A Review on Machine Learning Approaches for the Prediction of Glucose Levels and Hypogylcemia

TL;DR

This review analyzes machine learning models for predicting blood glucose levels and hypoglycemia in Type 1 Diabetes, highlighting the best models, prediction horizons, and factors affecting accuracy.

Contribution

It provides a comprehensive comparison of ML approaches for glucose prediction, emphasizing the impact of data, model type, and personalization on performance.

Findings

1-hour prediction horizon yields optimal results.

Conventional ML excels in classification, deep learning in regression.

Personalization improves accuracy, but data quality limits its effectiveness.

Abstract

Type 1 Diabetes (T1D) is an autoimmune disease leading to insulin insufficiency. Thus, patients require lifelong insulin therapy, which has a side effect of hypoglycemia. Hypoglycemia is a critical state of decreased blood glucose levels (BGL) below 70 mg/dL and is associated with increased risk of mortality. Machine learning (ML) models can improve diabetes management by predicting hypoglycemia and providing optimal prevention methods. ML models are classified into regression and classification based, that forecast glucose levels and identify events based on defined labels, respectively. This review investigates state-of-the-art models trained on data of continuous glucose monitoring (CGM) devices from patients with T1D. We compare the models' performance across short-term (15 to 120 min) and long term (3 to more than 24 hours) prediction horizons (PHs). Particularly, we explore: 1) How much in advance can glucose values or a hypoglycemic event be accurately predicted? 2) Which models have the best performance? 3) Which factors impact the performance? and 4) Does personalization increase performance? The results show that 1) a PH of up to 1 hour provides the best results. 2) Conventional ML methods yield the best results for classification and DL for regression. A single model cannot adequately classify across multiple PHs. 3) The model performance is influenced by multivariate datasets and the input sequence length (ISL). 4) Personal data enhances performance but due to limited data quality population-based models are preferred.