A Critical Review of the state-of-the-art on Deep Neural Networks for Blood Glucose Prediction in Patients with Diabetes

TL;DR

This paper evaluates and compares ten neural network models and proposes two ensemble models for blood glucose prediction in diabetic patients, using a standardized dataset and multiple statistical methods to identify the most effective approaches.

Contribution

It provides a comprehensive comparison of recent neural networks and introduces ensemble models, offering insights into their relative performance and clinical applicability.

Findings

Identifies top-performing neural network models for blood glucose prediction.

Quantifies error increases in less accurate models compared to the best.

Provides a ranking and statistical analysis of model performance.

Abstract

This article compares ten recently proposed neural networks and proposes two ensemble neural network-based models for blood glucose prediction. All of them are tested under the same dataset, preprocessing workflow, and tools using the OhioT1DM Dataset at three different prediction horizons: 30, 60, and 120 minutes. We compare their performance using the most common metrics in blood glucose prediction and rank the best-performing ones using three methods devised for the statistical comparison of the performance of multiple algorithms: scmamp, model confidence set, and superior predictive ability. Our analysis highlights those models with the highest probability of being the best predictors, estimates the increase in error of the models that perform more poorly with respect to the best ones, and provides a guide for their use in clinical practice.