An Interpretable Prediction Model for Obesity Prediction using EHR Data

Childhood obesity is a major public health challenge. Obesity in early childhood and adolescence can lead to obesity and other health risks in adulthood. Early prediction and identification of high-risk populations can help to prevent its development. With early identification, proper interventions can be used for its prevention. In this paper, we build prediction models to predict future BMI from baseline medical history data. We used unaugmented Nemours EHR (Electronic Health Record) data as represented in the PEDSnet (A pediatric Learning Health System) common data model. We trained variety of machine learning models to perform binary classification of obese, and non-obese for children in early childhood ages and during adolescence. We explored if deep learning techniques that can model the temporal nature of EHR data would improve the performance of predicting obesity as compared to other machine learning techniques that ignore temporality. We also added attention layer at top of rnn layer in our model to compute the attention scores of each hidden layer corresponding to each input timestep. The attention score for each timestep were computed as an average score given to all the features associated with the timestep. These attention scores added interpretability at both timestep level and the features associated with the timesteps.