[This corrects the article DOI: 10.1016/j.obpill.2024.100121.].
Early identification of children at high risk of obesity can provide clinicians with the information needed to provide targeted lifestyle counseling to high-risk children at a critical time to change the disease course.
This study aimed to develop predictive models of childhood obesity, applying advanced machine learning methods to a large unaugmented electronic health record (EHR) dataset. This work improves on other studies that have (i) relied on data not routinely available in EHRs (like prenatal data), (ii) focused on single-age predictions, or (iii) not been rigorously validated.
A customized sequential deep-learning model to predict the development of obesity was built, using EHR data from 36,191 diverse children aged 0–10 years. The model was evaluated using extensive discrimination, calibration, and utility analysis; and was validated temporally, geographically, and across various subgroups.
Our results are mostly better or comparable to similar studies. Specifically, the model achieved an AUROC above 0.8 in all cases (with most cases around 0.9) for predicting obesity within the next 3 years for children 2–7 years of age. Validation results show the model's robustness and top predictors match important risk factors of obesity.
Our model can predict the risk of obesity for young children at multiple time points using only routinely collected EHR data, greatly facilitating its integration into clinical care. Our model can be used as an objective screening tool to provide clinicians with insights into a patient's risk for developing obesity so that early lifestyle counseling can be provided to prevent future obesity in young children.
The prevalence of obesity among the general US adults is 42 %. With increasing immigrant population in the US, the obesity burden among immigrants in the US has been reported to approach or exceed that of the general US population. To our knowledge, this is the first study to report obesity treatment among immigrants in the US. The study aims to evaluate the effectiveness of obesity treatment among immigrant women in primary care at a safety-net academic health center in the US.
This was a retrospectively, electronic medical record chart review of patients who had virtual weight management visits in a primary care setting. Self-reported anthropometric and demographic data were used. Primary outcomes were changes in weight and BMI from initial to follow-up visits as well as bodyweight percentage change from initial weight. Secondary outcomes were ≥5 % and ≥10 % weight reduction. Chi-square or Fisher's exact tests were used for independent categorical variables. Paired t-tests were performed to evaluate the changes in weight and BMI.
The study found average weight reduction of 8.6 kg (100.2–91.6, p < 0.01) which corresponds to an average of 8.7 % weight reduction among immigrant women in the program. The overall average BMI decreased by 3.4 kg/m2 (38.1–34.1, p < 0.01). In the study, 85 % lost 5 % or more, and 42 % lost 10 % or more of their initial weight.
Immigrant women followed for weight management in primary care lost significant weight and BMI, and significant proportion of them achieved clinically meaningful weight reduction. Future large sample size and randomized controlled studies are needed to confirm the findings.