Prepregnancy and prenatal risk factors for the neurodevelopmental delay of offspring: Machine learning analysis using national health insurance claims data

Prepregnancy and prenatal risk factors for the neurodevelopmental delay of offspring: Machine learning analysis using national health insurance claims data | 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 Article Prepregnancy and prenatal risk factors for the neurodevelopmental delay of offspring: Machine learning analysis using national health insurance claims data Seung-Woo Yang, Kwang-Sig Lee, Ju Sun Heo, Eun-Saem Choi, Kyumin Kim, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3913046/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract Neurodevelopmental disorders (NDD) in offspring are associated with a complex combination of pre-and postnatal factors. This study uses machine learning and population data to evaluate the association between prepregnancy or prenatal predictors and the NDD of offspring for as more reflective of the real world. Population-based retrospective cohort data were obtained from Korea National Health Insurance Service claims data for 209,424 singleton offspring and their mothers who gave birth for the first time in 2007. The dependent variables were motor development disorder (MDD), cognitive development disorder (CDD) and combined overall neurodevelopmental disorder (NDD) from offspring. Seventeen independent variables from 2002–2007 were included. Random forest variable importance and Shapley Additive Explanation (SHAP) values were calculated to analyze the directions of its associations with the predictors. The random forest with oversampling registered much higher areas under the receiver-operating-characteristic curves than the logistic regression, 72% vs. 50% (MDD), 76% vs. 51% (CDD) and 68% vs. 50% (NDD). Based on random forest variable importance, low socioeconomic status and age at birth were highly ranked. In SHAP values, there was a positive association between NDD and pre- or perinatal outcomes, especially, fetal male sex with growth restriction associated the development of NDD in offspring. Health sciences/Risk factors Health sciences/Medical research/Paediatric research Physical sciences/Mathematics and computing/Scientific data Health sciences/Signs and symptoms/Disability Health sciences/Signs and symptoms/Reproductive signs and symptoms Figures Figure 1 Figure 2 Figure 3 Introduction Neurodevelopmental disorders (NDDs) in offspring are associated with a complex combination of pre-and postnatal genetic factors or environment 1 . Delay in development is generally determined when a child does not attain developmental milestones compared to peers from the same population 2,3 . The terminology of developmental delay itself is not a definite diagnosis but rather a categorical, illustrative term used in the clinic 4 . Therefore, developmental disorders are a very large categorical sequences or patterns meaning that development is disrupted with delays or deviations in developmental processes 3 . NDD includes broad motor developmental disorders (MDD) and developmental disorders, such as attention-deficit/hyperactivity disorder (ADHD), autism spectrum disorder (ASD), and some cognitive developmental disorders, including learning disability (LD) or mental retardation, namely, intellectual disability (ID) 5,6 . The etiologies of NDDs vary, with both genetic and environmental factors being involved. Among the environmental factors, prepregnancy and perinatal factors are the most important 7,8 . The DOHaD (Developmental Origins of Health and Disease) theory is that various in utero environments during pregnancy induce predictive adaptive responses of offspring that anticipate later environments and that the degree of their adaptation between these environments and later environments is related to future disease risk 9,10 . As is well known, levels of dopamine are different in people with ADHD than in those without ADHD 11 . Therefore, striatal dopamine transporter abnormalities are thought to underlie the pathophysiology and psychostimulant treatment 12 . ASD is highly associated with heritable factors such as epigenetic factors or genetic factors 13 . Cognitive disorder is associated with prenatal risk factors, including low birth weight, maternal BMI or maternal anemia 14–16 . Despite the field of interest, there are few large cohort references that suggest prenatal risk factors for motor or cognitive and language developmental disorder. This study uses machine learning and population data to test the association between prepregnancy or prenatal risk factors and the neurodevelopmental disorders of offspring for as more reflective in the real world. Results Descriptive statistics are shown in Table 1 . NDD, including MDD and CDD, showed a higher tendency in the prepregnancy history of DM, HTN, and psychological problems. Other perinatal complications, such as PROM, placenta abruptio, GDM, PIH, PTB and antidepressant use history, are also increased in both MDD and CDD than normal. Model performance is presented in Table 2 . The random forest with oversampling registered much higher AUCs than the logistic regression with oversampling, at 72% vs. 50% (MDD), 76% vs. 51% (CDD) and 68% vs. 50% (NDD). Based on random forest variable importance, as shown in Table 3 , low SES, age at birth, antidepressant use, prepregnancy depression, male fetus, prepregnancy anxiety, prepregnancy diabetes, prepregnancy hypertension, PIH and postpartum depression ranked within the top 10 for MDD, CDD and NDD. Table 1 Baseline characteristics of the study population. Variable MDD (n = 6,141) CDD (n = 5,434) Normal(n = 197,849) Age mean 30.4 ± 3.5 30.1 ± 4.1 30.2 ± 3.8 SES mean 10.1 ± 5.1 9.7 ± 5.2 10.0 ± 5.0 Male 3138 (51.1) 3677 (57) 99543 (50.3) preHTN 144 (2.3) 134 (2.5) 3388 (1.7) preDM 237 (3.9) 228 (4.2) 5855 (3.0) preDepression 291(4.7) 317 (5.8) 7454 (3.8) preAnxiety 1147 (18.7) 915 (16.8) 28864 (14.6) PTB 1145 (18.6) 988 (18.2) 30262 (15.2) LGA 16 (0.3) 9 (0.2) 335 (0.2) SGA 21 (0.4) 39 (0.7) 426 (0.2) FGR 1254 (20.4)) 1121 (20.6) 32537 (16.4) PROM 1158 (18.9) 999 (18.4) 30660 (15.5) Placenta abruptio 1191 (19.4) 1027 (18.9) 31370 (15.9) Postpartum Depression 108 (1.8) 117 (2.2) 2410 (1.2) GDM 496 (8.1) 424 (7.8) 12555 (6.3) PIH 75 (1.2) 80 (1.5) 1784 (0.9) Antidepressant 647 (10.5) 577 (10.6) 17099 (8.6) Abbreviation: SES, social economic status; HTN, hypertension; DM. diabetes; PTB, preterm birth; LGA, large for gestational age; SGA, small for gestational age; FGR, fetal growth restriction; PROM, premature rupture of membrane; GDM, gestational diabetes; PIH, pregnancy induced hypertension Table 2 The areas under the receiver operating characteristic curve (AUC) for the random forest. MDD CDD NDD Logistic Regression Accuracy 0.67 0.67 0.67 AUC 0.50 0.51 0.50 Confusion Matrix 40734 22 40272 680 39467 169 20213 16 19418 827 16508 211 Random Forest Accuracy 0.78 0.80 0.75 AUC 0.72 0.76 0.68 Confusion Matrix 36763 3993 36455 4497 35685 3951 9471 10758 7782 12463 10628 9091 Table 3 Random forest variable importance of prediction model Rank MDD Importance CDD Importance NDD Importance 1 SES 0.4115 SES 0.3771 Age 0.3999 2 Age 0.3859 Age 0.3219 SES 0.3902 3 Antidepressant 0.022 Sex 0.1044 Sex 0.0441 4 preDepression 0.018 preAnxiety 0.029 Antidepressant 0.0181 5 preAnxiety 0.0157 Antidepressant 0.023 preAnxiety 0.0172 6 Sex 0.0154 preDM 0.0139 preDM 0.0147 7 preDM 0.0149 preDepression 0.0113 preDepression 0.0117 8 preHTN 0.0123 preHTN 0.0095 preHTN 0.009 9 Postpartum Depression 0.0101 PIH 0.0082 PIH 0.0088 10 PIH 0.0098 Postpartum Depression 0.0081 Postpartum Depression 0.0086 11 GDM 0.0056 GDM 0.0072 GDM 0.0054 12 FGR 0.0045 FGR 0.0062 FGR 0.0047 13 PTB 0.0039 PTB 0.0044 PTB 0.0038 14 SGA 0.003 Placenta abruptio 0.0037 Placenta abruptio 0.003 15 Placenta abruptio 0.0028 PPROM 0.0035 PROM 0.003 16 PPROM 0.0027 SGA 0.0033 SGA 0.0028 17 LGA 0.0026 LGA 0.0019 LGA 0.0022 Abbreviation: SES, social economic status; HTN, hypertension; DM. diabetes; PTB, preterm birth; LGA, large for gestational age; SGA, small for gestational age; FGR, fetal growth restriction; PROM, premature rupture of membrane; GDM, gestational diabetes; PIH, pregnancy induced hypertension The positive association between NDD and its major predictor is more apparent from SHAP value in S2 table. The absolute value of max SHAP (the positive) was greater than that of min SHAP (the negative), which indicates a positive relationship between neurodevelopment and its major predictor. For example, in SHAP values of FGR for NDD have the range of (− 0.08, 0.28), some participants have SHAP values as low as − 0.08, and other participants have SHAP values as high as 0.28. This indicate that FGR into machine learning will decrease or increase the probability of the NDD by the range of − 0.08 to 0.25. In other words, there exists a positive association between FGR and NDD in general. Figures 1 , 2 and 3 are the SHAP summary plots for MDD, CDD and NDD, which plots the SHAP value of a major predictor for every participant. The blue (or red) color denotes the low (or high) value of a major predictor for a participant. For instance, in Fig. 3 , blue points with the absence of FGR were located on the left side with low SHAP values, whereas red points with the presence of FGR were located on the right side with high SHAP values which are represented as -0.08 to 0.28 (S2 table). The SHAP dependence plots, for every participant, the value of a predictor in the horizontal axis vs. its SHAP value for in the vertical axis. In S3 Figure, for instance, points with the absence of FGR (with a value of 0) were positioned in the left bottom with low SHAP values, while points with the presence of FGR (with a value of 1) were positioned in the right top with high SHAP values. Also, fetal male sex (the blue color) was positioned in the right top, therefore male sex is highest association with FGR for the prediction of NDD. However, the relationship between continuous variables and NDD can take a U-shaped form, as shown in S6 figure, such as SES and age. Discussion In this study, we evaluated prenatal risk factors for offspring’s NDD with a higher accuracy model through random forest machine learning and SHAP variable importance analysis. As a result, maternal age and low social economic status most affected the development of NDD. Also, maternal risk factors, including psychological problems, pregnancy complications such as PIH and GDM, maternal prepregnancy DM, and fetal risk factors for FGR, SGA, and male sex, were associated with NDD. Additionally, higher-ranked important variables such as prepregnancy DM/HTN, GDM, and PIH are very similar to previous literature that evaluated risk factors for NDD 17–20 . The DOHaD theory suggests that the uncertain in-utero environment in early fetal developmental periods affected health risk factors in adulthood of offspring 9,10 . Based on this hypothesis, prediction and identification of high-risk groups for various diseases were assumed and therefore evaluate the preventive diagnosis, early intervention, and therapeutic treatment 5 . Age is a well-known risk factor for pregnancy complications. Both very young and advanced maternal age at childbirth affect the adverse outcomes of their offspring such as low birth weight and neonatal mortality 21,22 . Gao et al reported that in terms of NDD, young and advanced maternal age at childbirth are associated with ADHD and LD risk 6 . In our results, age was one of the most important variables (Table 3 ) for the model and showed U-shape patterns in S1, S2, and S3 figure, which means that young and advanced ages were associated with the risk of MDD, CDD and NDD. Also, SES and age is the most associated factors. Maternal psychological status and drug use also affected offspring NDD. Stress during pregnancy is also known to induce brain inflammation and influence fetal brain development 23 . It is well known that increased stress-related corticosteroid hormones such as cortisol and corticosterone are a consequence of stress. Fetal exposure to high concentrations of cortisol results in developmental delays and NDD 5 . Additionally, several researchers have reported that antidepressant drugs such as selective serotonin reuptake inhibitors (SSRIs) affect the development of ASD depending on whether disturbance of the serotonin system is involved in the pathophysiology of ASD 24,25 . In our results, maternal prepregnancy depression and anxiety history and antidepressant drugs are important risk factors for NDD development. In particular, anxiety and antidepressant drug use were highly positively correlated with NDD in the SHAP value analysis. Additionally, these factors are the most affected covariates to other variables in the SHAP independence plot. In this study, fetal risk factors such as SGA, FGR, and male sex were associated with the development of NDD. Generally, FGR results in SGA and brain remodeling, in which the volume in the gray matter of the limbic region is reduced. In addition, the regional expanded volumes of the frontoinsular, frontal, and temporoparietal areas affect the disturbance of balanced neurodevelopment 26 . Additionally, male predominance in the incidence of NDD is often highlighted 27 . Females of many species including humans generally showed enhanced immune responses and increased resistance to disease and infection than males 28 . Because of several neurological disorders caused by pathological reactive microglia in central nervous system, sex difference in neurodevelopment is occurred 29 . Quinn et al. reported from a large-scale study that sex differences in reading impairment exist and are attributable largely to male vulnerability as opposed to ascertainment bias 30 . In our study, FGR and male sex were highly associated with a risk of NDD. Furthermore, in the dependence plot, FGR and male sex are strongly associated each other and covariates as risk factors for NDD. In their large cohort study of the relationship between low birth weight and LD at 11 years old, Johnson et al. reported that low birth weight was associated with an increased risk for LD in male offspring but not in female offspring (OR = 4.32, 95% CI 1.55–12.04). Additionally, these results depend on the difference in SES 15 . Within our study, SES, FGR, and male sex were highly ranked variables in the importance analysis, and this result reinforces the results of previous studies. The limitation of this study is that it was a retrospective analysis utilizing an administrative database, which relies on the accuracy and consistency of the individuals coding the data. Therefore, the severity or grade of NDD was not fully adjusted. Additionally, due to limitations regarding the extraction of data on body mass index, adjustments for some well-known risk factors such as prepregnancy obesity were not performed. 17,31 Major issues of NDD, such as ADHD and ASD, were excluded in this cohort; therefore, these models have limitations in applications. However, as described above, because these two issues affect more genetic and heritable factors than other NDDs, these issues cause confounding bias in evaluating prepregnancy or pregnancy risk factors. In this study, age and SES is the two most affect factors in MDD, CDD, and NDD model. Therefore, there may be bias in which the influence of other variables was measured insignificantly. For evaluating this, subgroup analysis in age and SES parameters will be needed in further study. FGR and PTB are also known as major risk factors of NDD 32,33 . Especially, FGR, the early-on-set rather than late-on-set type is critically affected more severe patterns of neurodevelopmental outcome in offspring because of placenta insufficiency sequence 32,34 . Also, PTB in early gestational weeks in Influencing each other with FGR, which can be an important risk factor for NDD 33 . However, because our original coding data set does not identify gestational weeks of diagnosis for FGR and PTB, the influence of these factors may be underestimated. Notwithstanding the above limitations, this study had the advantage of involving a large nationwide assessment of the association between NDDs and various pregnancy risk factors with an accurate and high-validity machine learning model compared to logistic regression, which reflects the real world. These results not only reinforce the results of previous studies but also extend the knowledge of NDD, so it would be useful to counsel mothers during prepregnancy or pregnancy and their FGR offspring. Methods Participants and Variables Population-based retrospective cohort data came from Korea National Health Insurance Service claims data for 209,424 singleton offspring and their primiparity mothers in 2007. This retrospective cohort study was approved by the Institutional Review Board (IRB) of Korea University Anam Hospital on 2022AN0184 (2022.04.11) and informed consent was waived by the IRB. Also, all methods were performed in accordance with the relevant guidelines and regulations. The dependent variables were MDD, CDD and NDD (sum of MDD and CDD) from 2007–2021 (Table S1 ). Seventeen independent variables were ( 1 ) five predictors in 2007, namely, age at birth (years), sex (male vs. female), low socioeconomic status [SES, measured by an insurance fee with a range of 1 (the highest group) to 20 (the lowest group)], small for gestational age (SGA), and large for gestational age (LGA); ( 2 ) four predictors from 2002–2006 (no vs. yes), namely, pregestational hypertension, pregestational diabetes, pregestational depression, and pregestational anxiety; ( 3 ) seven predictors within 10 months before childbirth (no vs. yes), namely, fetal growth restriction (FGR), premature rupture of membranes (PROM), placenta abruption, pregnancy induced hypertension (PIH), gestational diabetes (GDM), preterm birth (PTB) and antidepressant medication; and ( 4 ) one predictor within 12 months after childbirth, namely, postpartum depression. These predictors were screened from ICD-10 and anatomical therapeutic chemical (ATC) codes (N06A). (Table S1 ). Machine Learning Analysis The logistic regression and random forest were used for the prediction of NDD. A random forest is a group of decision trees that make majority votes on the dependent variable (“bootstrap aggregation”). A random forest with 100 decision trees was performed. The training and testing of this random forest takes two steps. First, new data with participants are created based on random sampling with replacement, and a decision tree is created based on these new data. Here, some participants in the original data are excluded from the new data, and these leftovers are called out-of-bag data. This process is repeated 100 times; specifically, 100 new data are created, 100 decision trees are created, and 100 out-of-bag data are created. Second, the 100 decision trees make predictions on the dependent variable of every participant in the out-of-bag data, their majority vote is taken as their final prediction on this participant, and the out-of-bag error is calculated as the proportion of wrong votes on all participants in the out-of-bag data 35–37 . In this study total 209,424 cases with full information were split into training and validation sets at an 80:20 ratio (167,539 vs. 41,885 cases). A criterion for the validation of the trained models was accuracy (a ratio of correct predictions among 41,885 cases) and the area under the receiver-operating-characteristic curve (AUC) (area under the plot of sensitivity vs. 1 - specificity). Variable Importance Analysis The Shapley Additive Explanation (SHAP) values were calculated to analyze the directions of association between NDD and predictors in the prediction model. R-Studio 1.3.959 (R-Studio Inc: Boston, United States) was employed for the analysis during January 1, 2023-February 28, 2023. The SHAP value of a predictor for a participant measures the difference between what machine learning predicts for the probability of MDD, CDD and NDD with and without the predictor. Random forest impurity importance and random forest permutation importance were the only explainable artificial intelligence methods before machine learning accuracy importance, and SHAP was introduced as an extension or alternative very recently. In other words, the SHAP value combines the results of all possible subgroup analyses, which are ignored in linear or logistic regression with an unrealistic assumption of ceteris paribus , namely, “all the other variables staying constant”. 35–37 Declarations Conflicts of Interest: The authors report no conflicts of interest. Author Contribution Conceptualization: K.S.L & K.H.A, curation: K.S.L & K.K, Formal analysis & Methodology: K.S.L & K.K; Supervision & Validation: S.W.Y, E.S.C, J.S.H & K.H.A; Visualization: K.S.L & K.K,; Roles/Writing - original draft; S.W.Y & K.S.L, Writing - review & editing: S.W.Y, J.S.H & K.H.A Data availability All data generated or analysed during this study are included in this published article and its supplementary information files. The datasets generated and/or analysed during the current study are not publicly available. This is because the dataset for this study is only available on the NHIS servers for one year after the dataset was generated. References Yasumitsu-Lovell, K. et al. Pre-/perinatal reduced optimality and neurodevelopment at 1 month and 3 years of age: Results from the Japan Environment and Children's Study (JECS). PLoS One 18, e0280249, doi: 10.1371/journal.pone.0280249 (2023). Choo, Y. Y., Agarwal, P., How, C. H. & Yeleswarapu, S. P. Developmental delay: identification and management at primary care level. Singapore Med J 60, 119–123, doi: 10.11622/smedj.2019025 (2019). Mithyantha, R., Kneen, R., McCann, E. & Gladstone, M. Current evidence-based recommendations on investigating children with global developmental delay. Arch Dis Child 102, 1071–1076, doi: 10.1136/archdischild-2016-311271 (2017). Levy, Y. 'Developmental Delay' Reconsidered: The Critical Role of Age-Dependent, Co-variant Development. Front Psychol 9, 503, doi: 10.3389/fpsyg.2018.00503 (2018). Doi, M., Usui, N. & Shimada, S. Prenatal Environment and Neurodevelopmental Disorders. Front Endocrinol (Lausanne) 13, 860110, doi: 10.3389/fendo.2022.860110 (2022). Gao, L., Li, S., Yue, Y. & Long, G. Maternal age at childbirth and the risk of attention-deficit/hyperactivity disorder and learning disability in offspring. Front Public Health 11, 923133, doi: 10.3389/fpubh.2023.923133 (2023). Barker, D. J., Winter, P. D., Osmond, C., Margetts, B. & Simmonds, S. J. Weight in infancy and death from ischaemic heart disease. Lancet 2, 577–580, doi: 10.1016/s0140-6736(89)90710-1 (1989). Bilder, D. A. et al. Prenatal and perinatal factors associated with intellectual disability. Am J Intellect Dev Disabil 118, 156–176, doi: 10.1352/1944-7558-118.2.156 (2013). Barker, D. J. & Osmond, C. Infant mortality, childhood nutrition, and ischaemic heart disease in England and Wales. Lancet 1, 1077–1081, doi: 10.1016/s0140-6736(86)91340-1 (1986). Barker, D. J., Osmond, C., Golding, J., Kuh, D. & Wadsworth, M. E. Growth in utero, blood pressure in childhood and adult life, and mortality from cardiovascular disease. BMJ 298, 564–567, doi: 10.1136/bmj.298.6673.564 (1989). Volkow, N. D. et al. Evaluating dopamine reward pathway in ADHD: clinical implications. JAMA 302, 1084–1091, doi: 10.1001/jama.2009.1308 (2009). Fusar-Poli, P., Rubia, K., Rossi, G., Sartori, G. & Balottin, U. Striatal dopamine transporter alterations in ADHD: pathophysiology or adaptation to psychostimulants? A meta-analysis. Am J Psychiatry 169, 264–272, doi: 10.1176/appi.ajp.2011.11060940 (2012). Yoon, S. H., Choi, J., Lee, W. J. & Do, J. T. Genetic and Epigenetic Etiology Underlying Autism Spectrum Disorder. J Clin Med 9, doi: 10.3390/jcm9040966 (2020). Andersen, C. H., Thomsen, P. H., Nohr, E. A. & Lemcke, S. Maternal body mass index before pregnancy as a risk factor for ADHD and autism in children. Eur Child Adolesc Psychiatry 27, 139–148, doi: 10.1007/s00787-017-1027-6 (2018). Johnson, E. O. & Breslau, N. Increased risk of learning disabilities in low birth weight boys at age 11 years. Biol Psychiatry 47, 490–500, doi: 10.1016/s0006-3223(99)00223-1 (2000). Wiegersma, A. M., Dalman, C., Lee, B. K., Karlsson, H. & Gardner, R. M. Association of Prenatal Maternal Anemia With Neurodevelopmental Disorders. JAMA Psychiatry 76, 1294–1304, doi: 10.1001/jamapsychiatry.2019.2309 (2019). Kong, L., Chen, X., Gissler, M. & Lavebratt, C. Relationship of prenatal maternal obesity and diabetes to offspring neurodevelopmental and psychiatric disorders: a narrative review. Int J Obes (Lond) 44, 1981–2000, doi: 10.1038/s41366-020-0609-4 (2020). Chen, S., Zhao, S., Dalman, C., Karlsson, H. & Gardner, R. Association of maternal diabetes with neurodevelopmental disorders: autism spectrum disorders, attention-deficit/hyperactivity disorder and intellectual disability. Int J Epidemiol 50, 459–474, doi: 10.1093/ije/dyaa212 (2021). Brand, J. S., Lawlor, D. A., Larsson, H. & Montgomery, S. Association Between Hypertensive Disorders of Pregnancy and Neurodevelopmental Outcomes Among Offspring. JAMA Pediatr 175, 577–585, doi: 10.1001/jamapediatrics.2020.6856 (2021). Maher, G. M. et al. Association of Hypertensive Disorders of Pregnancy With Risk of Neurodevelopmental Disorders in Offspring: A Systematic Review and Meta-analysis. JAMA Psychiatry 75, 809–819, doi: 10.1001/jamapsychiatry.2018.0854 (2018). Gibbs, C. M., Wendt, A., Peters, S. & Hogue, C. J. The impact of early age at first childbirth on maternal and infant health. Paediatr Perinat Epidemiol 26 Suppl 1, 259–284, doi: 10.1111/j.1365-3016.2012.01290.x (2012). Lean, S. C., Derricott, H., Jones, R. L. & Heazell, A. E. P. Advanced maternal age and adverse pregnancy outcomes: A systematic review and meta-analysis. PLoS One 12, e0186287, doi: 10.1371/journal.pone.0186287 (2017). Diz-Chaves, Y., Astiz, M., Bellini, M. J. & Garcia-Segura, L. M. Prenatal stress increases the expression of proinflammatory cytokines and exacerbates the inflammatory response to LPS in the hippocampal formation of adult male mice. Brain Behav Immun 28, 196–206, doi: 10.1016/j.bbi.2012.11.013 (2013). Suarez, E. A. et al. Association of Antidepressant Use During Pregnancy With Risk of Neurodevelopmental Disorders in Children. JAMA Intern Med 182, 1149–1160, doi: 10.1001/jamainternmed.2022.4268 (2022). Chandana, S. R. et al. Significance of abnormalities in developmental trajectory and asymmetry of cortical serotonin synthesis in autism. Int J Dev Neurosci 23, 171–182, doi: 10.1016/j.ijdevneu.2004.08.002 (2005). Sacchi, C. et al. Neurodevelopmental Outcomes following Intrauterine Growth Restriction and Very Preterm Birth. J Pediatr 238, 135–144 e110, doi: 10.1016/j.jpeds.2021.07.002 (2021). Dan, B. Sex differences in neurodevelopmental disorders. Dev Med Child Neurol 63, 492, doi: 10.1111/dmcn.14853 (2021). Hanamsagar, R. & Bilbo, S. D. Sex differences in neurodevelopmental and neurodegenerative disorders: Focus on microglial function and neuroinflammation during development. J Steroid Biochem Mol Biol 160, 127–133, doi: 10.1016/j.jsbmb.2015.09.039 (2016). Schwarz, J. M., Sholar, P. W. & Bilbo, S. D. Sex differences in microglial colonization of the developing rat brain. J Neurochem 120, 948–963, doi: 10.1111/j.1471-4159.2011.07630.x (2012). Quinn, J. M. & Wagner, R. K. Gender Differences in Reading Impairment and in the Identification of Impaired Readers: Results From a Large-Scale Study of At-Risk Readers. J Learn Disabil 48, 433–445, doi: 10.1177/0022219413508323 (2015). Sanchez, C. E. et al. Maternal pre-pregnancy obesity and child neurodevelopmental outcomes: a meta-analysis. Obes Rev 19, 464–484, doi: 10.1111/obr.12643 (2018). Baschat, A. A. Neurodevelopment after fetal growth restriction. Fetal Diagn Ther 36, 136–142, doi: 10.1159/000353631 (2014). Saigal, S. & Doyle, L. W. An overview of mortality and sequelae of preterm birth from infancy to adulthood. Lancet 371, 261–269, doi: 10.1016/S0140-6736(08)60136-1 (2008). Figueras, F. & Gratacos, E. Update on the diagnosis and classification of fetal growth restriction and proposal of a stage-based management protocol. Fetal Diagn Ther 36, 86–98, doi: 10.1159/000357592 (2014). Lee, K. S. & Kim, E. S. Explainable Artificial Intelligence in the Early Diagnosis of Gastrointestinal Disease. Diagnostics (Basel) 12, doi: 10.3390/diagnostics12112740 (2022). Lee, K. S. & Ham, B. J. Machine Learning on Early Diagnosis of Depression. Psychiatry Investig 19, 597–605, doi: 10.30773/pi.2022.0075 (2022). Lee, K. S. & Park, H. Machine learning on thyroid disease: a review. Front Biosci (Landmark Ed) 27, 101, doi: 10.31083/j.fbl2703101 (2022). Additional Declarations No competing interests reported. Supplementary Files SupplementaryFigure.pdf supplementarytable.docx Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 19 Mar, 2024 Reviews received at journal 10 Mar, 2024 Reviewers agreed at journal 10 Mar, 2024 Reviewers agreed at journal 02 Mar, 2024 Reviewers invited by journal 13 Feb, 2024 Editor assigned by journal 13 Feb, 2024 Editor invited by journal 13 Feb, 2024 Submission checks completed at journal 13 Feb, 2024 First submitted to journal 31 Jan, 2024 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-3913046","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":272781729,"identity":"3b529c03-bfd2-4beb-bce0-add0d4ad8671","order_by":0,"name":"Seung-Woo Yang","email":"","orcid":"","institution":"Department of Obstetrics and Gynecology, Sanggye Paik Hospital, Inje University College of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Seung-Woo","middleName":"","lastName":"Yang","suffix":""},{"id":272781730,"identity":"21aa3bff-6bb2-4d92-99ab-a1cdd82b196a","order_by":1,"name":"Kwang-Sig Lee","email":"","orcid":"","institution":"AI Center, Korea University College of Medicine, Anam Hospital","correspondingAuthor":false,"prefix":"","firstName":"Kwang-Sig","middleName":"","lastName":"Lee","suffix":""},{"id":272781731,"identity":"5503c472-3e5b-4b9e-b64f-731851dd62f9","order_by":2,"name":"Ju Sun Heo","email":"","orcid":"","institution":"Department of Pediatrics, Korea University College of Medicine, Anam Hospital","correspondingAuthor":false,"prefix":"","firstName":"Ju","middleName":"Sun","lastName":"Heo","suffix":""},{"id":272781732,"identity":"9f5c5930-8efc-41d4-9690-a3fb427bc7af","order_by":3,"name":"Eun-Saem Choi","email":"","orcid":"","institution":"Department of Obstetrics and Gynecology, Korea University College of Medicine, Anam Hospital","correspondingAuthor":false,"prefix":"","firstName":"Eun-Saem","middleName":"","lastName":"Choi","suffix":""},{"id":272781733,"identity":"070c1811-2c54-442a-9768-c17c6c83deac","order_by":4,"name":"Kyumin Kim","email":"","orcid":"","institution":"Department of Statistics, Korea University College of Political Science and Economics","correspondingAuthor":false,"prefix":"","firstName":"Kyumin","middleName":"","lastName":"Kim","suffix":""},{"id":272781734,"identity":"ff6a4e06-b576-4b2a-b0b7-fd7e822e5a30","order_by":5,"name":"Ki Hoon Ahn","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5klEQVRIie3PIQvCQBTA8Ymg5cR6QeZXeCKcCvswE2GWKUajyXRo9WOsie2NQyw3VjcMCtYFwWJQcTqTyE2b4f7h4MH9eHeGodP9Y4QYeBxTE54TtL8iBX8hreaL0PQo5pKiqEydrpeNX5AqDxBJSfSX5WDtnUfUaJXnqCQ0mNlIiRis+NCJefqwDhc5DwsJIFAx8NBlEUkJRD21qD+IDaIPYcLiy4PsDmoCAQdE27Ehctk225Lz/YaU4E/QanhRwrY1oARkD5TElG7zdL3ROoQui5OLZcLG36vXvEd+u67T6XS6j90Bgy5MnEMm7r0AAAAASUVORK5CYII=","orcid":"","institution":"Department of Obstetrics and Gynecology, Korea University College of Medicine, Anam Hospital","correspondingAuthor":true,"prefix":"","firstName":"Ki","middleName":"Hoon","lastName":"Ahn","suffix":""}],"badges":[],"createdAt":"2024-01-31 07:59:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3913046/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3913046/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":51117403,"identity":"3854633b-fd4f-47a3-ac6a-a5197f89075a","added_by":"auto","created_at":"2024-02-14 12:05:36","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":591860,"visible":true,"origin":"","legend":"\u003cp\u003eSHAP summary plot for MDD\u003c/p\u003e","description":"","filename":"Figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-3913046/v1/645614d69200b8edd3ee1bbd.png"},{"id":51117404,"identity":"3dedcef8-2f74-479b-a506-b7e3359293bf","added_by":"auto","created_at":"2024-02-14 12:05:37","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":597789,"visible":true,"origin":"","legend":"\u003cp\u003eSHAP summary plot for CDD\u003c/p\u003e","description":"","filename":"Figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-3913046/v1/46a2a0779d202ad679ef80c3.png"},{"id":51117406,"identity":"f5200b62-0014-42a1-8c76-1455896b9a9b","added_by":"auto","created_at":"2024-02-14 12:05:37","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":769214,"visible":true,"origin":"","legend":"\u003cp\u003eSHAP summary plot for NDD\u003c/p\u003e","description":"","filename":"Figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-3913046/v1/f4bde6f4a01f6eb2a6499833.png"},{"id":51117632,"identity":"096aafaf-cda8-48fe-9a44-f34c44d79552","added_by":"auto","created_at":"2024-02-14 12:13:37","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":737336,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3913046/v1/db136dcd-076e-46e4-b5cf-cce6f3d7c04e.pdf"},{"id":51117407,"identity":"cd47c401-d854-486b-be14-556625e7d345","added_by":"auto","created_at":"2024-02-14 12:05:37","extension":"pdf","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":914119,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFigure.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3913046/v1/e2da12b6722f5f96f5dffa2b.pdf"},{"id":51117405,"identity":"b6a256d6-d59d-406e-9c26-2432226111cd","added_by":"auto","created_at":"2024-02-14 12:05:37","extension":"docx","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":16405,"visible":true,"origin":"","legend":"","description":"","filename":"supplementarytable.docx","url":"https://assets-eu.researchsquare.com/files/rs-3913046/v1/5160c7627a4e20e34944adf6.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Prepregnancy and prenatal risk factors for the neurodevelopmental delay of offspring: Machine learning analysis using national health insurance claims data","fulltext":[{"header":"Introduction","content":"\u003cp\u003eNeurodevelopmental disorders (NDDs) in offspring are associated with a complex combination of pre-and postnatal genetic factors or environment\u003csup\u003e1\u003c/sup\u003e. Delay in development is generally determined when a child does not attain developmental milestones compared to peers from the same population\u003csup\u003e2,3\u003c/sup\u003e. The terminology of developmental delay itself is not a definite diagnosis but rather a categorical, illustrative term used in the clinic\u003csup\u003e4\u003c/sup\u003e. Therefore, developmental disorders are a very large categorical sequences or patterns meaning that development is disrupted with delays or deviations in developmental processes\u003csup\u003e3\u003c/sup\u003e. NDD includes broad motor developmental disorders (MDD) and developmental disorders, such as attention-deficit/hyperactivity disorder (ADHD), autism spectrum disorder (ASD), and some cognitive developmental disorders, including learning disability (LD) or mental retardation, namely, intellectual disability (ID) \u003csup\u003e5,6\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eThe etiologies of NDDs vary, with both genetic and environmental factors being involved. Among the environmental factors, prepregnancy and perinatal factors are the most important \u003csup\u003e7,8\u003c/sup\u003e. The DOHaD (Developmental Origins of Health and Disease) theory is that various in utero environments during pregnancy induce predictive adaptive responses of offspring that anticipate later environments and that the degree of their adaptation between these environments and later environments is related to future disease risk \u003csup\u003e9,10\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eAs is well known, levels of dopamine are different in people with ADHD than in those without ADHD\u003csup\u003e11\u003c/sup\u003e. Therefore, striatal dopamine transporter abnormalities are thought to underlie the pathophysiology and psychostimulant treatment \u003csup\u003e12\u003c/sup\u003e. ASD is highly associated with heritable factors such as epigenetic factors or genetic factors\u003csup\u003e13\u003c/sup\u003e. Cognitive disorder is associated with prenatal risk factors, including low birth weight, maternal BMI or maternal anemia\u003csup\u003e14\u0026ndash;16\u003c/sup\u003e. Despite the field of interest, there are few large cohort references that suggest prenatal risk factors for motor or cognitive and language developmental disorder. This study uses machine learning and population data to test the association between prepregnancy or prenatal risk factors and the neurodevelopmental disorders of offspring for as more reflective in the real world.\u003c/p\u003e"},{"header":"Results","content":"\u003cp\u003eDescriptive statistics are shown in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. NDD, including MDD and CDD, showed a higher tendency in the prepregnancy history of DM, HTN, and psychological problems. Other perinatal complications, such as PROM, placenta abruptio, GDM, PIH, PTB and antidepressant use history, are also increased in both MDD and CDD than normal. Model performance is presented in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. The random forest with oversampling registered much higher AUCs than the logistic regression with oversampling, at 72% vs. 50% (MDD), 76% vs. 51% (CDD) and 68% vs. 50% (NDD). Based on random forest variable importance, as shown in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e, low SES, age at birth, antidepressant use, prepregnancy depression, male fetus, prepregnancy anxiety, prepregnancy diabetes, prepregnancy hypertension, PIH and postpartum depression ranked within the top 10 for MDD, CDD and NDD.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eBaseline characteristics of the study population.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVariable\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMDD (n\u0026thinsp;=\u0026thinsp;6,141)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eCDD (n\u0026thinsp;=\u0026thinsp;5,434)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNormal(n\u0026thinsp;=\u0026thinsp;197,849)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge mean\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e30.4\u0026thinsp;\u0026plusmn;\u0026thinsp;3.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e30.1\u0026thinsp;\u0026plusmn;\u0026thinsp;4.1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e30.2\u0026thinsp;\u0026plusmn;\u0026thinsp;3.8\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSES mean\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10.1\u0026thinsp;\u0026plusmn;\u0026thinsp;5.1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9.7\u0026thinsp;\u0026plusmn;\u0026thinsp;5.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e10.0\u0026thinsp;\u0026plusmn;\u0026thinsp;5.0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3138 (51.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3677 (57)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99543 (50.3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003epreHTN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e144 (2.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e134 (2.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e3388 (1.7)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003epreDM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e237 (3.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e228 (4.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5855 (3.0)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003epreDepression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e291(4.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e317 (5.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e7454 (3.8)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003epreAnxiety\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1147 (18.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e915 (16.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e28864 (14.6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePTB\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1145 (18.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e988 (18.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e30262 (15.2)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLGA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e16 (0.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9 (0.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e335 (0.2)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSGA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e21 (0.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e39 (0.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e426 (0.2)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFGR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1254 (20.4))\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1121 (20.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e32537 (16.4)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePROM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1158 (18.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e999 (18.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e30660 (15.5)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePlacenta abruptio\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1191 (19.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1027 (18.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e31370 (15.9)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePostpartum Depression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e108 (1.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e117 (2.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2410 (1.2)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGDM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e496 (8.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e424 (7.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e12555 (6.3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePIH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e75 (1.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e80 (1.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1784 (0.9)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAntidepressant\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e647 (10.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e577 (10.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e17099 (8.6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"4\"\u003eAbbreviation: SES, social economic status; HTN, hypertension; DM. diabetes; PTB, preterm birth; LGA, large for gestational age; SGA, small for gestational age; FGR, fetal growth restriction; PROM, premature rupture of membrane; GDM, gestational diabetes; PIH, pregnancy induced hypertension\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eThe areas under the receiver operating characteristic curve (AUC) for the random forest.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"8\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e \u003cp\u003eMDD\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e \u003cp\u003eCDD\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e \u003cp\u003eNDD\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e \u003cp\u003e\u003cb\u003eLogistic Regression\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAccuracy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e \u003cp\u003e0.67\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e \u003cp\u003e0.67\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e \u003cp\u003e0.67\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAUC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e \u003cp\u003e0.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e \u003cp\u003e0.51\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e \u003cp\u003e0.50\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eConfusion Matrix\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e40734\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e40272\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e680\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e39467\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e169\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e20213\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e19418\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e827\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e16508\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e211\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e \u003cp\u003e\u003cb\u003eRandom Forest\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAccuracy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e \u003cp\u003e0.78\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e \u003cp\u003e0.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e \u003cp\u003e0.75\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAUC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e \u003cp\u003e0.72\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e \u003cp\u003e0.76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e \u003cp\u003e0.68\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eConfusion Matrix\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e36763\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e3993\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e36455\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e4497\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e35685\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e3951\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9471\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e10758\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e7782\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e12463\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e10628\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e9091\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eRandom forest variable importance of prediction model\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"7\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRank\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMDD\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eImportance\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eCDD\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eImportance\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNDD\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eImportance\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSES\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.4115\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSES\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3771\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eAge\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.3999\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAge\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.3859\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eAge\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3219\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eSES\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.3902\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAntidepressant\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSex\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.1044\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eSex\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.0441\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003epreDepression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.018\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003epreAnxiety\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.029\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eAntidepressant\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.0181\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003epreAnxiety\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0157\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eAntidepressant\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003epreAnxiety\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.0172\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSex\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0154\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003epreDM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.0139\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003epreDM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.0147\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003epreDM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0149\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003epreDepression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.0113\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003epreDepression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.0117\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003epreHTN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0123\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003epreHTN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.0095\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003epreHTN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.009\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePostpartum Depression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0101\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePIH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.0082\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003ePIH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.0088\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePIH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0098\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePostpartum Depression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.0081\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003ePostpartum Depression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.0086\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGDM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0056\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eGDM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.0072\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eGDM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.0054\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFGR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0045\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eFGR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.0062\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eFGR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.0047\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePTB\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0039\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePTB\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.0044\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003ePTB\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.0038\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSGA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.003\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePlacenta abruptio\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.0037\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003ePlacenta abruptio\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.003\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePlacenta abruptio\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0028\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePPROM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.0035\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003ePROM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.003\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePPROM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0027\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSGA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.0033\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eSGA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.0028\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLGA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.0026\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eLGA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.0019\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eLGA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.0022\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"7\"\u003eAbbreviation: SES, social economic status; HTN, hypertension; DM. diabetes; PTB, preterm birth; LGA, large for gestational age; SGA, small for gestational age; FGR, fetal growth restriction; PROM, premature rupture of membrane; GDM, gestational diabetes; PIH, pregnancy induced hypertension\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eThe positive association between NDD and its major predictor is more apparent from SHAP value in S2 table. The absolute value of max SHAP (the positive) was greater than that of min SHAP (the negative), which indicates a positive relationship between neurodevelopment and its major predictor. For example, in SHAP values of FGR for NDD have the range of (\u0026minus;\u0026thinsp;0.08, 0.28), some participants have SHAP values as low as \u0026minus;\u0026thinsp;0.08, and other participants have SHAP values as high as 0.28. This indicate that FGR into machine learning will decrease or increase the probability of the NDD by the range of \u0026minus;\u0026thinsp;0.08 to 0.25. In other words, there exists a positive association between FGR and NDD in general. Figures\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, \u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e and \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e are the SHAP summary plots for MDD, CDD and NDD, which plots the SHAP value of a major predictor for every participant. The blue (or red) color denotes the low (or high) value of a major predictor for a participant. For instance, in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e, blue points with the absence of FGR were located on the left side with low SHAP values, whereas red points with the presence of FGR were located on the right side with high SHAP values which are represented as -0.08 to 0.28 (S2 table). The SHAP dependence plots, for every participant, the value of a predictor in the horizontal axis vs. its SHAP value for in the vertical axis. In S3 Figure, for instance, points with the absence of FGR (with a value of 0) were positioned in the left bottom with low SHAP values, while points with the presence of FGR (with a value of 1) were positioned in the right top with high SHAP values. Also, fetal male sex (the blue color) was positioned in the right top, therefore male sex is highest association with FGR for the prediction of NDD. However, the relationship between continuous variables and NDD can take a U-shaped form, as shown in S6 figure, such as SES and age.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eIn this study, we evaluated prenatal risk factors for offspring\u0026rsquo;s NDD with a higher accuracy model through random forest machine learning and SHAP variable importance analysis. As a result, maternal age and low social economic status most affected the development of NDD. Also, maternal risk factors, including psychological problems, pregnancy complications such as PIH and GDM, maternal prepregnancy DM, and fetal risk factors for FGR, SGA, and male sex, were associated with NDD. Additionally, higher-ranked important variables such as prepregnancy DM/HTN, GDM, and PIH are very similar to previous literature that evaluated risk factors for NDD \u003csup\u003e17\u0026ndash;20\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eThe DOHaD theory suggests that the uncertain in-utero environment in early fetal developmental periods affected health risk factors in adulthood of offspring \u003csup\u003e9,10\u003c/sup\u003e. Based on this hypothesis, prediction and identification of high-risk groups for various diseases were assumed and therefore evaluate the preventive diagnosis, early intervention, and therapeutic treatment \u003csup\u003e5\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eAge is a well-known risk factor for pregnancy complications. Both very young and advanced maternal age at childbirth affect the adverse outcomes of their offspring such as low birth weight and neonatal mortality\u003csup\u003e21,22\u003c/sup\u003e. Gao et al reported that in terms of NDD, young and advanced maternal age at childbirth are associated with ADHD and LD risk \u003csup\u003e6\u003c/sup\u003e. In our results, age was one of the most important variables (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e) for the model and showed U-shape patterns in S1, S2, and S3 figure, which means that young and advanced ages were associated with the risk of MDD, CDD and NDD. Also, SES and age is the most associated factors.\u003c/p\u003e \u003cp\u003eMaternal psychological status and drug use also affected offspring NDD. Stress during pregnancy is also known to induce brain inflammation and influence fetal brain development \u003csup\u003e23\u003c/sup\u003e. It is well known that increased stress-related corticosteroid hormones such as cortisol and corticosterone are a consequence of stress. Fetal exposure to high concentrations of cortisol results in developmental delays and NDD\u003csup\u003e5\u003c/sup\u003e. Additionally, several researchers have reported that antidepressant drugs such as selective serotonin reuptake inhibitors (SSRIs) affect the development of ASD depending on whether disturbance of the serotonin system is involved in the pathophysiology of ASD \u003csup\u003e24,25\u003c/sup\u003e. In our results, maternal prepregnancy depression and anxiety history and antidepressant drugs are important risk factors for NDD development. In particular, anxiety and antidepressant drug use were highly positively correlated with NDD in the SHAP value analysis. Additionally, these factors are the most affected covariates to other variables in the SHAP independence plot.\u003c/p\u003e \u003cp\u003eIn this study, fetal risk factors such as SGA, FGR, and male sex were associated with the development of NDD. Generally, FGR results in SGA and brain remodeling, in which the volume in the gray matter of the limbic region is reduced. In addition, the regional expanded volumes of the frontoinsular, frontal, and temporoparietal areas affect the disturbance of balanced neurodevelopment \u003csup\u003e26\u003c/sup\u003e. Additionally, male predominance in the incidence of NDD is often highlighted \u003csup\u003e27\u003c/sup\u003e. Females of many species including humans generally showed enhanced immune responses and increased resistance to disease and infection than males\u003csup\u003e28\u003c/sup\u003e. Because of several neurological disorders caused by pathological reactive microglia in central nervous system, sex difference in neurodevelopment is occurred\u003csup\u003e29\u003c/sup\u003e. Quinn et al. reported from a large-scale study that sex differences in reading impairment exist and are attributable largely to male vulnerability as opposed to ascertainment bias \u003csup\u003e30\u003c/sup\u003e. In our study, FGR and male sex were highly associated with a risk of NDD. Furthermore, in the dependence plot, FGR and male sex are strongly associated each other and covariates as risk factors for NDD. In their large cohort study of the relationship between low birth weight and LD at 11 years old, Johnson et al. reported that low birth weight was associated with an increased risk for LD in male offspring but not in female offspring (OR\u0026thinsp;=\u0026thinsp;4.32, 95% CI 1.55\u0026ndash;12.04). Additionally, these results depend on the difference in SES \u003csup\u003e15\u003c/sup\u003e. Within our study, SES, FGR, and male sex were highly ranked variables in the importance analysis, and this result reinforces the results of previous studies.\u003c/p\u003e \u003cp\u003eThe limitation of this study is that it was a retrospective analysis utilizing an administrative database, which relies on the accuracy and consistency of the individuals coding the data. Therefore, the severity or grade of NDD was not fully adjusted. Additionally, due to limitations regarding the extraction of data on body mass index, adjustments for some well-known risk factors such as prepregnancy obesity were not performed. \u003csup\u003e17,31\u003c/sup\u003e Major issues of NDD, such as ADHD and ASD, were excluded in this cohort; therefore, these models have limitations in applications. However, as described above, because these two issues affect more genetic and heritable factors than other NDDs, these issues cause confounding bias in evaluating prepregnancy or pregnancy risk factors. In this study, age and SES is the two most affect factors in MDD, CDD, and NDD model. Therefore, there may be bias in which the influence of other variables was measured insignificantly. For evaluating this, subgroup analysis in age and SES parameters will be needed in further study. FGR and PTB are also known as major risk factors of NDD\u003csup\u003e32,33\u003c/sup\u003e. Especially, FGR, the early-on-set rather than late-on-set type is critically affected more severe patterns of neurodevelopmental outcome in offspring because of placenta insufficiency sequence \u003csup\u003e32,34\u003c/sup\u003e. Also, PTB in early gestational weeks in Influencing each other with FGR, which can be an important risk factor for NDD\u003csup\u003e33\u003c/sup\u003e. However, because our original coding data set does not identify gestational weeks of diagnosis for FGR and PTB, the influence of these factors may be underestimated. Notwithstanding the above limitations, this study had the advantage of involving a large nationwide assessment of the association between NDDs and various pregnancy risk factors with an accurate and high-validity machine learning model compared to logistic regression, which reflects the real world. These results not only reinforce the results of previous studies but also extend the knowledge of NDD, so it would be useful to counsel mothers during prepregnancy or pregnancy and their FGR offspring.\u003c/p\u003e"},{"header":"Methods","content":"\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003eParticipants and Variables\u003c/h2\u003e \u003cp\u003ePopulation-based retrospective cohort data came from Korea National Health Insurance Service claims data for 209,424 singleton offspring and their primiparity mothers in 2007. This retrospective cohort study was approved by the Institutional Review Board (IRB) of Korea University Anam Hospital on 2022AN0184 (2022.04.11) and informed consent was waived by the IRB. Also, all methods were performed in accordance with the relevant guidelines and regulations. The dependent variables were MDD, CDD and NDD (sum of MDD and CDD) from 2007\u0026ndash;2021 (Table \u003cspan refid=\"MOESM1\" class=\"InternalRef\"\u003eS1\u003c/span\u003e). Seventeen independent variables were (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e) five predictors in 2007, namely, age at birth (years), sex (male vs. female), low socioeconomic status [SES, measured by an insurance fee with a range of 1 (the highest group) to 20 (the lowest group)], small for gestational age (SGA), and large for gestational age (LGA); (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e) four predictors from 2002\u0026ndash;2006 (no vs. yes), namely, pregestational hypertension, pregestational diabetes, pregestational depression, and pregestational anxiety; (\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e) seven predictors within 10 months before childbirth (no vs. yes), namely, fetal growth restriction (FGR), premature rupture of membranes (PROM), placenta abruption, pregnancy induced hypertension (PIH), gestational diabetes (GDM), preterm birth (PTB) and antidepressant medication; and (\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e) one predictor within 12 months after childbirth, namely, postpartum depression. These predictors were screened from ICD-10 and anatomical therapeutic chemical (ATC) codes (N06A). (Table \u003cspan refid=\"MOESM1\" class=\"InternalRef\"\u003eS1\u003c/span\u003e).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003eMachine Learning Analysis\u003c/h2\u003e \u003cp\u003eThe logistic regression and random forest were used for the prediction of NDD. A random forest is a group of decision trees that make majority votes on the dependent variable (\u0026ldquo;bootstrap aggregation\u0026rdquo;). A random forest with 100 decision trees was performed. The training and testing of this random forest takes two steps. First, new data with participants are created based on random sampling with replacement, and a decision tree is created based on these new data. Here, some participants in the original data are excluded from the new data, and these leftovers are called out-of-bag data. This process is repeated 100 times; specifically, 100 new data are created, 100 decision trees are created, and 100 out-of-bag data are created. Second, the 100 decision trees make predictions on the dependent variable of every participant in the out-of-bag data, their majority vote is taken as their final prediction on this participant, and the out-of-bag error is calculated as the proportion of wrong votes on all participants in the out-of-bag data\u003csup\u003e35\u0026ndash;37\u003c/sup\u003e. In this study total 209,424 cases with full information were split into training and validation sets at an 80:20 ratio (167,539 vs. 41,885 cases). A criterion for the validation of the trained models was accuracy (a ratio of correct predictions among 41,885 cases) and the area under the receiver-operating-characteristic curve (AUC) (area under the plot of sensitivity vs. 1 - specificity).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003eVariable Importance Analysis\u003c/h2\u003e \u003cp\u003eThe Shapley Additive Explanation (SHAP) values were calculated to analyze the directions of association between NDD and predictors in the prediction model. R-Studio 1.3.959 (R-Studio Inc: Boston, United States) was employed for the analysis during January 1, 2023-February 28, 2023. The SHAP value of a predictor for a participant measures the difference between what machine learning predicts for the probability of MDD, CDD and NDD with and without the predictor. Random forest impurity importance and random forest permutation importance were the only explainable artificial intelligence methods before machine learning accuracy importance, and SHAP was introduced as an extension or alternative very recently. In other words, the SHAP value combines the results of all possible subgroup analyses, which are ignored in linear or logistic regression with an unrealistic assumption of \u003cem\u003eceteris paribus\u003c/em\u003e, namely, \u0026ldquo;all the other variables staying constant\u0026rdquo;.\u003csup\u003e35\u0026ndash;37\u003c/sup\u003e\u003c/p\u003e \u003c/div\u003e"},{"header":"Declarations","content":"\u003cp\u003e \u003ch2\u003eConflicts of Interest:\u003c/h2\u003e \u003cp\u003eThe authors report no conflicts of interest.\u003c/p\u003e \u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eConceptualization: K.S.L \u0026amp; K.H.A, curation: K.S.L \u0026amp; K.K, Formal analysis \u0026amp; Methodology: K.S.L \u0026amp; K.K; Supervision \u0026amp; Validation: S.W.Y, E.S.C, J.S.H \u0026amp; K.H.A; Visualization: K.S.L \u0026amp; K.K,; Roles/Writing - original draft; S.W.Y \u0026amp; K.S.L, Writing - review \u0026amp; editing: S.W.Y, J.S.H \u0026amp; K.H.A\u003c/p\u003e\u003ch2\u003eData availability\u003c/h2\u003e \u003cp\u003eAll data generated or analysed during this study are included in this published article and its supplementary information files. The datasets generated and/or analysed during the current study are not publicly available. This is because the dataset for this study is only available on the NHIS servers for one year after the dataset was generated.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eYasumitsu-Lovell, K. \u003cem\u003eet al.\u003c/em\u003e Pre-/perinatal reduced optimality and neurodevelopment at 1 month and 3 years of age: Results from the Japan Environment and Children's Study (JECS). PLoS One 18, e0280249, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1371/journal.pone.0280249\u003c/span\u003e\u003cspan address=\"10.1371/journal.pone.0280249\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChoo, Y. Y., Agarwal, P., How, C. H. \u0026amp; Yeleswarapu, S. P. Developmental delay: identification and management at primary care level. Singapore Med J 60, 119\u0026ndash;123, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.11622/smedj.2019025\u003c/span\u003e\u003cspan address=\"10.11622/smedj.2019025\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2019).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMithyantha, R., Kneen, R., McCann, E. \u0026amp; Gladstone, M. Current evidence-based recommendations on investigating children with global developmental delay. Arch Dis Child 102, 1071\u0026ndash;1076, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1136/archdischild-2016-311271\u003c/span\u003e\u003cspan address=\"10.1136/archdischild-2016-311271\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2017).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLevy, Y. 'Developmental Delay' Reconsidered: The Critical Role of Age-Dependent, Co-variant Development. Front Psychol 9, 503, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fpsyg.2018.00503\u003c/span\u003e\u003cspan address=\"10.3389/fpsyg.2018.00503\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDoi, M., Usui, N. \u0026amp; Shimada, S. Prenatal Environment and Neurodevelopmental Disorders. Front Endocrinol (Lausanne) 13, 860110, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fendo.2022.860110\u003c/span\u003e\u003cspan address=\"10.3389/fendo.2022.860110\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGao, L., Li, S., Yue, Y. \u0026amp; Long, G. Maternal age at childbirth and the risk of attention-deficit/hyperactivity disorder and learning disability in offspring. Front Public Health 11, 923133, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fpubh.2023.923133\u003c/span\u003e\u003cspan address=\"10.3389/fpubh.2023.923133\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBarker, D. J., Winter, P. D., Osmond, C., Margetts, B. \u0026amp; Simmonds, S. J. Weight in infancy and death from ischaemic heart disease. Lancet 2, 577\u0026ndash;580, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/s0140-6736(89)90710-1\u003c/span\u003e\u003cspan address=\"10.1016/s0140-6736(89)90710-1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (1989).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBilder, D. A. \u003cem\u003eet al.\u003c/em\u003e Prenatal and perinatal factors associated with intellectual disability. Am J Intellect Dev Disabil 118, 156\u0026ndash;176, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1352/1944-7558-118.2.156\u003c/span\u003e\u003cspan address=\"10.1352/1944-7558-118.2.156\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2013).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBarker, D. J. \u0026amp; Osmond, C. Infant mortality, childhood nutrition, and ischaemic heart disease in England and Wales. Lancet 1, 1077\u0026ndash;1081, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/s0140-6736(86)91340-1\u003c/span\u003e\u003cspan address=\"10.1016/s0140-6736(86)91340-1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (1986).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBarker, D. J., Osmond, C., Golding, J., Kuh, D. \u0026amp; Wadsworth, M. E. Growth in utero, blood pressure in childhood and adult life, and mortality from cardiovascular disease. BMJ 298, 564\u0026ndash;567, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1136/bmj.298.6673.564\u003c/span\u003e\u003cspan address=\"10.1136/bmj.298.6673.564\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (1989).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVolkow, N. D. \u003cem\u003eet al.\u003c/em\u003e Evaluating dopamine reward pathway in ADHD: clinical implications. JAMA 302, 1084\u0026ndash;1091, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1001/jama.2009.1308\u003c/span\u003e\u003cspan address=\"10.1001/jama.2009.1308\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2009).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFusar-Poli, P., Rubia, K., Rossi, G., Sartori, G. \u0026amp; Balottin, U. Striatal dopamine transporter alterations in ADHD: pathophysiology or adaptation to psychostimulants? A meta-analysis. Am J Psychiatry 169, 264\u0026ndash;272, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1176/appi.ajp.2011.11060940\u003c/span\u003e\u003cspan address=\"10.1176/appi.ajp.2011.11060940\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2012).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYoon, S. H., Choi, J., Lee, W. J. \u0026amp; Do, J. T. Genetic and Epigenetic Etiology Underlying Autism Spectrum Disorder. J Clin Med 9, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/jcm9040966\u003c/span\u003e\u003cspan address=\"10.3390/jcm9040966\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAndersen, C. H., Thomsen, P. H., Nohr, E. A. \u0026amp; Lemcke, S. Maternal body mass index before pregnancy as a risk factor for ADHD and autism in children. Eur Child Adolesc Psychiatry 27, 139\u0026ndash;148, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s00787-017-1027-6\u003c/span\u003e\u003cspan address=\"10.1007/s00787-017-1027-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJohnson, E. O. \u0026amp; Breslau, N. Increased risk of learning disabilities in low birth weight boys at age 11 years. Biol Psychiatry 47, 490\u0026ndash;500, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/s0006-3223(99)00223-1\u003c/span\u003e\u003cspan address=\"10.1016/s0006-3223(99)00223-1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2000).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWiegersma, A. M., Dalman, C., Lee, B. K., Karlsson, H. \u0026amp; Gardner, R. M. Association of Prenatal Maternal Anemia With Neurodevelopmental Disorders. JAMA Psychiatry 76, 1294\u0026ndash;1304, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1001/jamapsychiatry.2019.2309\u003c/span\u003e\u003cspan address=\"10.1001/jamapsychiatry.2019.2309\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2019).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKong, L., Chen, X., Gissler, M. \u0026amp; Lavebratt, C. Relationship of prenatal maternal obesity and diabetes to offspring neurodevelopmental and psychiatric disorders: a narrative review. Int J Obes (Lond) 44, 1981\u0026ndash;2000, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/s41366-020-0609-4\u003c/span\u003e\u003cspan address=\"10.1038/s41366-020-0609-4\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen, S., Zhao, S., Dalman, C., Karlsson, H. \u0026amp; Gardner, R. Association of maternal diabetes with neurodevelopmental disorders: autism spectrum disorders, attention-deficit/hyperactivity disorder and intellectual disability. Int J Epidemiol 50, 459\u0026ndash;474, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1093/ije/dyaa212\u003c/span\u003e\u003cspan address=\"10.1093/ije/dyaa212\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBrand, J. S., Lawlor, D. A., Larsson, H. \u0026amp; Montgomery, S. Association Between Hypertensive Disorders of Pregnancy and Neurodevelopmental Outcomes Among Offspring. JAMA Pediatr 175, 577\u0026ndash;585, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1001/jamapediatrics.2020.6856\u003c/span\u003e\u003cspan address=\"10.1001/jamapediatrics.2020.6856\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMaher, G. M. \u003cem\u003eet al.\u003c/em\u003e Association of Hypertensive Disorders of Pregnancy With Risk of Neurodevelopmental Disorders in Offspring: A Systematic Review and Meta-analysis. JAMA Psychiatry 75, 809\u0026ndash;819, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1001/jamapsychiatry.2018.0854\u003c/span\u003e\u003cspan address=\"10.1001/jamapsychiatry.2018.0854\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGibbs, C. M., Wendt, A., Peters, S. \u0026amp; Hogue, C. J. The impact of early age at first childbirth on maternal and infant health. Paediatr Perinat Epidemiol 26 Suppl 1, 259\u0026ndash;284, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/j.1365-3016.2012.01290.x\u003c/span\u003e\u003cspan address=\"10.1111/j.1365-3016.2012.01290.x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2012).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLean, S. C., Derricott, H., Jones, R. L. \u0026amp; Heazell, A. E. P. Advanced maternal age and adverse pregnancy outcomes: A systematic review and meta-analysis. PLoS One 12, e0186287, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1371/journal.pone.0186287\u003c/span\u003e\u003cspan address=\"10.1371/journal.pone.0186287\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2017).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDiz-Chaves, Y., Astiz, M., Bellini, M. J. \u0026amp; Garcia-Segura, L. M. Prenatal stress increases the expression of proinflammatory cytokines and exacerbates the inflammatory response to LPS in the hippocampal formation of adult male mice. Brain Behav Immun 28, 196\u0026ndash;206, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.bbi.2012.11.013\u003c/span\u003e\u003cspan address=\"10.1016/j.bbi.2012.11.013\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2013).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSuarez, E. A. \u003cem\u003eet al.\u003c/em\u003e Association of Antidepressant Use During Pregnancy With Risk of Neurodevelopmental Disorders in Children. JAMA Intern Med 182, 1149\u0026ndash;1160, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1001/jamainternmed.2022.4268\u003c/span\u003e\u003cspan address=\"10.1001/jamainternmed.2022.4268\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChandana, S. R. \u003cem\u003eet al.\u003c/em\u003e Significance of abnormalities in developmental trajectory and asymmetry of cortical serotonin synthesis in autism. Int J Dev Neurosci 23, 171\u0026ndash;182, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.ijdevneu.2004.08.002\u003c/span\u003e\u003cspan address=\"10.1016/j.ijdevneu.2004.08.002\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2005).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSacchi, C. \u003cem\u003eet al.\u003c/em\u003e Neurodevelopmental Outcomes following Intrauterine Growth Restriction and Very Preterm Birth. \u003cem\u003eJ Pediatr\u003c/em\u003e 238, 135\u0026ndash;144 e110, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.jpeds.2021.07.002\u003c/span\u003e\u003cspan address=\"10.1016/j.jpeds.2021.07.002\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDan, B. Sex differences in neurodevelopmental disorders. Dev Med Child Neurol 63, 492, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/dmcn.14853\u003c/span\u003e\u003cspan address=\"10.1111/dmcn.14853\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHanamsagar, R. \u0026amp; Bilbo, S. D. Sex differences in neurodevelopmental and neurodegenerative disorders: Focus on microglial function and neuroinflammation during development. J Steroid Biochem Mol Biol 160, 127\u0026ndash;133, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.jsbmb.2015.09.039\u003c/span\u003e\u003cspan address=\"10.1016/j.jsbmb.2015.09.039\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2016).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSchwarz, J. M., Sholar, P. W. \u0026amp; Bilbo, S. D. Sex differences in microglial colonization of the developing rat brain. J Neurochem 120, 948\u0026ndash;963, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/j.1471-4159.2011.07630.x\u003c/span\u003e\u003cspan address=\"10.1111/j.1471-4159.2011.07630.x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2012).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eQuinn, J. M. \u0026amp; Wagner, R. K. Gender Differences in Reading Impairment and in the Identification of Impaired Readers: Results From a Large-Scale Study of At-Risk Readers. J Learn Disabil 48, 433\u0026ndash;445, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1177/0022219413508323\u003c/span\u003e\u003cspan address=\"10.1177/0022219413508323\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2015).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSanchez, C. E. \u003cem\u003eet al.\u003c/em\u003e Maternal pre-pregnancy obesity and child neurodevelopmental outcomes: a meta-analysis. Obes Rev 19, 464\u0026ndash;484, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/obr.12643\u003c/span\u003e\u003cspan address=\"10.1111/obr.12643\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBaschat, A. A. Neurodevelopment after fetal growth restriction. Fetal Diagn Ther 36, 136\u0026ndash;142, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1159/000353631\u003c/span\u003e\u003cspan address=\"10.1159/000353631\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2014).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSaigal, S. \u0026amp; Doyle, L. W. An overview of mortality and sequelae of preterm birth from infancy to adulthood. Lancet 371, 261\u0026ndash;269, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/S0140-6736(08)60136-1\u003c/span\u003e\u003cspan address=\"10.1016/S0140-6736(08)60136-1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2008).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFigueras, F. \u0026amp; Gratacos, E. Update on the diagnosis and classification of fetal growth restriction and proposal of a stage-based management protocol. Fetal Diagn Ther 36, 86\u0026ndash;98, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1159/000357592\u003c/span\u003e\u003cspan address=\"10.1159/000357592\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2014).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLee, K. S. \u0026amp; Kim, E. S. Explainable Artificial Intelligence in the Early Diagnosis of Gastrointestinal Disease. Diagnostics (Basel) 12, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/diagnostics12112740\u003c/span\u003e\u003cspan address=\"10.3390/diagnostics12112740\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLee, K. S. \u0026amp; Ham, B. J. Machine Learning on Early Diagnosis of Depression. Psychiatry Investig 19, 597\u0026ndash;605, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.30773/pi.2022.0075\u003c/span\u003e\u003cspan address=\"10.30773/pi.2022.0075\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLee, K. S. \u0026amp; Park, H. Machine learning on thyroid disease: a review. Front Biosci (Landmark Ed) 27, 101, doi:\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.31083/j.fbl2703101\u003c/span\u003e\u003cspan address=\"10.31083/j.fbl2703101\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-3913046/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3913046/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eNeurodevelopmental disorders (NDD) in offspring are associated with a complex combination of pre-and postnatal factors. This study uses machine learning and population data to evaluate the association between prepregnancy or prenatal predictors and the NDD of offspring for as more reflective of the real world. Population-based retrospective cohort data were obtained from Korea National Health Insurance Service claims data for 209,424 singleton offspring and their mothers who gave birth for the first time in 2007. The dependent variables were motor development disorder (MDD), cognitive development disorder (CDD) and combined overall neurodevelopmental disorder (NDD) from offspring. Seventeen independent variables from 2002\u0026ndash;2007 were included. Random forest variable importance and Shapley Additive Explanation (SHAP) values were calculated to analyze the directions of its associations with the predictors. The random forest with oversampling registered much higher areas under the receiver-operating-characteristic curves than the logistic regression, 72% vs. 50% (MDD), 76% vs. 51% (CDD) and 68% vs. 50% (NDD). Based on random forest variable importance, low socioeconomic status and age at birth were highly ranked. In SHAP values, there was a positive association between NDD and pre- or perinatal outcomes, especially, fetal male sex with growth restriction associated the development of NDD in offspring.\u003c/p\u003e","manuscriptTitle":"Prepregnancy and prenatal risk factors for the neurodevelopmental delay of offspring: Machine learning analysis using national health insurance claims data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-02-14 12:05:32","doi":"10.21203/rs.3.rs-3913046/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-03-19T06:20:41+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-03-11T03:54:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"1b73d1d6-27b6-48d2-b955-71d332c935c1","date":"2024-03-10T15:46:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"7b37b756-3ba6-4f5b-9c20-5d607d01db5d_SNPRID","date":"2024-03-02T12:17:19+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-02-14T01:16:00+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-02-14T01:11:48+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-02-13T07:21:07+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-02-13T07:16:51+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-01-31T07:50:40+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"ac6133b6-07af-4c8c-a94a-43f53d6ca2dc","owner":[],"postedDate":"February 14th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":28751653,"name":"Health sciences/Risk factors"},{"id":28751654,"name":"Health sciences/Medical research/Paediatric research"},{"id":28751655,"name":"Physical sciences/Mathematics and computing/Scientific data"},{"id":28751656,"name":"Health sciences/Signs and symptoms/Disability"},{"id":28751657,"name":"Health sciences/Signs and symptoms/Reproductive signs and symptoms"}],"tags":[],"updatedAt":"2024-06-11T05:49:43+00:00","versionOfRecord":[],"versionCreatedAt":"2024-02-14 12:05:32","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3913046","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3913046","identity":"rs-3913046","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}