Background Because of the strong link between childhood obesity and adulthood obesity comorbidities, and the difficulty in decreasing body mass index (BMI) later in life, effective strategies are needed to address this condition in early childhood. The ability to predict obesity before age five could be a useful tool, allowing prevention strategies to focus on high risk children. The few existing prediction models for obesity in childhood have primarily employed data from longitudinal cohort studies, relying on difficult to collect data that are not readily available to all practitioners. Instead, we utilized real-world unaugmented electronic health record (EHR) data from the first two years of life to predict obesity status at age five, an approach not yet taken in pediatric obesity research. Methods and findings We trained a variety of machine learning algorithms to perform both binary classification and regression. Following previous studies demonstrating different obesity determinants for boys and girls, we similarly developed separate models for both groups. In each of the separate models for boys and girls we found that weight for length z-score, BMI between 19 and 24 months, and the last BMI measure recorded before age two were the most important features for prediction. The best performing models were able to predict obesity with an Area Under the Receiver Operator Characteristic Curve (AUC) of 81.7% for girls and 76.1% for boys. Conclusions We were able to predict obesity at age five using EHR data with an AUC comparable to cohort-based studies, reducing the need for investment in additional data collection. Our results suggest that machine learning approaches for predicting future childhood obesity using EHR data could improve the ability of clinicians and researchers to drive future policy, intervention design, and the decision-making process in a clinical setting.
Hispanic women have a higher prevalence of weight associated complications in pregnancy. This ethnic disparity is likely related to behavior patterns, social circumstances, environmental exposures, and access to healthcare, rather than biologic differences. The objective was to determine associations between sociodemographic characteristics, health behaviors, and psychosocial stressors and gestational weight gain (GWG) in low-income Hispanic women. During pregnancy, information on sociodemographic characteristics, health behaviors, and psychosocial stressors were collected. Linear regression estimated mean differences in GWG by selected predictors. Multinomial logistic regression estimated odds of inadequate and excessive GWG by selected predictors. Five-hundred and eight women were included, 38% had inadequate and 28% had excessive GWG; 57% with a normal pre-pregnancy BMI had inadequate GWG. Compared to women with normal BMI, women with overweight or obesity were more likely to have excessive GWG (aRRR = 1.88, 95% CI: 1.04, 3.40 and aRRR = 1.98, 95% CI: 1.08, 3.62, respectively). Mean total GWG was higher among women who were nulliparous (ß = 1.34 kg, 95% CI: 0.38, 2.29) and those who engaged in ≥3 h of screen time daily (ß = 0.98 kg, 95% CI: 0.02, 1.94), and lower among women who were physically active during pregnancy (ß = −1.00 kg, 95% CI: −1.99, −0.03). Eating breakfast daily was associated with lower risk of inadequate GWG (aRRR = 0.47, 95% CI: 0.26, 0.83). Depressive symptoms and poor adherence to dietary recommendations were prevalent, but none of the psychosocial or dietary variables were associated with GWG. In this cohort of primarily immigrant, low-income, Hispanic women, there were high rates of poor adherence to diet and physical activity recommendations, and a majority of women did not meet GWG guidelines. Modifiable health behaviors were associated with GWG, and their promotion should be included in prenatal care.
Background: Disparities in obesity-promoting feeding patterns begin in pregnancy and infancy, underscoring the need for early primary prevention in high-risk groups. We sought to determine the impact of a primary care-based child obesity prevention intervention beginning during pregnancy on maternal infant feeding practices, knowledge, and styles at 10 months in low-income Hispanic families. Methods: The Starting Early Program (StEP) randomized controlled trial enrolled pregnant women at a third trimester visit. Women (n = 533) were randomized to standard care or an intervention with prenatal/postpartum individual nutrition counseling and nutrition and parenting support groups coordinated with pediatric visits. Feeding practices (breastfeeding, family meals, juice, and cereal in the bottle) were assessed using questions from the Infant Feeding Practices Study II. Feeding styles were assessed using the Infant Feeding Style Questionnaire. We analyzed impacts on feeding practices, knowledge, and styles using regression analyses adjusting for covariates. Results: Four hundred twelve mothers completed 10-month assessments. Intervention mothers were more likely to give breast milk as the only milk source [adjusted odds ratio (AOR) 1.65, 95% confidence interval (CI) 1.06-2.58] and have daily family meals (AOR 1.91, 95% CI 1.19-3.05), and less likely to give juice (AOR 0.60, 95% CI 0.39-0.92) or cereal in the bottle (AOR 0.54, 95% CI 0.30-0.97) compared to controls. Intervention mothers were more likely to exhibit lower pressuring, indulgent and laissez-faire feeding styles, and to have higher knowledge. Attending a greater number of group sessions increased intervention impacts. Conclusions: StEP led to reduced obesity-promoting feeding practices and styles, and increased knowledge and provides great potential for population-scalability.
OBJECTIVES: To determine impact of a primary care-based child obesity prevention intervention beginning during pregnancy on early childhood weight outcomes in low-income Hispanic families.METHODS: A randomized controlled trial comparing mother-infant pairs receiving either standard care or the Starting Early Program providing prenatal and postpartum nutrition counseling and nutrition parenting support groups targeting key obesity-related feeding practices in low-income groups. Primary outcomes were reduction in weight-for-age z-scores (WFAzs) from clinical anthropometric measures, obesity prevalence (weight for age $95th percentile), and excess weight gain (WFAz trajectory) from birth to age 3 years. Secondary outcomes included dose effects.RESULTS: Pregnant women (n = 566) were enrolled in the third trimester; 533 randomized to intervention (n = 266) or control (n = 267). Also, 358 children had their weight measured at age 2 years; 285 children had weight measured at age 3 years. Intervention infants had lower mean WFAz at 18 months (0.49 vs 0.73, P = .04) and 2 years (0.56 vs 0.81, P = .03) but not at 3 years (0.63 vs 0.59, P = .76). No group differences in obesity prevalence were found. When generalized estimating equations were used, significant average treatment effects were detected between 10-26 months (B = 20.19, P = .047), although not through age 3 years. In within group dose analyses at 3 years, obesity rates (26.4%, 22.5%, 8.0%, P = .02) decreased as attendance increased with low, medium, and high attendance.CONCLUSIONS: Mean WFAz and growth trajectories were lower for the intervention group through age 2 years, but there were no group differences at age 3. Further study is needed to enhance sustainability of effects beyond age 2.WHAT'S KNOWN ON THIS SUBJECT: Elevated weight in infancy contributes to disparities in later obesity, yet study of primary care-based preventive models during pregnancy and early childhood for high-risk groups is limited.WHAT THIS STUDY ADDS: In this randomized trial of lowincome Hispanic mother-infant pairs, the Starting Early Program led to lower weight trajectories and weight-for-age z-scores through age 2 years, although not sustained at age 3 years. Increased intervention exposure was associated with greater impacts.
Increased efforts are necessary to improve obesity diagnosis and management in younger children who have not yet developed comorbidities. Additionally, the role of pediatric hospitalists as consultants for surgical patients should be further explored as a tool for addressing obesity during inpatient hospitalization.
Objective: To determine whether the lockdown period of the initial COVID-19 surge in New York affected gestational weight gain (GWG), newborn birth weight (BW), and the frequency of gestational diabetes (GDM). Maternal and newborn outcomes during the first wave of the pandemic were compared to those during the same timeframe in the previous two years. Study Design: Retrospective cross-sectional study of all live singleton term deliveries from April 1st to July 31st between 2018-2020 at seven hospitals within a large academic health system in New York. Patients were excluded for missing data on: BW, GWG, pre-pregnancy body mass index (BMI), and gestational age at delivery. We compared GWG, GDM, and BW during the pandemic period (April-July 2020) with the same months in 2018 and 2019 (pre-pandemic) to account for seasonality. Linear regression was used to model the continuous outcomes of GWG and BW. Logistic regression was used to model the binary outcome of GDM. Results: A total of 20,548 patients were included in the study: 6,672 delivered during the pandemic period and 13,876 delivered during the pre-pandemic period. On regression analysis, after adjustment for study epoch and patient characteristics, the pandemic period was associated with lower GWG (β -0.46, 95% CI -0.87 to -0.05), more GDM (aOR 1.24, 95% CI 1.10 to 1.39), and no change in newborn BW (β 0.03, 95% CI -11.7 to 11.8) compared with the referent period. The largest increases in GDM between the two study epochs were noted in patients who identified as Hispanic (8.6% vs. 6.0%; P<0.005) and multiracial/other (11.8% vs. 7.0%; P<0.001). Conclusion: The lockdown period of the pandemic was associated with a decrease in GWG and increase in GDM. Not all groups were affected equally. Hispanic and multiracial patients experienced a larger percentage change in gestational diabetes compared to non-Hispanic white patients.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.