Machine Learning based prediction of Glucose Levels in Type 1 Diabetes Patients with the use of Continuous Glucose Monitoring Data

TL;DR

This paper explores machine learning models, including LSTM, for predicting blood glucose levels in Type 1 Diabetes patients using continuous monitoring data, aiming to improve diabetes management and safety.

Contribution

It compares various ML models for glucose prediction, establishes an optimal training methodology for the CITY dataset, and analyzes model performance and behavior.

Findings

LSTM achieved an RMSE of 28.55 but was not significantly better than AR models.

The study established an optimal training methodology for the CITY dataset.

Insights into LSTM behavior may enhance trust and certification in artificial pancreas systems.

Abstract

A task of vital clinical importance, within Diabetes management, is the prevention of hypo/hyperglycemic events. Increasingly adopted Continuous Glucose Monitoring (CGM) devices offer detailed, non-intrusive and real time insights into a patient's blood glucose concentrations. Leveraging advanced Machine Learning (ML) Models as methods of prediction of future glucose levels, gives rise to substantial quality of life improvements, as well as providing a vital tool for monitoring diabetes. A regression based prediction approach is implemented recursively, with a series of Machine Learning Models: Linear Regression, Hidden Markov Model, Long-Short Term Memory Network. By exploiting a patient's past 11 hours of blood glucose (BG) concentration measurements, a prediction of the 60 minutes is made. Results will be assessed using performance metrics including: Root Mean Squared Error (RMSE), normalised energy of the second-order differences (ESOD) and F1 score. Research of past and current approaches, as well as available dataset, led to the establishment of an optimal training methodology for the CITY dataset, which may be leveraged by future model development. Performance was aligned with similar state-of-art ML models, with LSTM having RMSE of 28.55, however no significant advantage was observed over classical Auto-regressive AR models. Compelling insights into LSTM prediction behaviour could increase public and legislative trust and understanding, progressing the certification of ML models in Artificial Pancreas Systems (APS).