)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e174 (33.02)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003eNewborn birth weight\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;2.5 kg\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e67 (6.64)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e69 (13.09)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003e19.196\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2.5 to 4 kg\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e880 (87.22)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e420 (79.70)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026gt;\u0026thinsp;4 kg\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e62 (6.14)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e38 (7.21)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003eType of delivery\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eFull term delivery\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e898 (89.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e430 (81.59)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003e16.363\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePremature birth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e98 (9.71)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e84 (15.94)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eExpired production\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e13 (1.29)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e13 (2.47)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eWhether there is neonatal asphyxia\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eyes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e30 (2.97)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e34 (6.45)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e10.490\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eno\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e979 (97.03)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e493 (93.55)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003ePresence of birth defects\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eno\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1002 (99.31)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e518 (98.29)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e3.453\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e0.063\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eyes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e7 (0.69)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e9 (1.71)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003ePresence or absence of a neonatal illness\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eno\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e987 (97.82)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e503 (95.45)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e6.714\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e0.010\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eyes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e22 (2.18)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e24 (4.55)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003eDegree of mental resilience\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLow level\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e114 (11.30)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e187 (35.48)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003e230.385\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMedium level\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e193 (19.13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e180 (34.16)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eHigh level\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e702 (69.57)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e160 (30.36)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003eDegree of social support\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLow level\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e9 (0.89)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e10 (1.90)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003e121.965\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMedium level\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e173 (17.15)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e224 (42.50)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eHigh level\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e827 (81.96)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e293 (55.60)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003eLogistic regression analysis of influencing factors of postpartum depression\u003c/h2\u003e\u003cp\u003e With the presence of PPD (0\u0026thinsp;=\u0026thinsp;no, 1\u0026thinsp;=\u0026thinsp;yes) as the dependent variable, according to the results of univariate analysis, the living environment, gestational age at delivery, delivery mode, pregnancy complications, neonatal birth weight, delivery type, neonatal asphyxia, neonatal diseases, psychological resilience, and social support were included in logistic regression analysis. The results revealed that the lower the level of social support was (compared with the high level of social support, the OR value of the middle level of social support was 1.949), the lower the level of psychological resilience was (compared with the high level of psychological resilience, the lower the level of psychological resilience was, the lower the level of psychological resilience was, the lower the level of social support was, and the higher the level of psychological resilience was, the lower the level of psychological resilience was). The OR values of the low and medium levels of psychological resilience were 5.091 and 3.595, respectively. Pregnancy complications (OR\u0026thinsp;=\u0026thinsp;1.356) and cesarean section (OR\u0026thinsp;=\u0026thinsp;1.406) were risk factors for PDD. No neonatal asphyxia (OR\u0026thinsp;=\u0026thinsp;0.524) or birth weight of 2.5\u0026ndash;4 kg (OR\u0026thinsp;=\u0026thinsp;0.593) were protective factors against PPD. The living environment, gestational age at delivery, mode of delivery, type of delivery, and presence of neonatal diseases did not affect the occurrence of PPD. See Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\u003ch2\u003eDecision tree analysis of influencing factors of postpartum depression\u003c/h2\u003e\u003cp\u003eIn this study, the decision tree was grown into three levels and a total of seven end nodes. A total of four influencing factors were identified, including psychological resilience, social support, pregnancy complications and delivery mode. The root node was psychological resilience, which showed that psychological resilience had the highest correlation with PPD in perinatal women. With the decrease in psychological resilience, the rate of postpartum depression tended to increase. See Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e\u003ch2\u003eComparison of the analysis results of the two models\u003c/h2\u003e\u003cp\u003eThe results of the two models revealed that psychological resilience, social support, and pregnancy complications were the influencing factors of PPD. There were no significant differences in living environment, gestational age at delivery, mode of delivery, birth weight, type of delivery, neonatal asphyxia, or neonatal diseases. The receiver operating characteristic (ROC) curves of the two models were plotted. The AUC of the two models was \u0026gt;\u0026thinsp;0.5, indicating that the models had a good prediction effect. The ROC curves of the two models were similar, indicating that the classification effects of the two models were similar, but there were also some differences between the two models. The influencing factors of the logistic regression model, birth weight and the presence of neonatal asphyxia, were excluded from the classification decision tree model. See Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eThe AUC of the logistic regression model was 0.754 (95% CI: 0.728\u0026ndash;0.780), the specificity was 72%, and the sensitivity was 70.2%. The AUC of the classification decision tree model was 0.738 (95% CI: 0.711\u0026ndash;0.765), the specificity was 69.6%, and the sensitivity was 69.6%. Both \u003cem\u003eP\u003c/em\u003e values of the two models were \u0026lt;\u0026thinsp;0.001, indicating that the classification effects of the two models were of practical significance. The AUC values of the two models were greater than 0.7, indicating that the classification prediction results of the two models had a certain accuracy. In general, although the classification performance of the two models was similar, the classification decision tree model had lower specificity and sensitivity than did the logistic regression model, and the prediction performance of the logistic regression model was better than that of the classification decision tree model.See Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003e\u003cb\u003eComparison of the classification effects of the logistic regression model and classification decision tree\u003c/b\u003e model\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"7\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eModels\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAUC\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eStandard error\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003e95%\u003cem\u003eCI\u003c/em\u003e\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eSensitivity (%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eSpecificity (%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eYouden index\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLogistic regression\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.754\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.013\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e[0.728, 0.780]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.702\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.720\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.470\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eClassification decision tree\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.738\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.014\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e[0.711, 0.765]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.696\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.696\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.439\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eWith the increasing importance of mental health in society, postpartum depression has become a common concern [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. Postpartum depression is a common and serious psychological disorder [\u003cspan additionalcitationids=\"CR24\" citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. Domestic and foreign scholars have performed many studies [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e], It has been shown to be closely related to a variety of factors, including physiological changes after childbirth [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]、 rapid change of role [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e] 、parenting stress, inadequate family support, past history of mental illness, and socioeconomic status [\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. Therefore, for postpartum depression, we need to take comprehensive intervention measures, including strengthening the popularization of postpartum mental health knowledge, providing personalized psychological counselling services, strengthening the family and social support system, identifying and treating potential mental health problems in time, and optimizing the postpartum medical service process, to effectively reduce the incidence of postpartum depression. To protect maternal mental health, the healthy development of mother\u0026ndash;infant relationships should be promoted, and a more harmonious family and social environment should be built.\u003c/p\u003e\u003cp\u003eThe detection rate of PPD was 34.31% among 1536 pregnant women, which was higher than the average level [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]. This difference may be due to differences in culture, economy, customs, lifestyle, and medical conditions across regions, which may affect the psychological state [\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]. At the same time, families facing greater economic pressure may face more life troubles [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e], such as child care costs, career development and other issues, thus increasing the psychological burden on parturients. Postpartum depression not only is a serious threat to maternal physical and mental health but also may have adverse effects [\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e] on the growth environment of infants, the family atmosphere, and even wider society.\u003c/p\u003e\u003cp\u003eThe results of this study revealed that the detection rate of PPD differed across the different resilience groups, that the level of resilience group was greater than the high level of resilience group was, and that resilience had the greatest influence on PPD, which was consistent [\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e] with the positive psychological traits of individuals in the face of adversity. Psychological resilience is a protective factor [\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e]. Resilience partially mediates [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e] the relationship between postpartum negative life events and postpartum depression. Women with a greater degree of psychological resilience are better able to effectively buffer the adverse effects of postpartum negative life events and highlight and strengthen their advantages to avoid negative emotions. The results of this study suggest that the impact of postpartum negative life events can be reduced by increasing the level of psychological resilience of parturients and improving their adaptability to cope with adverse life events. To stimulate positive emotions in parturients and actively face postpartum personal and environmental changes, the incidence of PPD should be reduced.\u003c/p\u003e\u003cp\u003eIn addition, this study revealed that social support was also an important protective factor for maternal mental health, suggesting that providing adequate social support for women during puerperium helps them relieve stress and reduce its occurrence [\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e, \u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e]. During puerperium, family members, especially husbands, should provide more care and support to puerperae, understand their physical and mental changes after childbirth, and shoulder the responsibility of parenting together. The ability of a puerpera to find a sense of belonging to the family during the puerpera can enhance the anti-stress ability of the puerpera to relieve their negative mood [\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e]. Social support plays an important role in preventing and treating postpartum depression [\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e]. Therefore, measures such as strengthening family support, establishing a community support network, providing professional psychological support, and improving the social security system can effectively improve the level of social support and reduce the risk of postpartum depression.\u003c/p\u003e\u003cp\u003eThe effect of delivery mode on the development of PPD has been widely studied [\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e, \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]. The results of this study revealed that the incidence of PPD in this study was as high as 36.17%, and CS was a risk factor for PPD. Although this delivery method can reduce pain during childbirth, it is difficult to recover quickly after the operation because of the high degree of psychological pressure and the difficulty of movement and feeding, which increases the possibility of postpartum depression. The release of cortisol (a stress hormone) is greater during cesarean section, and the stress of cesarean section is more likely to induce mild or moderate PPD [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]. One study suggested that the link between high cortisol levels caused by surgical stress and PPD may be related [\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e, \u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e]. To ensure that women with C-sections have rapid access to mental health care, the progression of postpartum mental disorders should be carefully monitored; therefore, comprehensive maternal interventions should be intensified to reduce the likelihood of postpartum depression.\u003c/p\u003e\u003cp\u003eThis study also revealed that the presence of pregnancy complications is a risk factor for PPD, and women with pregnancy complications are more likely to have depression. The results of Zhang Yan et al [\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e] suggested that attention should be given to screening for depression in the process of perinatal health care, and women with high-risk factors should be guided to correctly view the impact of high-risk factors to prevent or reduce the occurrence of depression.\u003c/p\u003e\u003cdiv id=\"Sec16\" class=\"Section2\"\u003e\u003ch2\u003eLimitations\u003c/h2\u003e\u003cp\u003eFirst, some statistically significant factors in the logistic regression model were not included in the decision tree model, which may be due to the limitation of sample size, especially the sample size at each node and the depth of the decision tree. The influence of these variables on PPD may not be revealed until later in the decision tree. In addition, although these variables have a certain influence on postpartum depression in perinatal women, their effect may be relatively weak compared with that of other variables, and they may be misjudged as interfering factors and excluded from the data analysis. Second, the measurement of postpartum depression relied only on scales and did not involve professional psychiatric interviews, so the outcome measures reflected only maternal depressive emotional problems rather than formal psychiatric diagnoses of depression or anxiety. These data were obtained through self-report questionnaires and may be subject to recall bias, which may affect the accuracy of the results. Moreover, this study used a cross-sectional study design, which makes it difficult to accurately determine causality compared with a cohort study design. Finally, this study used a convenient sampling method, which may cause sample bias, resulting in underrepresentation of the sample size. In conclusion, future studies should design larger-scale and more complete research protocols to assess the influencing factors of PPD more accurately and provide a solid theoretical basis for improving the adverse mood of parturients.\u003c/p\u003e\u003c/div\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eWe are grateful to all the families and pregnant women for their participation.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eStudy design and manuscript drafting by Xin He. Data collection by Bahedana Sailike, Xiaoting Wang, Sufeila Shalayiding, and Meng Weicui. Data analysis and interpretation: Xin He, Bahedana Sailike, Xiaoting Wang, Sufeila Shalayiding, and Meng Weicui. Critical revision of the manuscript by Ting Jiang. All the authors approved the final version for publication.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was supported by the Xinjiang Uygur Autonomous Region \u0026ldquo;14th Five-Year Plan\u0026rdquo; Higher Education School Characteristic Discipline of Public Health and Preventive Medicine, the National Natural Science Foundation of China (82360669) and the Key Laboratory of Population Health and Eugenics of Anhui Province (JKYS20231).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThank you very much for the editor\u0026rsquo;s attention and recognition of our research work. We appreciate the BMC Public Health journal\u0026rsquo;s requirements for data sharing; however, because our data involve the privacy of maternal and we have entered into a relevant confidentiality agreement, we may not be able to provide the raw data. We have fully described the study design, analyses and results, as well as the process of data analysis and processing. Researchers seeking access to anonymous portions of the data may contact the corresponding author, Ting Jiang (Email: [email protected]). Requests will be reviewed on a case-by-case basis, and approved applicants will receive data in accordance with the terms of the ethical approval and confidentiality agreements.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eHuman ethics and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eInformed consent was obtained from each participant. In accordance with the principles of the Declaration of Helsinki, this study was approved by the Ethics Committee of Xinjiang Medical University (approval number: XJYKDXR20230303023).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no competing interests.\u003c/p\u003e\n"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eByatt N, Brenckle L, Sankaran P, et al. Effectiveness of two systems-level interventions to address perinatal depression in obstetric settings (PRISM): An active-controlled cluster-randomised trial. Lancet Public Health. 2024;9:e35\u0026ndash;46.\u003c/li\u003e\n\u003cli\u003eHu N, Luo J, Xiang W, et al. The relationship between postpartum negative life events and postpartum depression: A moderated mediation model of neuroticism and psychological flexibility. BMC Psychiatry. 2024;24:147.\u003c/li\u003e\n\u003cli\u003eUnderwood L, Waldie K, D\u0026rsquo;Souza S, et al. A review of longitudinal studies on antenatal and postnatal depression. Arch Womens Ment Health. 2016;19:711\u0026ndash;20.\u003c/li\u003e\n\u003cli\u003eRogers A, Obst S, Teague SJ, et al. Association between maternal perinatal depression and anxiety and child and adolescent development: A meta-analysis. JAMA Pediatr. 2020;174:1082\u0026ndash;92.\u003c/li\u003e\n\u003cli\u003eKuehner C. Why is depression more common among women than among men? Lancet Psychiatry. 2017;4:146\u0026ndash;58.\u003c/li\u003e\n\u003cli\u003eMcHenry J, Carrier N, Hull E, et al. Sex differences in anxiety and depression: Role of testosterone. Front Neuroendocrinol. 2014;35:42\u0026ndash;57.\u003c/li\u003e\n\u003cli\u003eLamus MN, Pabon S, MPoca C, et al. Giving women WOICE postpartum: Prevalence of maternal morbidity in high-risk pregnancies using the WHO-WOICE instrument. BMC PREGNANCY CHILDBIRTH. 2021;21:357.\u003c/li\u003e\n\u003cli\u003ePayne JL, Maguire J. Pathophysiological mechanisms implicated in postpartum depression. Front Neuroendocrinol. 2019;52:165\u0026ndash;80.\u003c/li\u003e\n\u003cli\u003eObrochta CA, Chambers C, Bandoli G. Psychological distress in pregnancy and postpartum. Women Birth J Aust Coll Midwives. 2020;33:583\u0026ndash;91.\u003c/li\u003e\n\u003cli\u003eYaqoob H, Ju X-D, Bibi M, et al. a systematic review of risk factors of postpartum depression. Evidence from asian culture . Acta Psychol (Amst). 2024;249:104436.\u003c/li\u003e\n\u003cli\u003eHagatulah N, Br\u0026auml;nn E, Oberg AS, et al. Perinatal depression and risk of mortality: Nationwide, register based study in sweden. BMJ. 2024;384:e075462.\u003c/li\u003e\n\u003cli\u003eGopalan P, Spada ML, Shenai N, et al. Postpartum depression-identifying risk and access to intervention. Curr Psychiatry Rep. 2022;24:889\u0026ndash;96.\u003c/li\u003e\n\u003cli\u003eGrissette BG, Spratling R, Aycock DM. Barriers to help-seeking behavior among women with postpartum depression. J Obstet Gynecol Neonatal Nurs JOGNN. 2018;47:812\u0026ndash;9.\u003c/li\u003e\n\u003cli\u003ePugliese V, Bruni A, Carbone EA, et al. Maternal stress, prenatal medical illnesses and obstetric complications: Risk factors for schizophrenia spectrum disorder, bipolar disorder and major depressive disorder. Psychiatry Res. 2019;271:23\u0026ndash;30.\u003c/li\u003e\n\u003cli\u003eMoore Simas TA, Flynn MP, Kroll-Desrosiers AR, et al. A systematic review of integrated care interventions addressing perinatal depression care in ambulatory obstetric care settings. Clin Obstet Gynecol. 2018;61:573\u0026ndash;90.\u003c/li\u003e\n\u003cli\u003eKim K-M, Kim J-H, Rhee H-S, et al. Development of a prediction model for the depression level of the elderly in low-income households: Using decision trees, logistic regression, neural networks, and random forest. Sci Rep. 2023;13:11473.\u003c/li\u003e\n\u003cli\u003eCox JL, Holden JM, Sagovsky R. Detection of postnatal depression. Development of the 10-item edinburgh postnatal depression scale. Br J Psychiatry J Ment Sci. 1987;150:782\u0026ndash;6.\u003c/li\u003e\n\u003cli\u003eGibson J, McKenzie-McHarg K, Shakespeare J, et al. A systematic review of studies validating the edinburgh postnatal depression scale in antepartum and postpartum women. Acta Psychiatr Scand. 2009;119:350\u0026ndash;64.\u003c/li\u003e\n\u003cli\u003eXiao Julan, Wen Yi, Luo Weixiang, et al. Reliability and validity test of the Chinese version of the Edinburgh Postpartum Depression Scale in pregnant women. Modern Preventive Medicine. 2022; 49:3320\u0026ndash;5.\u003c/li\u003e\n\u003cli\u003eYu X, Zhang J. Factor analysis and psychometric evaluation of the connor-davidson resilience scale (cd-risc) with Chinese people. Soc Behav Personal Int J. 2007;35:19\u0026ndash;30.\u003c/li\u003e\n\u003cli\u003eSCohen S, Matthews KA. Social support, type a behavior, and coronary artery disease. Psychosom Med. 1987;49:325\u0026ndash;30.\u003c/li\u003e\n\u003cli\u003eHou Juan, Jia Keke, Fang Xiaoyi. The development trend and social changes of marital satisfaction between Chinese couples in the past 20 years. Acta Psychologica Sinica. 2024; 56:895\u0026ndash;915.\u003c/li\u003e\n\u003cli\u003eChen Q, Li W, Xiong J, et al. Prevalence and risk factors associated with postpartum depression during the COVID-19 pandemic: A literature review and meta-analysis. Int J Environ Res Public Health. 2022;19:2219.\u003c/li\u003e\n\u003cli\u003eSun R, Zhao M, Ma L, et al. High psychological stress levels related to delivery can increase the occurrence of postpartum mental disorders. Front Psychiatry. 2023;14:1273647.\u003c/li\u003e\n\u003cli\u003ePearlstein T, Howard M, Salisbury A, et al. Postpartum depression. Am J Obstet Gynecol. 2009;200:357\u0026ndash;64.\u003c/li\u003e\n\u003cli\u003eHirose A, Terauchi M, Odai T, et al. Postpartum hair loss is associated with anxiety. J Obstet Gynaecol Res. 2024;50:2239\u0026ndash;45.\u003c/li\u003e\n\u003cli\u003eParia A, Atallah A, Nourredine M, et al. Early detection of perinatal depression in couples: A single-center prospective study. Eur Psychiatry J Assoc Eur Psychiatr. 2024;67:e48.\u003c/li\u003e\n\u003cli\u003eGarnacho-Garnacho VE, Rodr\u0026iacute;guez-L\u0026oacute;pez ES, Oliva-Pascual-Vaca \u0026Aacute;, et al. Maternal psychological well-being as a protector in infantile colic. Nutrients. 2024;16:2342.\u003c/li\u003e\n\u003cli\u003eStewart DE, Vigod SN. Postpartum depression: Pathophysiology, treatment, and emerging therapeutics. Annu Rev Med. 2019;70:183\u0026ndash;96.\u003c/li\u003e\n\u003cli\u003eDai Xuemei. Postpartum depression is associated with different modes of delivery. Journal of Mudanjiang Medical College. 2019; 40:75\u0026ndash;6, 150.\u003c/li\u003e\n\u003cli\u003eThornton BM. The effects of spiritual, religious, and psychological coping during pregnancy on post-pregnancy health outcomes. 2024.\u003c/li\u003e\n\u003cli\u003eHahn-Holbrook J, Cornwell-Hinrichs T, Anaya I. Economic and health predictors of national postpartum depression prevalence: A systematic review, meta-analysis, and meta-regression of 291 studies from 56 countries. Front Psychiatry. 2017;8:248.\u003c/li\u003e\n\u003cli\u003eMatsunaga M, Okajima J, Furutani K, et al. Associations of rumination, behavioral activation, and perceived reward with mothers\u0026rsquo; postpartum depression during the COVID-19 pandemic: A cross-sectional study. Front Psychiatry. 2024;15:1295988.\u003c/li\u003e\n\u003cli\u003eBaattaiah BA, Alharbi MD, Babteen NM, et al. The relationship between fatigue, sleep quality, resilience, and the risk of postpartum depression: An emphasis on maternal mental health. BMC Psychol. 2023;11:10.\u003c/li\u003e\n\u003cli\u003eYuping Zhou, Fanyan Huang, Yuqi Chen, et al. Postpartum depression and psychological resilience in women and their spouses are subject-object interdependent. Military nursing. 2023; 40:10\u0026ndash;3.\u003c/li\u003e\n\u003cli\u003eShumin Zhang, Qian Wei, Yunhui Zhang, et al. Mediating and moderating effects of maternal resilience of postpartum depression symptoms on parent-child interaction in early infancy. Chinese Journal of Public Health. 2023; 39:212\u0026ndash;8.\u003c/li\u003e\n\u003cli\u003eZhuang Youqing, Jiang Cuiting, Zeng Liling, et al. The mediating effect of maternal resilience on the relationship between postpartum negative life events and postpartum depression. PLA Journal of Nursing. 2021; 38:18\u0026ndash;21.\u003c/li\u003e\n\u003cli\u003eZhang Y, Jin S. The impact of social support on postpartum depression: The mediator role of self-efficacy. J Health Psychol. 2016;21:720\u0026ndash;6.\u003c/li\u003e\n\u003cli\u003eCho H, Lee K, Choi E, et al. Association between social support and postpartum depression. Sci Rep. 2022;12:3128.\u003c/li\u003e\n\u003cli\u003eDagher RK, Bruckheim HE, Colpe LJ, et al. Perinatal depression: Challenges and opportunities. J Womens Health 2002. 2021;30:154\u0026ndash;9.\u003c/li\u003e\n\u003cli\u003eVan Sieleghem S, Danckaerts M, Rieken R, et al. Childbirth related PTSD and its association with infant outcome: A systematic review. Early Hum Dev. 2022;174:105667.\u003c/li\u003e\n\u003cli\u003eRauh C, Beetz A, Burger P, et al. Delivery mode and the course of pre- and postpartum depression. Arch Gynecol Obstet. 2012;286:1407\u0026ndash;12.\u003c/li\u003e\n\u003cli\u003eDinan TG. Glucocorticoids and the genesis of depressive illness. A psychobiological model. Br J Psychiatry J Ment Sci. 1994;164:365\u0026ndash;71.\u003c/li\u003e\n\u003cli\u003eEdwards DR, Porter SA, Stein GS. A pilot study of postnatal depression following caesarean section using two retrospective self-rating instruments. J Psychosom Res. 1994;38:111\u0026ndash;7.\u003c/li\u003e\n\u003cli\u003eZhang Yan, Weng Xueling, Qi Xiaochen. Research on the application effect of clinical pathways in the nursing of gestational diabetes mellitus. Journal of Practical Gynecologic Endocrinology (electronic version). 2018; 5:109\u0026ndash;10.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"postpartum depression, resilience, social support, logistic regression, decision tree","lastPublishedDoi":"10.21203/rs.3.rs-7282695/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7282695/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e\u003cp\u003eTo study the status of postpartum depression and its main influencing factors by using logistic regression and a decision tree model and to understand the psychological characteristics of puerperae to take targeted measures to improve their mental health level.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e\u003cp\u003eA general demographic data questionnaire, the Edinburgh Postnatal Depression Scale (EPDS), the Connor-Davidson Resilience Scale (CD-RISC), and the Perceived Social Support Scale (PSSS) were used to investigate 1536 parturients who came to the Child Health Care Department of a tertiary hospital in Urumqi for physical examination. Using binary classification and a logistic regression model based on the classification of the decision tree analysis of postpartum women, the CHAID algorithm was used to compare the factors influencing PPD and the differences between the two models.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e\u003cp\u003eThe results of the logistic regression analysis model and decision tree model revealed that the level of resilience, degree of social support, and pregnancy complications were the influencing factors of PPD (\u003cem\u003eP\u0026thinsp;\u0026lt;\u0026thinsp;0.\u003c/em\u003e05), among which resilience was the most important influencing factor.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e\u003cp\u003eBoth models have predictive value for classification, and the logistic regression model is superior to the decision tree model in predicting PPD. However, both models have advantages and disadvantages and can complement each other to make the analysis results more practical.\u003c/p\u003e","manuscriptTitle":"Analysis of the Factors Influencing Postpartum Depression via Logistic Regression and Decision Tree Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-21 10:59:03","doi":"10.21203/rs.3.rs-7282695/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"2e3d0504-60b7-4dbb-b238-0232f09dadfc","owner":[],"postedDate":"August 21st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-12-22T08:40:15+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-21 10:59:03","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7282695","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7282695","identity":"rs-7282695","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}