Obesity Prediction with EHR Data: A deep learning approach with interpretable elements

TL;DR

This paper introduces a deep learning model using LSTM and attention mechanisms to predict childhood obesity from electronic health records, capturing longitudinal data and providing interpretability.

Contribution

It presents a novel LSTM-based deep learning approach with an attention layer for interpretable childhood obesity prediction from EHR data.

Findings

LSTM model outperforms traditional machine learning methods.

Attention scores help identify key features and time points.

Model predicts obesity risk from ages 2 to 20.

Abstract

Childhood obesity is a major public health challenge. Early prediction and identification of the children at a high risk of developing childhood obesity may help in engaging earlier and more effective interventions to prevent and manage obesity. Most existing predictive tools for childhood obesity primarily rely on traditional regression-type methods using only a few hand-picked features and without exploiting longitudinal patterns of children data. Deep learning methods allow the use of high-dimensional longitudinal datasets. In this paper, we present a deep learning model designed for predicting future obesity patterns from generally available items on children medical history. To do this, we use a large unaugmented electronic health records dataset from a large pediatric health system. We adopt a general LSTM network architecture which are known to better represent the longitudinal data. We train our proposed model on both dynamic and static EHR data. Our model is used to predict obesity for ages between 2-20 years. We compared the performance of our LSTM model with other machine learning methods that aggregate over sequential data and ignore temporality. To add interpretability, we have additionally included an attention layer to calculate the attention scores for the timestamps and rank features of each timestamp.