Enhancing the Interpretability of Deep Models in Heathcare Through Attention: Application to Glucose Forecasting for Diabetic People

TL;DR

This paper demonstrates that the RETAIN model, with its attention mechanism, provides an interpretable and accurate approach for glucose forecasting in diabetic patients, revealing important variables and behavioral patterns.

Contribution

It introduces the application of the RETAIN architecture to glucose prediction, showing it balances accuracy and interpretability better than other models in healthcare.

Findings

RETAIN achieves near-LSTM accuracy while maintaining interpretability.

Older signals beyond one hour are not used for 30-minute predictions.

The model's behavior adapts to events like carbohydrate intake and insulin infusion.

Abstract

The adoption of deep learning in healthcare is hindered by their "black box" nature. In this paper, we explore the RETAIN architecture for the task of glusose forecasting for diabetic people. By using a two-level attention mechanism, the recurrent-neural-network-based RETAIN model is interpretable. We evaluate the RETAIN model on the type-2 IDIAB and the type-1 OhioT1DM datasets by comparing its statistical and clinical performances against two deep models and three models based on decision trees. We show that the RETAIN model offers a very good compromise between accuracy and interpretability, being almost as accurate as the LSTM and FCN models while remaining interpretable. We show the usefulness of its interpretable nature by analyzing the contribution of each variable to the final prediction. It revealed that signal values older than one hour are not used by the RETAIN model for the 30-minutes ahead of time prediction of glucose. Also, we show how the RETAIN model changes its behavior upon the arrival of an event such as carbohydrate intakes or insulin infusions. In particular, it showed that the patient's state before the event is particularily important for the prediction. Overall the RETAIN model, thanks to its interpretability, seems to be a very promissing model for regression or classification tasks in healthcare.