OBJECTIVES: We explored the relationship between household food insecurity and maternal feeding styles, infant feeding practices, and perceptions and attitudes about infant weight in low-income mothers. METHODS: Mothers participating in the Special Supplemental Food Program for Women, Infants, and Children with infants aged between 2 weeks and 6 months were interviewed. By using regression analyses, the following relationships were examined between food insecurity and: (1) controlling feeding styles (restrictive and pressuring); (2) infant feeding practices, including breastfeeding, juice consumption, and adding cereal to the bottle; and (3) perceptions and attitudes about infant weight. Path analysis was used to determine if perceptions and attitudes about infant weight mediated the relationships between food insecurity and controlling feeding styles. RESULTS: The sample included 201 mother–infant pairs, with 35% reporting household food insecurity. Food-insecure mothers were more likely to exhibit restrictive (B [SE]: 0.18 [0.08]; 95% confidence interval [CI]: 0.02–0.34) and pressuring (B [SE]: 0.11 [0.06]; 95% CI: 0.001–0.22) feeding styles compared with food-secure mothers. No associations were found with feeding practices. Concern for their infant becoming overweight in the future was associated with food insecurity (adjusted odds ratio: 2.11 [95% CI: 1.02–4.38]). This concern mediated the relationship between food insecurity and both restrictive (P = .009) and pressuring (P = .01) feeding styles. CONCLUSIONS: Increased concern about future overweight and controlling feeding styles represent potential mechanisms by which food insecurity could be related to obesity. Obesity prevention should aim to decrease food insecurity and to reduce controlling feeding styles in families who remain food insecure.
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. 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. 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.