Building a Prediction Model for Children's Social-emotional Development: A Community- Based Cohort in Shanghai, China

Building a Prediction Model for Children's Social-emotional Development: A Community- Based Cohort in Shanghai, China | 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 Building a Prediction Model for Children's Social-emotional Development: A Community- Based Cohort in Shanghai, China Hualong Yuan, Yuechen Lou, Bihua Chen, Jiali Zhang, Weiming Tang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8060925/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Social-emotional development (SED) delays in early childhood significantly increase risks of behavioral and mental health disorders. Identifying modifiable risk and protective factors is crucial for improving SEDs in children. This prospective cohort study aims to develop a predictive model for SED delays in 18-month-old children using data from 419 mother-child dyads in Shanghai, China. Twenty-one variables across maternal biomedical, psychological, socioeconomic, and infant domains were analyzed, with maternal anxiety and depression status tracked at five timepoints from pregnancy to 18 months postpartum. The SED status of offspring measured by the Ages & Stages Questionnaire: Social-Emotional. Extreme Gradient Boosting (XGBoost) feature selection identified five key predictors. The mean delivery age of the mothers was 32.2 years. All children were from full-term singleton births. Higher maternal age and maternal educational level, adequate sleep at 1-year-old may reduce SED delay risk, while maternal anxiety/depression status at 18 months postpartum may increase the risk. The model achieved excellent predictive performance (AUC = 0.93). Findings suggested that community-level screening of maternal mental health at 18 months postpartum and tailored measures (e.g., parental health education on child sleep patterns) to ensure adequate sleep for children could mitigate SED delays. Social-emotional development delay children prediction cohort study Figures Figure 1 Figure 2 Introduction Social-emotional development (SED) refers to the capacity of individuals, especially young children, to identify and manage their own feelings, form relationships, and learn from interactions with others (Gaudet and Letourneau, 2015 ). As a foundation for human development, SED plays a crucial role in shaping cognitive abilities and mental health outcomes throughout life, equipping children to manage relationships, regulate emotions, and develop lifelong mental health skills (Gaudet and Letourneau, 2015 ; Yong et al., 2023 ). Globally, 7–24% of children under 3 years exhibit parent-reported social-emotional difficulties, with a median prevalence of 10% (Briggs-Gowan et al., 2001 ; Briggs et al., 2012 ). Longitudinal evidence from Shanghai, China (2018–2021) indicates 8.4% of 12-month-old manifest SED concerns (Hu et al., 2025 ), and such deficits significantly elevate risks for behavioral disorders, learning impairments, and adolescent psychopathology (Briggs-Gowan and Carter, 2008 ). SED in the early years also predicts the mental health status in adulthood (Bian et al., 2017 ), which is a strong concern for childhood development. For example, a systematic and meta-analysis, incorporating 18,282 children ages 12–83 months from 8 countries, reported 20.1% of children under 7 years experiencing mental disorders (Vasileva et al., 2021 ), while Chinese epidemiological studies, involving 73,992 children and adolescents aged 6–16 across five provinces, documented 17.5% prevalence (Li et al., 2022 ). The association between maternal mental health and offspring SED is well-established in developmental research—with evidence linking perinatal mental health disturbances to long-term offspring SED impairments even into adolescence (Maruyama et al., 2019 ; Rogers et al., 2020 ; Stein et al., 2014 ). However, three critical knowledge gaps persist, limiting the development of contextually valid SED prediction models, particularly for Asian populations. First, Asian cohorts remain substantially underrepresented in global studies of offspring SED (Yong et al., 2023 ), and existing predictive frameworks are predominantly derived from Western populations. Yet Asia’s unique context may modulate the predictive value of variables commonly included in Western SED models. This gap raises uncertainty about whether existing models can reliably forecast SED outcomes for Asian children, highlighting the need for region-specific prediction frameworks. Second, current predictive models for offspring SED have overlooked key modifiable variables that may contribute to prediction accuracy. For instance, infant sleep patterns and household pet ownership (a potential source of child social interaction) have rarely been integrated into SED prediction models. Third, and most centrally, the relative predictive weight of prenatal versus postnatal maternal mental health exposures on offspring SED remains contested. While perinatal mental health is a key determinant (e.g., maternal depression affecting 11.1% of Shanghai mothers correlates with impaired child emotion recognition and reduced social interaction, severely hindering the normal development of children’s social-emotional abilities(Zhang et al., 2023 )). Some scholars argue that maternal postpartum depression is more influential due to reduced daily interactions and a higher frequency of corporal punishment (Rotheram-Fuller et al., 2018 ). In contrast, accumulating evidence suggests that prenatal maternal stress exposure has been shown to have enduring consequences on brain development in the offspring, including abnormal brain structure and circuitry, as well as long-term neurodevelopmental impairments (Leis et al., 2014; Van den Bergh et al., 2018; Wu et al., 2022). The aim of this study is to develop a comprehensive predictive model for SED in 18-month-old children by addressing these gaps—specifically, by centering an Asian cohort (Shanghai, China), integrating underexplored predictors, and clarifying the timing-specific effects of maternal mental health—while also contributing to a robust, regionally tailored SED prediction framework. Methods Study Design This prospective cohort study was conducted at the Fenglin Community Health Service Center (FCHC) in Xuhui District, Shanghai. Pregnant women who registered at FCHC, from February 18, 2020, to April 19, 2021, were enrolled. Face-to-face interviews were conducted at the time of pregnancy registration to collect basic information and establish one-to-one relationships through WeChat (the most popular instant message application in China) to know the perinatal situation in real time. Then we followed up the participants in the second and third trimester, 2 weeks, 6 weeks, and 18 months after childbirth to collect information on the psychological status of the pregnant women. We also followed up with their offspring to observe their sleeping conditions and developmental status until they were 18 months old. The study was registered in the Chinese Clinical Trial Registry (ChiCTR2000029022) on January 11, 2020 and had ethical approval from the Shanghai Ethics Committee for Clinical Research (Approval Number: SECCR/2019-43). Informed consent was obtained from all individual participants (mothers) included in the study, and from the parents or legal guardians of all child participants. Study Population The study participants comprised the mother-infant dyads with term singleton births (≥37 gestational weeks) from the FCHC cohort. Exclusions applied to: (1) families who withdrew from the study, or (2) failed to complete developmental assessments during follow-up. Predictive Variables 21 predictive variables were selected based on literature review, including: maternal age, educational level, pre-pregnancy Body Mass Index (BMI), annual family income, owning pet, hemoglobin concentration at first prenatal visit (g/L), having any factors during pregnancy that could lead to a high-risk situation (such as being too young (<18 years old) or too old (≥35 years old), having a multiple pregnancy, having diabetes, hypertension, or heart disease, having a history of multiple miscarriages, preterm births, etc.), pre-pregnancy folic acid or assisted conception drug supplementation, gestational weight gain value, newborn birth weight, average daily sleep duration of infants at 1-year-old, Generalized Anxiety Disorder-7 (GAD-7) and Patient Health Questionnaire-9 (PHQ-9) scores at 5 time points (the second trimester, the third trimester, 2 weeks postpartum, 6 weeks postpartum, and 18 months postpartum). Patient Health Questionnaire-9 (PHQ-9), consists of 9 items, with a 4-point scale ranging from 0 to 3, according to the frequency of symptoms in the past 2 weeks. The total score ranges from 0 to 27 points, and can be used to assess the severity of depressive symptoms: 0-4 points are without depression, 5-9 points are mild, 10-14 points are moderate, and 15 points and above are severe. Internal reliability was excellent (Cronbach’s alpha = 0.89) (Zhang and He, 2015). Generalized Anxiety Disorder-7 (GAD-7), consisting of 7 items, is scored on a 4-point scale from 0 to 3, with a total score range of 0 to 21. GAD-7 is measured by the frequency of symptoms in the past 2 weeks, and can be used to assess the severity of anxiety symptoms: 0-4 anxiety-free, 5-9 mild, 10-14 moderate, 15 or above severe. Internal reliability was excellent (Cronbach’s alpha = 0.92) (Zhang and He, 2015). Outcome The social-emotional developmental status of offspring at 18 months is the outcome, measured using the Ages & Stages Questionnaires: Social-Emotional, Second Edition (ASQ:SE-2). It is a standardized developmental screening instrument that has been successfully studied in different countries, including China, as one of the most comprehensive and psychometrically sound measures of infant and toddler social-emotional development (Pontoppidan et al., 2017). The Chinese version of the measurement tool has been validated, with Cronbach's alpha coefficient for the 18-month Chinese version questionnaire of 0.84 (BIAN et al., 2021). ASQ:SE-2 assesses seven areas: self-regulation, compliance, communication, adaptive functioning, autonomy, affect, and interaction with people. In our study, we utilized the ASQ Chinese Online System, an online platform for questionnaire administration, scoring, and data management developed by Shanghai Zhangyuan Information Technology Co., Ltd. Upon completion of the questionnaire by parents, the system automatically scores responses and generates screening outcomes by comparing them with norms for Chinese children. Results are categorized into three developmental domains: below the threshold (< the 75th percentile, indicating typical development), close to the threshold (≥ the 75th percentile, but < the 90th percentile, suggesting potential developmental concerns), or above the threshold (≥ the 90th percentile, indicating significant risk of developmental delay). For our study, participants were categorized into two groups: a normal group (< the 75th percentile) and a delayed group (≥ the 75th percentile). Methodology of Data Analysis We utilized KNIME Analytics Platform V5.3 to build a predictive model. The Extreme Gradient Boosting (XGBoost) algorithm was applied to perform feature selection and to identify key predictive variables. Then, we interpreted the XGBoost model's behavior with a Global Surrogate Model (GSM, in this case, Logistic Regression Model) to explore the relationship between the key predictive variables and the target variable. After preparing the data by addressing missing values, removing highly-correlated variables and extreme outliers we proceeded with modeling and evaluation. 1. Feature Selection and Data Modeling Using the XGBoost Algorithm: A feature selection loop was established: 70% of the samples were randomly selected as the training set, and after being balanced by the SMOTE (Synthetic Minority Oversampling Technique) algorithm, the XGBoost algorithm was used to train the model. The remaining 30% of the samples served as the test set, which was input into the generated model for prediction. The predicted values were compared with the actual values to calculate Cohen's Kappa value. Using the backward feature elimination method, new models were continuously built by gradually reducing the predictor variables, and the above evaluation was repeated until the Kappa value no longer improved. The model with a Kappa value equal to or greater than 0.8 and the fewest predictor variables was selected. We take the predictive variables of this model as the key predictive variables. 2. Interpreting the XGBoost Model's Behavior with a Global Surrogate Model (GSM): As a machine learning method, XGBoost does not intuitively provide the relationship between input variables and the target variable. Therefore, an interpretable mimetic model (in this case, Logistic Linear Regression) was used to fit the prediction results of the complex model, thereby approximating and explaining its behavior. The reference category for the output variable was set to "0," so the probability of "1" represents the probability of abnormal socio-emotional development of the children. Results Baseline characteristics A total of 544 pregnant women were initially enrolled in the cohort study, among which, 26 participants withdrew during pregnancy, and 29 cases were excluded due to pregnancy loss. An additional 36 cases were excluded owing to preterm birth or twins, resulting in 453 eligible mother-child dyads. Subsequently, 34 pairs were excluded due to incomplete ASQ: SE-2 assessments at the 18-month follow-up, with a loss to follow-up rate of 7.5%, resulting in 419 mother-child dyads in the prediction model (Figure 1). Characteristics of the study population are shown in Table 1. The mean delivery age was 32.2 years (SD=3.5). The majority of women (92.1%) had a junior college or university education or above. Most of the population had a pre-pregnancy BMI within the normal range (18.5-24, 69.7%). Overall, 60.6% of the participants reported a household annual income (the participant and their spouse) ranging from 200,000 to 500,000 Chinese Yuan (CNY) pre-tax. Pet ownership was reported by 88 individuals (21.0%). The mean hemoglobin concentration at the first prenatal visit was 125.4 g/L (SD=9.74). Overall, 288 (68.7%) had a high-risk situation during pregnancy. Preconceptionally use of folic acid supplements or assisted fertility drugs was reported in 205 cases (48.9%). Gestational weight gain showed three patterns: 37 participants (8.8%) fell below the optimal range, 200 (47.7%) were within that range, and 182 (43.4%) exceeded that range. The mean birth weight of offspring was 3,364.69 g (SD=375.99), while infant sleep patterns at 1 year averaged 12.59 hours daily (SD=1.37). Table 2 shows the distribution of GAD-7 and PHQ-9 scores in different stages of pregnancy and the postpartum period. Scores of ≥10 (combining moderate [10–14] and severe [≥15] categories) showed distinct patterns across time points. For GAD-7, proportions were 2.2% (9 cases) in the second trimester, 1.4% (6 cases) in the third trimester, 1.2% (5 cases) at 2 weeks postpartum, 2.9% (12 cases) at 6 weeks postpartum, and 1.4% (6 cases) at 18 months postpartum. Similarly, PHQ-9 scores ≥10 were observed in 2.1% (9 cases) of participants in the second trimester, 1.7% (7 cases) in the third trimester, 0.7% (3 cases) at 2 weeks postpartum, 2.4% (10 cases) at 6 weeks postpartum, and 1.2% (5 cases) at 18 months postpartum. Outcome Regarding social-emotional developmental status, 377 participants demonstrated typical development, while 42 (10.0%) children did not achieve an ideal level of development, requiring attention due to potential or significant developmental concerns. Predictive Model Using “children’s social-emotional developmental status” as the target variable for feature selection, the final selected model's Kappa value was 0.837. The identified key predictive variables were: maternal age at delivery (β=-0.07), maternal educational level (β=-0.45), infant's average daily sleep duration at one year old (β=-0.08), and GAD-7 score (β=0.74) and PHQ-9 score (β=1.34) at 18 months postpartum (see Table 3). Maternal age, educational level, and infant's average daily sleep duration at 1-year-old were negatively correlated with the probability of delayed social-emotional developmental status in children. Higher maternal age, higher educational level, and adequate sleep at 1-year-old were associated with a lower probability of delayed social-emotional development. Conversely, maternal anxiety/depression status at 18 months postpartum were positively correlated with the probability of delayed social-emotional developmental status in children. Higher GAD-7 and PHQ-9 scores were associated with a higher likelihood of delayed social-emotional development. The ROC curve was used to evaluate the final selected model, with an AUC of 0.93, indicating a good predictive performance (see Figure 2). Discussion Building a predictive model for children's social-emotional development will enable us to deliver tailored interventions that enhance their growth. This study extended the existing literature by developing a prediction model, using a longitudinal study design, and including psychological measures into consideration. The present study identified key modifiable predictors of SED abnormalities in 18-month-old children, highlighting the protective roles of maternal age, educational attainment, and infant sleep duration, as well as the risks associated with postpartum maternal anxiety and depression. We found that insufficient sleep in 1-year-old children was associated with an increased risk of SED abnormalities, which explicitly underscores the critical role of sleep in supporting neurodevelopment during early childhood. This result aligns closely with prior empirical evidence. For example, a previous study reported that children sleeping less than 11 hours per night were nearly five times more likely to develop social-emotional problems than those sleeping 13–14 hours nightly (Hysing et al., 2016 ). Similarly, another study conducted in China noted that children with a daily total sleep time of < 12h/d had higher odds of experiencing emotional and behavioral difficulties (Hui et al., 2024 ). Notably, this link between insufficient sleep and elevated SED risk is not limited to toddlerhood, while a study further confirmed it persists even into age 5 (Sivertsen et al., 2015 ), emphasizing sleep’s long-term impact on emotional development trajectories. These collective findings highlight that promoting healthy sleep practices in infancy—such as establishing consistent bedtime routines, optimizing sleep environments, and adhering to age-appropriate sleep duration guidelines—should be prioritized as a pivotal, actionable measure to foster optimal social-emotional development in children. Notably, among the five timepoints at which we assessed maternal mental status—the second trimester, third trimester, 2 weeks postpartum, 6 weeks postpartum, and 18 months postpartum—only elevated GAD-7 and PHQ-9 scores at 18 months postpartum were identified as significant risk factors for offspring SED at the same age (18 months). This finding indicates that maternal mental status at 18 months postpartum, rather than during pregnancy or earlier postpartum stages, demonstrates a distinct association with children’s SED. More proximal negative mood appears to have a greater impact on children (Rotheram-Fuller et al., 2018 ). This is aligned with the existing literature, which demonstrates that maternal mental health status is closely linked to children's social-emotional and behavioral development (McDonald et al., 2018 ). The second year of life is marked by numerous key developmental transitions in children, including the emergence of secondary or self-conscious emotions, new self-regulatory and coping skills (Vondra et al., 2001 ). The 12-18-month bracket is a sensitive period of development, within which attachment patterns and affect regulatory capacities become more consistent (McIntosh et al., 2021 ). Negative maternal emotions at 18 months postpartum likely affect maternal caregiving sensitivity (e.g., reduced eye contact, tactile interaction) and decrease attachment security with children, directly interfering with the acquisition of socioemotional skills (McIntosh et al., 2021 ; Rotheram-Fuller et al., 2018 ). These findings underscore that maternal mental health during this sensitive neurodevelopmental window (18 months postpartum) may disrupt parent-child interaction patterns essential for healthy socioemotional maturation, especially since mental status at earlier timepoints (pregnancy, 2–6 weeks postpartum) did not show similar associations. This highlights the need for extended postpartum mental health monitoring beyond the perinatal period to support both maternal well-being and offspring SED. Our results demonstrate that older maternal age is associated with reduced risks of social-emotional developmental abnormalities in offspring. This finding also aligns with developmental theories and empirical evidence from longitudinal studies. For instance, a UK-based cohort study found that there were fewer social and emotional difficulties associated with increasing maternal age (Sutcliffe et al., 2012 ). This may be attributed to older mothers’ enhanced emotional maturity and parenting self-efficacy, which enable more responsive caregiving and consistent discipline (Tearne, 2015 ). Falster's population-based cohort study of 99,530 Australian children also revealed that compared to younger mothers, children born to mothers aged 30–35 years exhibited the lowest risk of multi-domain developmental deficits, including social competence, emotional maturity, and communication skills (Falster et al., 2018 ). Higher maternal educational level is also a protective factor for the social-emotional development of offspring. Previous research has consistently demonstrated that maternal educational attainment exerts a profound influence on offspring's socio-emotional development (Guoyan, 2008 ; McIntosh et al., 2021 ; Schmiedeberg and Schumann, 2019 ; Yuan-yuan et al., 2020 ; Yuying et al., 2024 ). A multi-regional study covering 14 large and medium-sized cities across China has provided compelling evidence that higher maternal educational attainment exerts a significant promotive effect on children's socio-emotional development (Guoyan, 2008 ). Mothers with higher education levels are more likely to adopt reasoning-based parenting approaches, balance autonomy with secure attachment, and implement targeted emotional interventions, all of which contribute to healthier social development and emotional regulation in offspring (Guoyan, 2008 ; Junge et al., 2021 ; Yuying et al., 2024 ). In Shanghai’s context, where educational achievement is highly prioritized, educated mothers may uniquely combine generational wisdom with contemporary parenting practices, creating a nurturing environment that mitigates both biological and cultural stressors on child development. Our study has several limitations. First, while maternal mental status and children’s SED status were collected via validated self-report questionnaires, the absence of clinical diagnostic confirmation introduces potential measurement bias. Future research could triangulate self-reports with clinician-administered assessments. Second, the sample size, though adequately powered for initial explorations, may limit generalizability to broader populations. Third, our study design focused primarily on variables of mothers and children, which may have led to incomplete capture of fathers’ factors (such as mental health) influencing the outcomes. Future research should prioritize collecting a more comprehensive set of current variables, such as fathers’ psychological state. Conclusion This study underscores the importance of maternal factors and infant care in social-emotional development in early childhood. Our findings emphasize the need for tailored interventions that address maternal mental health and infant sleep patterns to enhance children's mental health levels and social adaptation abilities. Future research should continue to explore strategies that mitigate developmental delays in at-risk populations. Declarations Authors' Statement: Hualong Yuan: Methodology, Investigation, Data curation, Conceptualization, Writing -review & editing, Writing - original draft. Yuechen Lou: Validation, Methodology, Formal analysis, Data curation, Writing - review & editing, Writing - original draft. Bihua chen: Resources, Project administration, Investigation, Writing - review & editing. Jiali Zhang: Supervision, Funding acquisition, Conceptualization, Writing -review & editing, Writing - original draft. Weiming Tang: Supervision, Investigation, Data curation, Conceptualization, Writing - review & editing, Writing - original draft. Acknowledgments : The authors thank all the study participants who contributed to this study. Funding: This study was supported by the Gaoyuan Program of Shanghai Xuhui District Health Commission (Award Number: SHXHZDXK202325, Recipient: Bihua Chen) and the General Program of Shanghai Xuhui District Health Commission and Xuhui District Science and Technology Commission (Award Number: SHXH202409, Recipient: Jiali Zhang). Declaration of generative AI use: The authors utilized AI to edit portions of the work to enhance the fluency of the reporting. IRB approval declaration: The study was registered in the Chinese Clinical Trial Registry (ChiCTR2000029022) on January 11, 2020 and had ethical approval from the Shanghai Ethics Committee for Clinical Research (Approval Number: SECCR/2019-43). Human Ethics and Consent to Participate declaration: Informed consent was obtained from all individual participants (mothers) included in the study, and from the parents or legal guardians of all child participants. Consent to Publish declaration: All authors have reviewed and approved the final version of the manuscript for submission. Competing Interest declaration: None References BIAN, X.-y., Jane, S., LU, H.-m., Yl, Y., WANG, G.-w., XU, R.-c., SONG, W., ZHANG, J., 2021. Study on the norm and the reliability of the second edition of the Ages & Stages Questionnaires: Social-Emotional with a Chinese national sample. Chinese Journal of Child Health Care 29, 23-27. Bian, X., Xie, H., Squires, J., Chen, C.-Y., 2017. Adapting a Parent-Completed, Socioemotional Questionnaire in China: The Ages & Stages Questionnaires: Social-Emotional. Infant Mental Health Journal 38, 258-266. Briggs-Gowan, M.J., Carter, A.S., 2008. Social-Emotional Screening Status in Early Childhood Predicts Elementary School Outcomes. Pediatrics 121, 957-962. Briggs-Gowan, M.J., Carter, A.S., Skuban, E.M., Horwitz, S.M., 2001. Prevalence of Social-Emotional and Behavioral Problems in a Community Sample of 1- and 2-Year-Old Children. Journal of the American Academy of Child & Adolescent Psychiatry 40, 811-819. Briggs, R.D., Stettler, E.M., Silver, E.J., Schrag, R.D.A., Nayak, M., Chinitz, S., Racine, A.D., 2012. Social-Emotional Screening for Infants and Toddlers in Primary Care. Pediatrics 129, e377-e384. Falster, K., Hanly, M., Banks, E., Lynch, J., Chambers, G., Brownell, M., Eades, S., Jorm, L., 2018. Maternal age and offspring developmental vulnerability at age five: A population-based cohort study of Australian children. PLOS Medicine 15. Gaudet, B., Letourneau, N., 2015. Socioeconomic Status and Social-Emotional Development of Children from Birth to 36 Months of Age: A Systematic Narrative Review, In: Wright, J.D. (Ed.), International Encyclopedia of the Social & Behavioral Sciences (Second Edition). Elsevier, Oxford, pp. 942-948. Guoyan, L., 2008. A Study on the Factors Affecting the Social-Emotional Development of Toddlers at the Age of 12 to 36 Months in China. Huazhong University of Science and Technology. Hu, S., Li, L., Yuan, Y., Zhang, Y., Xuan, J., Xu, X., Qiu, H., Zhou, C., Zhang, Y., Liu, X., Yu, X., 2025. Effects of allergic diseases on social-emotional development in children at 12 months of age: A Prospective Cohort Study. Journal of Affective Disorders 374, 171-178. Hui, C., Shuangqin, Y., Guopeng, G., Sumei, W., Liangliang, X., Liu, J., Fangfang, X., Fangbiao, T., 2024. Correlation of early parent-child interaction and sleep time with emotional and behavioral problems in preschool children. Chinese Journal of Child Health Care 32, 785-789. Hysing, M., Sivertsen, B., Garthus-Niegel, S., Eberhard-Gran, M., 2016. Pediatric sleep problems and social-emotional problems. A population-based study. Infant Behavior and Development 42, 111-118. Junge, K., Schmerse, D., Lankes, E.-M., Carstensen, C.H., Steffensky, M., 2021. How the home learning environment contributes to children's early science knowledge—Associations with parental characteristics and science-related activities. Early Childhood Research Quarterly 56, 294-305. Li, F., Cui, Y., Li, Y., Guo, L., Ke, X., Liu, J., Luo, X., Zheng, Y., Leckman, J.F., 2022. Prevalence of mental disorders in school children and adolescents in China: diagnostic data from detailed clinical assessments of 17,524 individuals. Journal of Child Psychology and Psychiatry 63, 34-46. Maruyama, J.M., Pastor-Valero, M., Santos, I.S., Munhoz, T.N., Barros, F.C., Matijasevich, A., 2019. Impact of maternal depression trajectories on offspring socioemotional competences at age 11: 2004 Pelotas Birth Cohort. Journal of Affective Disorders 253, 8-17. McDonald, S.W., Kehler, H.L., Tough, S.C., 2018. Risk factors for delayed social‐emotional development and behavior problems at age two: Results from the All Our Babies/Families (AOB/F) cohort. Health Science Reports 1. McIntosh, J.E., Olsson, C.A., Schuijers, M., Tan, E.S., Painter, F., Schnabel, A., LeBas, G., Higgs-Howarth, S., Benstead, M., Booth, A.T., Hutchinson, D., 2021. Exploring Perinatal Indicators of Infant Social-Emotional Development: A Review of the Replicated Evidence. Clinical Child and Family Psychology Review 24, 450-483. Pontoppidan, M., Niss, N.K., Pejtersen, J.H., Julian, M.M., Væver, M.S., 2017. Parent report measures of infant and toddler social-emotional development: a systematic review. Family Practice 34, 127-137. Rogers, A., Obst, S., Teague, S.J., Rossen, L., Spry, E.A., Macdonald, J.A., Sunderland, M., Olsson, C.A., Youssef, G., Hutchinson, D., 2020. Association Between Maternal Perinatal Depression and Anxiety and Child and Adolescent Development. JAMA Pediatrics 174. Rotheram-Fuller, E.J., Tomlinson, M., Scheffler, A., Weichle, T.W., Hayati Rezvan, P., Comulada, W.S., Rotheram-Borus, M.J., 2018. Maternal patterns of antenatal and postnatal depressed mood and the impact on child health at 3-years postpartum. Journal of Consulting and Clinical Psychology 86, 218-230. Schmiedeberg, C., Schumann, N., 2019. Poverty and Adverse Peer Relationships among Children in Germany: a Longitudinal Study. Child Indicators Research 12, 1717-1733. Sivertsen, B., Harvey, A.G., Reichborn-Kjennerud, T., Torgersen, L., Ystrom, E., Hysing, M., 2015. Later Emotional and Behavioral Problems Associated With Sleep Problems in Toddlers. JAMA Pediatrics 169. Stein, A., Pearson, R.M., Goodman, S.H., Rapa, E., Rahman, A., McCallum, M., Howard, L.M., Pariante, C.M., 2014. Effects of perinatal mental disorders on the fetus and child. The Lancet 384, 1800-1819. Sutcliffe, A.G., Barnes, J., Belsky, J., Gardiner, J., Melhuish, E., 2012. The health and development of children born to older mothers in the United Kingdom: observational study using longitudinal cohort data. Bmj 345, e5116-e5116. Tearne, J.E., 2015. Older maternal age and child behavioral and cognitive outcomes: a review of the literature. Fertility and Sterility 103, 1381-1391. Vasileva, M., Graf, R.K., Reinelt, T., Petermann, U., Petermann, F., 2021. Research review: A meta-analysis of the international prevalence and comorbidity of mental disorders in children between 1 and 7 years. J Child Psychol Psychiatry 62, 372-381. Vondra, J.I., Shaw, D.S., Swearingen, L., Cohen, M., Owens, E.B., 2001. Attachment stability and emotional and behavioral regulation from infancy to preschool age. Development and Psychopathology 13, 13-33. Yong, G.H., Lin, M.-H., Toh, T.-H., Marsh, N.V., 2023. Social-Emotional Development of Children in Asia: A Systematic Review. Behavioral Sciences 13. Yuan-yuan, Z., Xingming, J., Xiao-yan, B., Sha-sha, W., Yong-shuang, F., Jin-jin, C., 2020. Study on Shanghai urban toddlers’ social-emotional development and related influencing factors. Chinese Journal of Child Health Care 28. Yuying, X., Chenming, G., Fangxuan, M., Xi, Z., Liping, Y., Jiali, D., 2024. Study on the correlation between home rearing environment and social emotional competence of infants and toddlers. Chinese Journal of Child Health Care 32, 559-565. Zhang, M., He, Y., 2015. Psychiatric Assessment Scale Manual. Hunan Science and Technology Press, Changsha. Zhang, T., Luo, Z.-C., Ji, Y., Chen, Y., Ma, R., Fan, P., Tang, N., Li, J., Tian, Y., Zhang, J., Ouyang, F., 2023. The impact of maternal depression, anxiety, and stress on early neurodevelopment in boys and girls. Journal of Affective Disorders 321, 74-82. Tables Table 1. Characteristics of the Study Population in Shanghai, China (N=419) Characteristics Overall (N=419) Maternal Age at Delivery (years) Mean (SD) 32.2 (3.52) Educational Level High school and below 33 (7.9%) Junior college/university 261 (62.3%) Master and above 125 (29.8%) Pre-pregnancy BMI ( kg/m 2 ) =28 8 (1.9%) Household Annual Income (RMB) =1000,000 8 (1.9%) Owning Pet 88 (21.0%) Hemoglobin Concentration at First Prenatal Visit (g/L) 125.4 (9.74) Having High-risk Situation during Pregnancy 288 (68.7%) Having Supplemented Folic Acid or Assisted Fertility Drugs Before Pregnancy 205 (48.9%) Gestational Weight Gain Inadequate 37 (8.8%) Normal 200 (47.7%) Excessive 182 (43.4%) Newborn Birth Weight (g) 3364.69 (375.99) Average Daily Sleep Duration of Infants at 1-year-old (hours) 12.65 (1.06) Table 2. Distribution of GAD-7 and PHQ-9 Scores in Different Stages of Pregnancy and Postpartum Period. Time Points during Pregnancy and Postpartum 0-4 None 5-9 Mild 10-14 Moderate ≥ 15 Severe GAD-7 PHQ-9 GAD-7 PHQ-9 GAD-7 PHQ-9 GAD-7 PHQ-9 Second Trimester (n=418) 372 (89.0%) 367 (87.8%) 37 (8.9%) 42 (10.0%) 9 (2.2%) 7 (1.7%) 0 (0.0%) 2 (0.5%) Third Trimester (n=419) 378 (90.2%) 366 (87.4%) 35 (8.4%) 46 (11.0%) 4 (1.0%) 6 (1.4%) 2 (0.5%) 1 (0.2%) 2 Weeks Postpartum (n=419) 380 (90.7%) 382 (91.2%) 34 (8.1%) 34 (8.1%) 5 (1.2%) 3 (0.7%) 0 (0.0%) 0 (0.0%) 6 Weeks Postpartum (n=419) 372 (88.8%) 385 (91.9%) 35 (8.4%) 24 (5.7%) 9 (2.1%) 6 (1.4%) 3 (0.7%) 4 (1.0%) 18 Months Postpartum (n=415) 385 (92.8%) 383 (92.3%) 24 (5.8%) 27 (6.5%) 6 (1.4%) 5 (1.2%) 0 (0.0%) 0 (0.0%) Table 3 . GSM (Logistic Linear Regression) Coefficients Variable s Coefficient Std. Error Z-score Maternal Age at Delivery -0.07 8.34E-4 -82.60 Maternal Educational Level -0.45 0.006 -78.90 GAD-7 Score at 18 Months Postpartum 0.74 0.009 79.50 PHQ-9 Score at 18 Months Postpartum 1.34 0.010 130.00 Average Daily Sleep Duration of Infants at 1-year-old -0.08 0.002 -44.60 Constant 4.13 0.035 117.00 When using a global surrogate model to interpret XGBoost, the P-value is not a primary concern, as the goal is to "mimic" and explain the predictive behavior of the XGBoost model rather than to infer the true real-world relationships of the variables. Therefore, hypothesis testing is not necessary; the focus is on the regression coefficients, which directly reflect the direction and strength of the features' influence. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 20 Dec, 2025 Reviewers agreed at journal 20 Dec, 2025 Reviewers invited by journal 12 Dec, 2025 Editor invited by journal 14 Nov, 2025 Editor assigned by journal 13 Nov, 2025 Submission checks completed at journal 13 Nov, 2025 First submitted to journal 07 Nov, 2025 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-8060925","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":560677014,"identity":"b991dc2b-7149-4e9e-a396-099336972144","order_by":0,"name":"Hualong Yuan","email":"","orcid":"","institution":"Fenglin Community Health Service Center in Xuhui District","correspondingAuthor":false,"prefix":"","firstName":"Hualong","middleName":"","lastName":"Yuan","suffix":""},{"id":560677015,"identity":"85059046-5aac-44be-82d9-68e64cc05ad2","order_by":1,"name":"Yuechen Lou","email":"","orcid":"","institution":"Baoshan District Health Commission","correspondingAuthor":false,"prefix":"","firstName":"Yuechen","middleName":"","lastName":"Lou","suffix":""},{"id":560677017,"identity":"3ca88efa-b2ac-42b7-966e-099d971d9db3","order_by":2,"name":"Bihua Chen","email":"","orcid":"","institution":"Fenglin Community Health Service Center in Xuhui District","correspondingAuthor":false,"prefix":"","firstName":"Bihua","middleName":"","lastName":"Chen","suffix":""},{"id":560677019,"identity":"0a96c537-eb1b-474a-896b-4592b1e8f80a","order_by":3,"name":"Jiali Zhang","email":"","orcid":"","institution":"Fenglin Community Health Service Center in Xuhui District","correspondingAuthor":false,"prefix":"","firstName":"Jiali","middleName":"","lastName":"Zhang","suffix":""},{"id":560677020,"identity":"c37609b3-f87c-4eee-be42-e70189821034","order_by":4,"name":"Weiming Tang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/0lEQVRIie3OMWsCMRTA8RcOvCXQNR3uO1QCgXJav8odgi455w5qA8V0Kq79GJ1CR+XAW879OhUpdOkNWV1qL0c6Rh0L5j88XuD9IAA+378MCUj+dt0+24LTBJv15TxiMyTA55Cb4nHxunubwSDc5t993osEydYa7uNUuEi5llVaFoDxZBRnakQFmQwJlGMnYVXaELlpPsYZzVSeCsIZIJm7ycfOkqua0Vt1sOTnCKmQIVPAhNNPpFaWCDcZlO3HVoCrmqFnNaQS15QkmzF1keun4ut9L+cQLjnVe3UXLUPe1XoaRy5iyx+agw4xa8eM5Pi5aW5GoE8f+nw+3yX2CzcAXXPmklgsAAAAAElFTkSuQmCC","orcid":"","institution":"University of North Carolina at Chapel Hill","correspondingAuthor":true,"prefix":"","firstName":"Weiming","middleName":"","lastName":"Tang","suffix":""}],"badges":[],"createdAt":"2025-11-08 02:53:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8060925/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8060925/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98753265,"identity":"72a641e9-1cc3-4e34-9f9a-a177b428e445","added_by":"auto","created_at":"2025-12-22 09:21:06","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":85902,"visible":true,"origin":"","legend":"","description":"","filename":"Figures7Oct2025.docx","url":"https://assets-eu.researchsquare.com/files/rs-8060925/v1/f476ea46ef82d30c3c2f69df.docx"},{"id":98777221,"identity":"0a55fd16-2da7-484f-adad-483831c3b1c3","added_by":"auto","created_at":"2025-12-22 12:26:04","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19801,"visible":true,"origin":"","legend":"","description":"","filename":"Tables7Oct2025.docx","url":"https://assets-eu.researchsquare.com/files/rs-8060925/v1/1743e062bbe7642ae847c5f7.docx"},{"id":98778422,"identity":"addd7360-865b-4f48-b855-07431ee06961","added_by":"auto","created_at":"2025-12-22 12:29:14","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":69577,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript10Nov20252.docx","url":"https://assets-eu.researchsquare.com/files/rs-8060925/v1/3308a445acd19903d7976499.docx"},{"id":98779280,"identity":"fcfc726c-214d-4712-9b48-0c1764e6b8d9","added_by":"auto","created_at":"2025-12-22 12:30:08","extension":"json","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6866,"visible":true,"origin":"","legend":"","description":"","filename":"454135d4186e4d26965ce2c6fbff848d.json","url":"https://assets-eu.researchsquare.com/files/rs-8060925/v1/d413165027bd3d8b6a69e301.json"},{"id":98778975,"identity":"a23bce3f-c01e-412f-a233-8610317a482e","added_by":"auto","created_at":"2025-12-22 12:29:51","extension":"xml","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":97379,"visible":true,"origin":"","legend":"","description":"","filename":"454135d4186e4d26965ce2c6fbff848d1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8060925/v1/43fc00c7755e7db599c179b3.xml"},{"id":98753269,"identity":"971c5aa2-9422-4b34-b0a3-40f6decf91fb","added_by":"auto","created_at":"2025-12-22 09:21:06","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55336,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8060925/v1/765fd2d5248c80fde5d06345.png"},{"id":98753267,"identity":"a06ee7b7-0fbc-45cd-80ae-8b5abc5838f3","added_by":"auto","created_at":"2025-12-22 09:21:06","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":286343,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8060925/v1/d6f8f7edda97d05737ef3296.jpeg"},{"id":98777859,"identity":"6b5febbd-b0e9-4768-a74f-1e872fb72a7f","added_by":"auto","created_at":"2025-12-22 12:28:34","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24698,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8060925/v1/6a755ab5829d93063ec45de8.png"},{"id":98753266,"identity":"434471c7-772c-4177-a5b6-b1fcf2eb3176","added_by":"auto","created_at":"2025-12-22 09:21:06","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":50859,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8060925/v1/b21642f35a06e9bc9a317a00.png"},{"id":98779153,"identity":"b5d30e62-a16a-46a0-875a-9ad6d5eefa41","added_by":"auto","created_at":"2025-12-22 12:30:00","extension":"xml","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":96124,"visible":true,"origin":"","legend":"","description":"","filename":"454135d4186e4d26965ce2c6fbff848d1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8060925/v1/411740d57e3983254628d733.xml"},{"id":98753273,"identity":"dcfaafd5-f0e1-4344-a04b-032abd270326","added_by":"auto","created_at":"2025-12-22 09:21:06","extension":"html","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":103921,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8060925/v1/08117bc8fe3285339d63e4df.html"},{"id":98753260,"identity":"85809525-99b8-411a-880e-9e3225d56fac","added_by":"auto","created_at":"2025-12-22 09:21:06","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":99145,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eFlow Diagram of the study subjects selection procedure\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-8060925/v1/7586aa33958504bfd8c9d0e0.png"},{"id":98753261,"identity":"1752d159-ca8c-4238-a3b9-42739d73790d","added_by":"auto","created_at":"2025-12-22 09:21:06","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":112679,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eThe ROC curve of the final selected model\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-8060925/v1/76d4b0b93c4bb9591a6bb1ed.png"},{"id":98784645,"identity":"b5740e54-23c1-425f-8994-876621847573","added_by":"auto","created_at":"2025-12-22 12:43:05","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1224799,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8060925/v1/33616590-c5a9-40dd-a1e1-bce5cb9477ea.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Building a Prediction Model for Children's Social-emotional Development: A Community- Based Cohort in Shanghai, China","fulltext":[{"header":"Introduction","content":"\u003cp\u003eSocial-emotional development (SED) refers to the capacity of individuals, especially young children, to identify and manage their own feelings, form relationships, and learn from interactions with others (Gaudet and Letourneau, \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e2015\u003c/span\u003e). As a foundation for human development, SED plays a crucial role in shaping cognitive abilities and mental health outcomes throughout life, equipping children to manage relationships, regulate emotions, and develop lifelong mental health skills (Gaudet and Letourneau, \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e2015\u003c/span\u003e; Yong et al., \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). Globally, 7\u0026ndash;24% of children under 3 years exhibit parent-reported social-emotional difficulties, with a median prevalence of 10% (Briggs-Gowan et al., \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e2001\u003c/span\u003e; Briggs et al., \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e2012\u003c/span\u003e). Longitudinal evidence from Shanghai, China (2018\u0026ndash;2021) indicates 8.4% of 12-month-old manifest SED concerns (Hu et al., \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e2025\u003c/span\u003e), and such deficits significantly elevate risks for behavioral disorders, learning impairments, and adolescent psychopathology (Briggs-Gowan and Carter, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e2008\u003c/span\u003e). SED in the early years also predicts the mental health status in adulthood (Bian et al., \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2017\u003c/span\u003e), which is a strong concern for childhood development. For example, a systematic and meta-analysis, incorporating 18,282 children ages 12\u0026ndash;83 months from 8 countries, reported 20.1% of children under 7 years experiencing mental disorders (Vasileva et al., \u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e2021\u003c/span\u003e), while Chinese epidemiological studies, involving 73,992 children and adolescents aged 6\u0026ndash;16 across five provinces, documented 17.5% prevalence (Li et al., \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e2022\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eThe association between maternal mental health and offspring SED is well-established in developmental research\u0026mdash;with evidence linking perinatal mental health disturbances to long-term offspring SED impairments even into adolescence (Maruyama et al., \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e2019\u003c/span\u003e; Rogers et al., \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; Stein et al., \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e2014\u003c/span\u003e). However, three critical knowledge gaps persist, limiting the development of contextually valid SED prediction models, particularly for Asian populations. First, Asian cohorts remain substantially underrepresented in global studies of offspring SED (Yong et al., \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2023\u003c/span\u003e), and existing predictive frameworks are predominantly derived from Western populations. Yet Asia\u0026rsquo;s unique context may modulate the predictive value of variables commonly included in Western SED models. This gap raises uncertainty about whether existing models can reliably forecast SED outcomes for Asian children, highlighting the need for region-specific prediction frameworks. Second, current predictive models for offspring SED have overlooked key modifiable variables that may contribute to prediction accuracy. For instance, infant sleep patterns and household pet ownership (a potential source of child social interaction) have rarely been integrated into SED prediction models. Third, and most centrally, the relative predictive weight of prenatal versus postnatal maternal mental health exposures on offspring SED remains contested. While perinatal mental health is a key determinant (e.g., maternal depression affecting 11.1% of Shanghai mothers correlates with impaired child emotion recognition and reduced social interaction, severely hindering the normal development of children\u0026rsquo;s social-emotional abilities(Zhang et al., \u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e2023\u003c/span\u003e)). Some scholars argue that maternal postpartum depression is more influential due to reduced daily interactions and a higher frequency of corporal punishment (Rotheram-Fuller et al., \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e2018\u003c/span\u003e). In contrast, accumulating evidence suggests that prenatal maternal stress exposure has been shown to have enduring consequences on brain development in the offspring, including abnormal brain structure and circuitry, as well as long-term neurodevelopmental impairments (Leis et al., 2014; Van den Bergh et al., 2018; Wu et al., 2022).\u003c/p\u003e \u003cp\u003eThe aim of this study is to develop a comprehensive predictive model for SED in 18-month-old children by addressing these gaps\u0026mdash;specifically, by centering an Asian cohort (Shanghai, China), integrating underexplored predictors, and clarifying the timing-specific effects of maternal mental health\u0026mdash;while also contributing to a robust, regionally tailored SED prediction framework.\u003c/p\u003e"},{"header":"Methods","content":"\u003cp\u003e\u003cstrong\u003e\u003cem\u003eStudy Design\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis prospective cohort study was conducted at the Fenglin Community Health Service Center (FCHC) in Xuhui District, Shanghai. Pregnant women who registered at FCHC, from February 18, 2020, to April 19, 2021, were enrolled. Face-to-face interviews were conducted at the time of pregnancy registration to collect basic information and establish one-to-one relationships through WeChat (the most popular instant message application in China) to know the perinatal situation in real time. Then we followed up the participants in the second and third trimester, 2 weeks, 6 weeks, and 18 months after childbirth to collect information on the psychological status of the pregnant women. We also followed up with their offspring to observe their sleeping conditions and developmental status until they were 18 months old.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe study was registered in the Chinese Clinical Trial Registry (ChiCTR2000029022) on January 11, 2020 and had ethical approval from the Shanghai Ethics Committee for Clinical Research (Approval Number: SECCR/2019-43). Informed consent was obtained from all individual participants (mothers) included in the study, and from the parents or legal guardians of all child participants.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eStudy Population\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study participants comprised the\u0026nbsp;mother-infant dyads with term singleton births (\u0026ge;37 gestational weeks) from the FCHC cohort. Exclusions applied to: (1) families who withdrew from the study, or (2) failed to complete developmental assessments during follow-up.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003ePredictive Variables\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e21 predictive variables were selected based on literature review, including: maternal age, educational level, pre-pregnancy Body Mass Index (BMI), annual family income, owning pet, hemoglobin concentration at first prenatal visit (g/L), having any factors during pregnancy that could lead to a high-risk situation (such as being too young (\u0026lt;18 years old) or too old (\u0026ge;35 years old), having a multiple pregnancy, having diabetes, hypertension, or heart disease, having a history of multiple miscarriages, preterm births, etc.), pre-pregnancy folic acid or assisted conception drug supplementation, gestational weight gain value, newborn birth weight, average daily sleep duration of infants at 1-year-old, Generalized Anxiety Disorder-7 (GAD-7) and Patient Health Questionnaire-9 (PHQ-9) scores at 5 time points (the second trimester, the third trimester, 2 weeks postpartum, 6 weeks postpartum, and 18 months postpartum).\u003c/p\u003e\n\u003cp\u003ePatient Health Questionnaire-9 (PHQ-9), consists of 9 items, with a 4-point scale ranging from 0 to 3, according to the frequency of symptoms in the past 2 weeks. The total score ranges from 0 to 27 points, and can be used to assess the severity of depressive symptoms: 0-4 points are without depression, 5-9 points are mild, 10-14 points are moderate, and 15 points and above are severe. Internal reliability was excellent (Cronbach\u0026rsquo;s alpha = 0.89) (Zhang and He, 2015).\u003c/p\u003e\n\u003cp\u003eGeneralized Anxiety Disorder-7 (GAD-7), consisting of 7 items, is scored on a 4-point scale from 0 to 3, with a total score range of 0 to 21. GAD-7 is measured by the frequency of symptoms in the past 2 weeks, and can be used to assess the severity of anxiety symptoms: 0-4 anxiety-free, 5-9 mild, 10-14 moderate, 15 or above severe. Internal reliability was excellent (Cronbach\u0026rsquo;s alpha = 0.92) (Zhang and He, 2015).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eOutcome\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe social-emotional developmental status of offspring at 18 months is the outcome, measured using the Ages \u0026amp; Stages Questionnaires: Social-Emotional, Second Edition (ASQ:SE-2). It is a standardized developmental screening instrument that has been successfully studied in different countries, including China, as one of the most comprehensive and psychometrically sound measures of infant and toddler social-emotional development (Pontoppidan et al., 2017). The Chinese version of the measurement tool has been validated, with Cronbach\u0026apos;s alpha coefficient for the 18-month Chinese version questionnaire of 0.84 (BIAN et al., 2021).\u0026nbsp;ASQ:SE-2\u0026nbsp;assesses seven areas: self-regulation, compliance, communication, adaptive functioning, autonomy, affect, and interaction with people. In our study, we utilized the ASQ Chinese Online System, an online platform for questionnaire administration, scoring, and data management developed by Shanghai Zhangyuan Information Technology Co., Ltd. Upon completion of the questionnaire by parents, the system automatically scores responses and generates screening outcomes by comparing them with norms for Chinese children. Results are categorized into three developmental domains: below the threshold (\u0026lt; the 75th percentile, indicating typical development), close to the threshold (\u0026ge; the 75th percentile, but \u0026lt; the 90th percentile, suggesting potential developmental concerns), or above the threshold (\u0026ge; the 90th percentile, indicating significant risk of developmental delay). For our study, participants were categorized into two groups: a normal group (\u0026lt; the 75th percentile) and a delayed group (\u0026ge; the 75th percentile).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eMethodology of Data Analysis\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eWe utilized KNIME Analytics Platform V5.3 to build a predictive model. The Extreme Gradient Boosting (XGBoost) algorithm was applied to perform feature selection and to identify key predictive variables. Then, we interpreted the XGBoost model\u0026apos;s behavior with a Global Surrogate Model (GSM, in this case, Logistic Regression Model) to explore the relationship between the key predictive variables and the target variable.\u003c/p\u003e\n\u003cp\u003eAfter preparing the data by addressing missing values, removing highly-correlated variables and extreme outliers we proceeded with modeling and evaluation.\u003c/p\u003e\n\u003cp\u003e1. Feature Selection and Data Modeling Using the XGBoost Algorithm: A feature selection loop was established: 70% of the samples were randomly selected as the training set, and after being balanced by the SMOTE (Synthetic Minority Oversampling Technique) algorithm, the XGBoost algorithm was used to train the model. The remaining 30% of the samples served as the test set, which was input into the generated model for prediction. The predicted values were compared with the actual values to calculate Cohen\u0026apos;s Kappa value. Using the backward feature elimination method, new models were continuously built by gradually reducing the predictor variables, and the above evaluation was repeated until the Kappa value no longer improved. The model with a Kappa value equal to or greater than 0.8 and the fewest predictor variables was selected. We take the predictive variables of this model as the key predictive variables.\u003c/p\u003e\n\u003cp\u003e2. Interpreting the XGBoost Model\u0026apos;s Behavior with a Global Surrogate Model (GSM): As a machine learning method, XGBoost does not intuitively provide the relationship between input variables and the target variable. Therefore, an interpretable mimetic model (in this case, Logistic Linear Regression) was used to fit the prediction results of the complex model, thereby approximating and explaining its behavior. The reference category for the output variable was set to \u0026quot;0,\u0026quot; so the probability of \u0026quot;1\u0026quot; represents the probability of abnormal socio-emotional development of the children.\u003c/p\u003e"},{"header":"Results","content":"\u003cp\u003e\u003cstrong\u003e\u003cem\u003eBaseline characteristics\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA total of 544 pregnant women were initially enrolled in the cohort study, among which, 26 participants withdrew during pregnancy, and 29 cases were excluded due to pregnancy loss. An additional 36 cases were excluded owing to preterm birth or twins, resulting in 453 eligible mother-child dyads. Subsequently, 34 pairs were excluded due to incomplete ASQ: SE-2 assessments at the 18-month follow-up, with a loss to follow-up rate of 7.5%, resulting in 419 mother-child dyads in the prediction model (Figure 1).\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eCharacteristics of the study population are shown in Table 1. The mean delivery age was 32.2 years (SD=3.5). The majority of women (92.1%) had a junior college or university education or above. Most of the population had a pre-pregnancy BMI within the normal range (18.5-24, 69.7%). Overall, 60.6% of the participants reported a household annual income (the participant and their spouse) ranging from 200,000 to 500,000 Chinese Yuan (CNY) pre-tax. Pet ownership was reported by 88 individuals (21.0%). The mean hemoglobin concentration at the first prenatal visit was 125.4 g/L (SD=9.74). Overall, 288 (68.7%) had a high-risk situation during pregnancy. Preconceptionally use of folic acid supplements or assisted fertility drugs was reported in 205 cases (48.9%). Gestational weight gain showed three patterns: 37 participants (8.8%) fell below the optimal range, 200 (47.7%) were within that range, and 182 (43.4%) exceeded that range. The mean birth weight of offspring was 3,364.69 g (SD=375.99), while infant sleep patterns at 1 year averaged 12.59 hours daily (SD=1.37).\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTable 2 shows the distribution of GAD-7 and PHQ-9 scores in different stages of pregnancy and the postpartum period. Scores of \u0026ge;10 (combining moderate [10\u0026ndash;14] and severe [\u0026ge;15] categories) showed distinct patterns across time points. For GAD-7, proportions were 2.2% (9 cases) in the second trimester, 1.4% (6 cases) in the third trimester, 1.2% (5 cases) at 2 weeks postpartum, 2.9% (12 cases) at 6 weeks postpartum, and 1.4% (6 cases) at 18 months postpartum. Similarly, PHQ-9 scores \u0026ge;10 were observed in 2.1% (9 cases) of participants in the second trimester, 1.7% (7 cases) in the third trimester, 0.7% (3 cases) at 2 weeks postpartum, 2.4% (10 cases) at 6 weeks postpartum, and 1.2% (5 cases) at 18 months postpartum.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eOutcome\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eRegarding social-emotional developmental status, 377 participants demonstrated typical development, while 42 (10.0%) children did not achieve an ideal level of development, requiring attention due to potential or significant developmental concerns.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003ePredictive Model\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eUsing \u0026ldquo;children\u0026rsquo;s social-emotional developmental status\u0026rdquo; as the target variable for feature selection, the final selected model\u0026apos;s Kappa value was 0.837. The identified key predictive variables were: maternal age at delivery (\u0026beta;=-0.07), maternal educational level (\u0026beta;=-0.45), infant\u0026apos;s average daily sleep duration at one year old (\u0026beta;=-0.08), and GAD-7 score (\u0026beta;=0.74) and PHQ-9 score (\u0026beta;=1.34) at 18 months postpartum (see Table 3).\u003c/p\u003e\n\u003cp\u003eMaternal age, educational level, and infant\u0026apos;s average daily sleep duration at 1-year-old were negatively correlated with the probability of delayed social-emotional developmental status in children. Higher maternal age, higher educational level, and adequate sleep at 1-year-old were associated with a lower probability of delayed social-emotional development. Conversely, maternal anxiety/depression status at 18 months postpartum were positively correlated with the probability of delayed social-emotional developmental status in children. Higher GAD-7 and PHQ-9 scores were associated with a higher likelihood of delayed social-emotional development.\u003c/p\u003e\n\u003cp\u003eThe ROC curve was used to evaluate the final selected model, with an AUC of 0.93, indicating a good predictive performance (see Figure 2).\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eBuilding a predictive model for children's social-emotional development will enable us to deliver tailored interventions that enhance their growth. This study extended the existing literature by developing a prediction model, using a longitudinal study design, and including psychological measures into consideration. The present study identified key modifiable predictors of SED abnormalities in 18-month-old children, highlighting the protective roles of maternal age, educational attainment, and infant sleep duration, as well as the risks associated with postpartum maternal anxiety and depression.\u003c/p\u003e \u003cp\u003eWe found that insufficient sleep in 1-year-old children was associated with an increased risk of SED abnormalities, which explicitly underscores the critical role of sleep in supporting neurodevelopment during early childhood. This result aligns closely with prior empirical evidence. For example, a previous study reported that children sleeping less than 11 hours per night were nearly five times more likely to develop social-emotional problems than those sleeping 13\u0026ndash;14 hours nightly (Hysing et al., \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e2016\u003c/span\u003e). Similarly, another study conducted in China noted that children with a daily total sleep time of \u0026lt;\u0026thinsp;12h/d had higher odds of experiencing emotional and behavioral difficulties (Hui et al., \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). Notably, this link between insufficient sleep and elevated SED risk is not limited to toddlerhood, while a study further confirmed it persists even into age 5 (Sivertsen et al., \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e2015\u003c/span\u003e), emphasizing sleep\u0026rsquo;s long-term impact on emotional development trajectories. These collective findings highlight that promoting healthy sleep practices in infancy\u0026mdash;such as establishing consistent bedtime routines, optimizing sleep environments, and adhering to age-appropriate sleep duration guidelines\u0026mdash;should be prioritized as a pivotal, actionable measure to foster optimal social-emotional development in children.\u003c/p\u003e \u003cp\u003eNotably, among the five timepoints at which we assessed maternal mental status\u0026mdash;the second trimester, third trimester, 2 weeks postpartum, 6 weeks postpartum, and 18 months postpartum\u0026mdash;only elevated GAD-7 and PHQ-9 scores at 18 months postpartum were identified as significant risk factors for offspring SED at the same age (18 months). This finding indicates that maternal mental status at 18 months postpartum, rather than during pregnancy or earlier postpartum stages, demonstrates a distinct association with children\u0026rsquo;s SED. More proximal negative mood appears to have a greater impact on children (Rotheram-Fuller et al., \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e2018\u003c/span\u003e). This is aligned with the existing literature, which demonstrates that maternal mental health status is closely linked to children's social-emotional and behavioral development (McDonald et al., \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e2018\u003c/span\u003e). The second year of life is marked by numerous key developmental transitions in children, including the emergence of secondary or self-conscious emotions, new self-regulatory and coping skills (Vondra et al., \u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e2001\u003c/span\u003e). The 12-18-month bracket is a sensitive period of development, within which attachment patterns and affect regulatory capacities become more consistent (McIntosh et al., \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e2021\u003c/span\u003e). Negative maternal emotions at 18 months postpartum likely affect maternal caregiving sensitivity (e.g., reduced eye contact, tactile interaction) and decrease attachment security with children, directly interfering with the acquisition of socioemotional skills (McIntosh et al., \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e2021\u003c/span\u003e; Rotheram-Fuller et al., \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e2018\u003c/span\u003e). These findings underscore that maternal mental health during this sensitive neurodevelopmental window (18 months postpartum) may disrupt parent-child interaction patterns essential for healthy socioemotional maturation, especially since mental status at earlier timepoints (pregnancy, 2\u0026ndash;6 weeks postpartum) did not show similar associations. This highlights the need for extended postpartum mental health monitoring beyond the perinatal period to support both maternal well-being and offspring SED.\u003c/p\u003e \u003cp\u003eOur results demonstrate that older maternal age is associated with reduced risks of social-emotional developmental abnormalities in offspring. This finding also aligns with developmental theories and empirical evidence from longitudinal studies. For instance, a UK-based cohort study found that there were fewer social and emotional difficulties associated with increasing maternal age (Sutcliffe et al., \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e2012\u003c/span\u003e). This may be attributed to older mothers\u0026rsquo; enhanced emotional maturity and parenting self-efficacy, which enable more responsive caregiving and consistent discipline (Tearne, \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e2015\u003c/span\u003e). Falster's population-based cohort study of 99,530 Australian children also revealed that compared to younger mothers, children born to mothers aged 30\u0026ndash;35 years exhibited the lowest risk of multi-domain developmental deficits, including social competence, emotional maturity, and communication skills (Falster et al., \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e2018\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eHigher maternal educational level is also a protective factor for the social-emotional development of offspring. Previous research has consistently demonstrated that maternal educational attainment exerts a profound influence on offspring's socio-emotional development (Guoyan, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2008\u003c/span\u003e; McIntosh et al., \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e2021\u003c/span\u003e; Schmiedeberg and Schumann, \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e2019\u003c/span\u003e; Yuan-yuan et al., \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; Yuying et al., \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). A multi-regional study covering 14 large and medium-sized cities across China has provided compelling evidence that higher maternal educational attainment exerts a significant promotive effect on children's socio-emotional development (Guoyan, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2008\u003c/span\u003e). Mothers with higher education levels are more likely to adopt reasoning-based parenting approaches, balance autonomy with secure attachment, and implement targeted emotional interventions, all of which contribute to healthier social development and emotional regulation in offspring (Guoyan, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2008\u003c/span\u003e; Junge et al., \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e2021\u003c/span\u003e; Yuying et al., \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). In Shanghai\u0026rsquo;s context, where educational achievement is highly prioritized, educated mothers may uniquely combine generational wisdom with contemporary parenting practices, creating a nurturing environment that mitigates both biological and cultural stressors on child development.\u003c/p\u003e \u003cp\u003eOur study has several limitations. First, while maternal mental status and children\u0026rsquo;s SED status were collected via validated self-report questionnaires, the absence of clinical diagnostic confirmation introduces potential measurement bias. Future research could triangulate self-reports with clinician-administered assessments. Second, the sample size, though adequately powered for initial explorations, may limit generalizability to broader populations. Third, our study design focused primarily on variables of mothers and children, which may have led to incomplete capture of fathers\u0026rsquo; factors (such as mental health) influencing the outcomes. Future research should prioritize collecting a more comprehensive set of current variables, such as fathers\u0026rsquo; psychological state.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eThis study underscores the importance of maternal factors and infant care in social-emotional development in early childhood. Our findings emphasize the need for tailored interventions that address maternal mental health and infant sleep patterns to enhance children\u0026apos;s mental health levels and social adaptation abilities. Future research should continue to explore strategies that mitigate developmental delays in at-risk populations.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAuthors\u0026apos; Statement:\u003c/strong\u003e Hualong Yuan: Methodology, Investigation, Data curation, Conceptualization, Writing -review \u0026amp; editing, Writing - original draft. Yuechen Lou: Validation, Methodology, Formal analysis, Data curation, Writing - review \u0026amp; editing, Writing - original draft. Bihua chen: Resources, Project administration, Investigation, Writing - review \u0026amp; editing. Jiali Zhang: Supervision, Funding acquisition, Conceptualization, Writing -review \u0026amp; editing, Writing - original draft. Weiming Tang: Supervision, Investigation, Data curation, Conceptualization, Writing - review \u0026amp; editing, Writing - original draft.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgments\u003c/strong\u003e: The authors thank all the study participants who contributed to this study.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding:\u003c/strong\u003e This study was supported by the Gaoyuan Program of Shanghai Xuhui District Health Commission (Award Number: SHXHZDXK202325, Recipient: Bihua Chen) and the General Program of Shanghai Xuhui District Health Commission and Xuhui District Science and Technology Commission (Award Number: SHXH202409, Recipient: Jiali Zhang).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eDeclaration of generative AI use:\u0026nbsp;\u003c/strong\u003eThe authors utilized AI to edit portions of the work to enhance the fluency of the reporting.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eIRB approval declaration:\u003c/strong\u003e The study was registered in the Chinese Clinical Trial Registry (ChiCTR2000029022) on January 11, 2020 and had ethical approval from the Shanghai Ethics Committee for Clinical Research (Approval Number: SECCR/2019-43).\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eHuman Ethics and Consent to Participate declaration:\u003c/strong\u003e Informed consent was obtained from all individual participants (mothers) included in the study, and from the parents or legal guardians of all child participants.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent to Publish declaration:\u003c/strong\u003e All authors have reviewed and approved the final version of the manuscript for submission.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting Interest declaration:\u003c/strong\u003e None\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eBIAN, X.-y., Jane, S., LU, H.-m., Yl, Y., WANG, G.-w., XU, R.-c., SONG, W., ZHANG, J., 2021. Study on the norm and the reliability of the second edition of the Ages \u0026amp; Stages Questionnaires: Social-Emotional with a Chinese national sample. Chinese Journal of Child Health Care 29, 23-27.\u003c/li\u003e\n\u003cli\u003eBian, X., Xie, H., Squires, J., Chen, C.-Y., 2017. Adapting a Parent-Completed, Socioemotional Questionnaire in China: The Ages \u0026amp; Stages Questionnaires: Social-Emotional. Infant Mental Health Journal 38, 258-266.\u003c/li\u003e\n\u003cli\u003eBriggs-Gowan, M.J., Carter, A.S., 2008. Social-Emotional Screening Status in Early Childhood Predicts Elementary School Outcomes. Pediatrics 121, 957-962.\u003c/li\u003e\n\u003cli\u003eBriggs-Gowan, M.J., Carter, A.S., Skuban, E.M., Horwitz, S.M., 2001. Prevalence of Social-Emotional and Behavioral Problems in a Community Sample of 1- and 2-Year-Old Children. Journal of the American Academy of Child \u0026amp; Adolescent Psychiatry 40, 811-819.\u003c/li\u003e\n\u003cli\u003eBriggs, R.D., Stettler, E.M., Silver, E.J., Schrag, R.D.A., Nayak, M., Chinitz, S., Racine, A.D., 2012. Social-Emotional Screening for Infants and Toddlers in Primary Care. Pediatrics 129, e377-e384.\u003c/li\u003e\n\u003cli\u003eFalster, K., Hanly, M., Banks, E., Lynch, J., Chambers, G., Brownell, M., Eades, S., Jorm, L., 2018. Maternal age and offspring developmental vulnerability at age five: A population-based cohort study of Australian children. PLOS Medicine 15.\u003c/li\u003e\n\u003cli\u003eGaudet, B., Letourneau, N., 2015. Socioeconomic Status and Social-Emotional Development of Children from Birth to 36 Months of Age: A Systematic Narrative Review, In: Wright, J.D. (Ed.), International Encyclopedia of the Social \u0026amp; Behavioral Sciences (Second Edition). Elsevier, Oxford, pp. 942-948.\u003c/li\u003e\n\u003cli\u003eGuoyan, L., 2008. A Study on the Factors Affecting the Social-Emotional Development of Toddlers at the Age of 12 to 36 Months in China. Huazhong University of Science and Technology.\u003c/li\u003e\n\u003cli\u003eHu, S., Li, L., Yuan, Y., Zhang, Y., Xuan, J., Xu, X., Qiu, H., Zhou, C., Zhang, Y., Liu, X., Yu, X., 2025. Effects of allergic diseases on social-emotional development in children at 12 months of age: A Prospective Cohort Study. Journal of Affective Disorders 374, 171-178.\u003c/li\u003e\n\u003cli\u003eHui, C., Shuangqin, Y., Guopeng, G., Sumei, W., Liangliang, X., Liu, J., Fangfang, X., Fangbiao, T., 2024. Correlation of early parent-child interaction and sleep time with emotional and behavioral problems in preschool children. Chinese Journal of Child Health Care 32, 785-789.\u003c/li\u003e\n\u003cli\u003eHysing, M., Sivertsen, B., Garthus-Niegel, S., Eberhard-Gran, M., 2016. Pediatric sleep problems and social-emotional problems. A population-based study. Infant Behavior and Development 42, 111-118.\u003c/li\u003e\n\u003cli\u003eJunge, K., Schmerse, D., Lankes, E.-M., Carstensen, C.H., Steffensky, M., 2021. How the home learning environment contributes to children\u0026apos;s early science knowledge\u0026mdash;Associations with parental characteristics and science-related activities. Early Childhood Research Quarterly 56, 294-305.\u003c/li\u003e\n\u003cli\u003eLi, F., Cui, Y., Li, Y., Guo, L., Ke, X., Liu, J., Luo, X., Zheng, Y., Leckman, J.F., 2022. Prevalence of mental disorders in school children and adolescents in China: diagnostic data from detailed clinical assessments of 17,524 individuals. Journal of Child Psychology and Psychiatry 63, 34-46.\u003c/li\u003e\n\u003cli\u003eMaruyama, J.M., Pastor-Valero, M., Santos, I.S., Munhoz, T.N., Barros, F.C., Matijasevich, A., 2019. Impact of maternal depression trajectories on offspring socioemotional competences at age 11: 2004 Pelotas Birth Cohort. Journal of Affective Disorders 253, 8-17.\u003c/li\u003e\n\u003cli\u003eMcDonald, S.W., Kehler, H.L., Tough, S.C., 2018. Risk factors for delayed social‐emotional development and behavior problems at age two: Results from the All Our Babies/Families (AOB/F) cohort. Health Science Reports 1.\u003c/li\u003e\n\u003cli\u003eMcIntosh, J.E., Olsson, C.A., Schuijers, M., Tan, E.S., Painter, F., Schnabel, A., LeBas, G., Higgs-Howarth, S., Benstead, M., Booth, A.T., Hutchinson, D., 2021. Exploring Perinatal Indicators of Infant Social-Emotional Development: A Review of the Replicated Evidence. Clinical Child and Family Psychology Review 24, 450-483.\u003c/li\u003e\n\u003cli\u003ePontoppidan, M., Niss, N.K., Pejtersen, J.H., Julian, M.M., V\u0026aelig;ver, M.S., 2017. Parent report measures of infant and toddler social-emotional development: a systematic review. Family Practice 34, 127-137.\u003c/li\u003e\n\u003cli\u003eRogers, A., Obst, S., Teague, S.J., Rossen, L., Spry, E.A., Macdonald, J.A., Sunderland, M., Olsson, C.A., Youssef, G., Hutchinson, D., 2020. Association Between Maternal Perinatal Depression and Anxiety and Child and Adolescent Development. JAMA Pediatrics 174.\u003c/li\u003e\n\u003cli\u003eRotheram-Fuller, E.J., Tomlinson, M., Scheffler, A., Weichle, T.W., Hayati Rezvan, P., Comulada, W.S., Rotheram-Borus, M.J., 2018. Maternal patterns of antenatal and postnatal depressed mood and the impact on child health at 3-years postpartum. Journal of Consulting and Clinical Psychology 86, 218-230.\u003c/li\u003e\n\u003cli\u003eSchmiedeberg, C., Schumann, N., 2019. Poverty and Adverse Peer Relationships among Children in Germany: a Longitudinal Study. Child Indicators Research 12, 1717-1733.\u003c/li\u003e\n\u003cli\u003eSivertsen, B., Harvey, A.G., Reichborn-Kjennerud, T., Torgersen, L., Ystrom, E., Hysing, M., 2015. Later Emotional and Behavioral Problems Associated With Sleep Problems in Toddlers. JAMA Pediatrics 169.\u003c/li\u003e\n\u003cli\u003eStein, A., Pearson, R.M., Goodman, S.H., Rapa, E., Rahman, A., McCallum, M., Howard, L.M., Pariante, C.M., 2014. Effects of perinatal mental disorders on the fetus and child. The Lancet 384, 1800-1819.\u003c/li\u003e\n\u003cli\u003eSutcliffe, A.G., Barnes, J., Belsky, J., Gardiner, J., Melhuish, E., 2012. The health and development of children born to older mothers in the United Kingdom: observational study using longitudinal cohort data. Bmj 345, e5116-e5116.\u003c/li\u003e\n\u003cli\u003eTearne, J.E., 2015. Older maternal age and child behavioral and cognitive outcomes: a review of the literature. Fertility and Sterility 103, 1381-1391.\u003c/li\u003e\n\u003cli\u003eVasileva, M., Graf, R.K., Reinelt, T., Petermann, U., Petermann, F., 2021. Research review: A meta-analysis of the international prevalence and comorbidity of mental disorders in children between 1 and 7 years. J Child Psychol Psychiatry 62, 372-381.\u003c/li\u003e\n\u003cli\u003eVondra, J.I., Shaw, D.S., Swearingen, L., Cohen, M., Owens, E.B., 2001. Attachment stability and emotional and behavioral regulation from infancy to preschool age. Development and Psychopathology 13, 13-33.\u003c/li\u003e\n\u003cli\u003eYong, G.H., Lin, M.-H., Toh, T.-H., Marsh, N.V., 2023. Social-Emotional Development of Children in Asia: A Systematic Review. Behavioral Sciences 13.\u003c/li\u003e\n\u003cli\u003eYuan-yuan, Z., Xingming, J., Xiao-yan, B., Sha-sha, W., Yong-shuang, F., Jin-jin, C., 2020. Study on Shanghai urban toddlers\u0026rsquo; social-emotional development and related influencing factors. Chinese Journal of Child Health Care 28.\u003c/li\u003e\n\u003cli\u003eYuying, X., Chenming, G., Fangxuan, M., Xi, Z., Liping, Y., Jiali, D., 2024. Study on the correlation between home rearing environment and social emotional competence of infants and toddlers. Chinese Journal of Child Health Care 32, 559-565.\u003c/li\u003e\n\u003cli\u003eZhang, M., He, Y., 2015. Psychiatric Assessment Scale Manual. Hunan Science and Technology Press, Changsha.\u003c/li\u003e\n\u003cli\u003eZhang, T., Luo, Z.-C., Ji, Y., Chen, Y., Ma, R., Fan, P., Tang, N., Li, J., Tian, Y., Zhang, J., Ouyang, F., 2023. The impact of maternal depression, anxiety, and stress on early neurodevelopment in boys and girls. Journal of Affective Disorders 321, 74-82.\u003c/li\u003e\n\u003c/ol\u003e"},{"header":"Tables","content":"\u003cp\u003e\u003cstrong\u003eTable 1. Characteristics of the Study Population in Shanghai, China (N=419)\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"580\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;Characteristics\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eOverall (N=419)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eMaternal Age at Delivery (years)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003eMean (SD)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e32.2 (3.52)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eEducational Level\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003eHigh school and below\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e33 (7.9%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003eJunior college/university\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e261 (62.3%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003eMaster and above\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e125 (29.8%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePre-pregnancy BMI (\u003c/strong\u003ekg/m\u003csup\u003e2\u003c/sup\u003e\u003cstrong\u003e)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e\u0026lt;18.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e64 (15.3%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e18.5-24\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e292 (69.7%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e24-28\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e55 (13.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e\u0026gt;=28\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e8 (1.9%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eHousehold Annual Income (RMB)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e\u0026lt;50,000\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e1 (0.2%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e50,000-100,000\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e16 (3.8%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e100,000-200,000\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e79 (18.9%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e200,000-500,000\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e254 (60.6%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e500,000-1000,000\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e61 (14.6%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e\u0026gt;=1000,000\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e8 (1.9%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eOwning Pet\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e88 (21.0%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eHemoglobin Concentration at First Prenatal Visit (g/L)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e125.4 (9.74)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eHaving High-risk Situation during Pregnancy\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e288 (68.7%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eHaving Supplemented Folic Acid or Assisted Fertility Drugs Before Pregnancy\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e205 (48.9%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eGestational Weight Gain\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003eInadequate\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e37 (8.8%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003eNormal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e200 (47.7%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003eExcessive\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e182 (43.4%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eNewborn Birth Weight (g)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e3364.69 (375.99)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 449px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eAverage Daily Sleep Duration of Infants at 1-year-old (hours)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 131px;\"\u003e\n \u003cp\u003e12.65 (1.06)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 2. Distribution of GAD-7 and PHQ-9 Scores in Different Stages of Pregnancy and Postpartum Period.\u003c/strong\u003e\u0026nbsp;\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"105%\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" style=\"width: 19px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTime Points during Pregnancy and Postpartum\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 20px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e0-4 None\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 20px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e5-9 Mild\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 19px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e10-14 Moderate\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 20px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026ge;\u003c/strong\u003e\u003cstrong\u003e15 Severe\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eGAD-7\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePHQ-9\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eGAD-7\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePHQ-9\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eGAD-7\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePHQ-9\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eGAD-7\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePHQ-9\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 19px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSecond Trimester (n=418)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e372\u0026nbsp;(89.0%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e367\u0026nbsp;(87.8%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e37\u0026nbsp;(8.9%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e42\u0026nbsp;(10.0%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e9\u0026nbsp;(2.2%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e7\u0026nbsp;(1.7%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e0\u0026nbsp;(0.0%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e2\u0026nbsp;(0.5%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 19px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eThird Trimester\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(n=419)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e378\u0026nbsp;(90.2%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e366\u0026nbsp;(87.4%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e35\u0026nbsp;(8.4%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e46\u0026nbsp;(11.0%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e4\u0026nbsp;(1.0%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e6\u0026nbsp;(1.4%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e2\u0026nbsp;(0.5%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e1\u0026nbsp;(0.2%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 19px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e2 Weeks Postpartum\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(n=419)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e380\u0026nbsp;(90.7%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e382\u0026nbsp;(91.2%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e34\u0026nbsp;(8.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e34\u0026nbsp;(8.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e5\u0026nbsp;(1.2%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e3\u0026nbsp;(0.7%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e0\u0026nbsp;(0.0%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e0\u0026nbsp;(0.0%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 19px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e6 Weeks Postpartum\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(n=419)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e372\u0026nbsp;(88.8%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e385\u0026nbsp;(91.9%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e35\u0026nbsp;(8.4%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e24\u0026nbsp;(5.7%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e9\u0026nbsp;(2.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e6\u0026nbsp;(1.4%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e3\u0026nbsp;(0.7%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e4\u0026nbsp;(1.0%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 19px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e18 Months Postpartum\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(n=415)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e385\u0026nbsp;(92.8%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e383\u0026nbsp;(92.3%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e24\u0026nbsp;(5.8%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e27\u0026nbsp;(6.5%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e6\u0026nbsp;(1.4%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e5\u0026nbsp;(1.2%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9px;\"\u003e\n \u003cp\u003e0\u0026nbsp;(0.0%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 10px;\"\u003e\n \u003cp\u003e0\u0026nbsp;(0.0%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003e3\u003c/strong\u003e\u003cstrong\u003e. GSM (Logistic Linear Regression) Coefficients\u003c/strong\u003e\u003c/p\u003e\n\u003cdiv align=\"center\"\u003e\n \u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"98%\"\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 50px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eVariable\u003c/strong\u003e\u003cstrong\u003es\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 16px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eCoefficient\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 17px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eStd. Error\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 15px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eZ-score\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 50px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eMaternal Age at Delivery\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 16px;\"\u003e\n \u003cp\u003e-0.07\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 17px;\"\u003e\n \u003cp\u003e8.34E-4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15px;\"\u003e\n \u003cp\u003e-82.60\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 50px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eMaternal Educational Level\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 16px;\"\u003e\n \u003cp\u003e-0.45\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 17px;\"\u003e\n \u003cp\u003e0.006\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15px;\"\u003e\n \u003cp\u003e-78.90\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 50px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eGAD-7 Score\u003c/strong\u003e\u003cstrong\u003e\u0026nbsp;at\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003e18 Months Postpartum\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 16px;\"\u003e\n \u003cp\u003e0.74\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 17px;\"\u003e\n \u003cp\u003e0.009\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15px;\"\u003e\n \u003cp\u003e79.50\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 50px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePHQ-9 Score\u003c/strong\u003e\u003cstrong\u003e\u0026nbsp;at\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003e18 Months Postpartum\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 16px;\"\u003e\n \u003cp\u003e1.34\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 17px;\"\u003e\n \u003cp\u003e0.010\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15px;\"\u003e\n \u003cp\u003e130.00\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 50px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eAverage Daily Sleep Duration of Infants at 1-year-old\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 16px;\"\u003e\n \u003cp\u003e-0.08\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 17px;\"\u003e\n \u003cp\u003e0.002\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15px;\"\u003e\n \u003cp\u003e-44.60\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 50px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eConstant\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 16px;\"\u003e\n \u003cp\u003e4.13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 17px;\"\u003e\n \u003cp\u003e0.035\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 15px;\"\u003e\n \u003cp\u003e117.00\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eWhen using a global surrogate model to interpret XGBoost, the P-value is not a primary concern, as the goal is to \u0026quot;mimic\u0026quot; and explain the predictive behavior of the XGBoost model rather than to infer the true real-world relationships of the variables. Therefore, hypothesis testing is not necessary; the focus is on the regression coefficients, which directly reflect the direction and strength of the features\u0026apos; influence.\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"bmc-public-health","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"pubh","sideBox":"Learn more about [BMC Public Health](http://bmcpublichealth.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/pubh/default.aspx","title":"BMC Public Health","twitterHandle":"@BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Social-emotional development, delay, children, prediction, cohort study","lastPublishedDoi":"10.21203/rs.3.rs-8060925/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8060925/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSocial-emotional development (SED) delays in early childhood significantly increase risks of behavioral and mental health disorders. Identifying modifiable risk and protective factors is crucial for improving SEDs in children. This prospective cohort study aims to develop a predictive model for SED delays in 18-month-old children using data from 419 mother-child dyads in Shanghai, China. Twenty-one variables across maternal biomedical, psychological, socioeconomic, and infant domains were analyzed, with maternal anxiety and depression status tracked at five timepoints from pregnancy to 18 months postpartum. The SED status of offspring measured by the Ages \u0026amp; Stages Questionnaire: Social-Emotional. Extreme Gradient Boosting (XGBoost) feature selection identified five key predictors. The mean delivery age of the mothers was 32.2 years. All children were from full-term singleton births. Higher maternal age and maternal educational level, adequate sleep at 1-year-old may reduce SED delay risk, while maternal anxiety/depression status at 18 months postpartum may increase the risk. The model achieved excellent predictive performance (AUC\u0026thinsp;=\u0026thinsp;0.93). Findings suggested that community-level screening of maternal mental health at 18 months postpartum and tailored measures (e.g., parental health education on child sleep patterns) to ensure adequate sleep for children could mitigate SED delays.\u003c/p\u003e","manuscriptTitle":"Building a Prediction Model for Children's Social-emotional Development: A Community- Based Cohort in Shanghai, China","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-22 09:21:01","doi":"10.21203/rs.3.rs-8060925/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2025-12-20T20:33:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"184469266069247631123191995689203192470","date":"2025-12-20T16:38:37+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-12T16:44:51+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-11-15T04:48:13+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-13T12:54:25+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-11-13T12:50:44+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Public Health","date":"2025-11-08T02:47:47+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-public-health","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"pubh","sideBox":"Learn more about [BMC Public Health](http://bmcpublichealth.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/pubh/default.aspx","title":"BMC Public Health","twitterHandle":"@BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"e185c317-337b-4bf5-969e-6d2250a002fe","owner":[],"postedDate":"December 22nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-12-22T09:21:01+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-22 09:21:01","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8060925","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8060925","identity":"rs-8060925","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}