Gupta Mehak, Eckrich Daniel, Bunnell H Timothy, Phan Thao-Ly T, Beheshti Rahmatollah
Southern Methodist University, Dallas, TX, USA.
Nemours Children's Health, Wilmington, DE, USA.
Obes Pillars. 2024 Sep 10;12:100128. doi: 10.1016/j.obpill.2024.100128. eCollection 2024 Dec.
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.
早期识别肥胖高危儿童可为临床医生提供所需信息，以便在关键时期为高危儿童提供有针对性的生活方式咨询，从而改变疾病进程。
本研究旨在开发儿童肥胖预测模型，将先进的机器学习方法应用于一个未经扩充的大型电子健康记录（EHR）数据集。这项工作改进了其他研究，那些研究存在以下问题：（i）依赖电子健康记录中非常规可用的数据（如产前数据）；（ii）专注于单年龄预测；或（iii）未经过严格验证。
利用来自36191名0至10岁不同儿童的电子健康记录数据，构建了一个定制的序列深度学习模型来预测肥胖的发展。该模型通过广泛的区分度、校准度和效用分析进行评估，并在时间、地理和不同亚组间进行验证。
我们的结果大多优于或与类似研究相当。具体而言，该模型在预测2至7岁儿童未来3年内肥胖情况时，在所有情况下的曲线下面积（AUROC）均高于0.8（大多数情况约为0.9）。验证结果显示了该模型的稳健性，且顶级预测因子与肥胖的重要风险因素相符。
我们的模型仅使用常规收集的电子健康记录数据，就能在多个时间点预测幼儿肥胖风险，极大地促进了其在临床护理中的整合。我们的模型可作为一种客观的筛查工具，为临床医生提供有关患者发生肥胖风险的见解从而能提供早期生活方式咨询，以预防幼儿未来肥胖。
