Forecasting glycaemia for type 1 diabetes mellitus patients by means of IoMT devices

Abstract

The chronic metabolic condition, Type 1 diabetes mellitus (DM1), is marked by consistent hyperglycemia due to the body's inability to produce sufficient insulin. This necessitates the patient's daily monitoring of blood glucose fluctuations to discern a trend and predict future glycemia, subsequently dictating the amount of external insulin needed to regulate glycemia effectively. However, this technique often grapples with a degree of inaccuracy, presenting potential hazards. Nonetheless, contemporary advancements in information and communication technologies (ICT) coupled with novel biological signal sensors offer a refreshing perspective for DM1 management by enabling comprehensive, continual patient health evaluation. Herein, burgeoning technological disruptions such as Big Data, the internet of medical things (IoMT), cloud computing, and machine learning algorithms (ML) could serve pivotal roles in the effective control of DM1. This paper delves into the exploration of the latest IoMT-based methodologies for the unbroken surveillance of DM1 management, facilitating a profound characterization of diabetic patients. The fusion of wearable technologies with machine learning strategies has the potential to yield robust models for short-term blood glucose prediction. The ambition of this study is to develop precise, individual-centric prediction models harnessing an array of pertinent factors. The study applied modeling techniques to a comprehensive dataset comprising glycaemia-associated biological attributes, sourced from an expansive passive monitoring campaign involving 40 DM1 patients. Leveraging the Random Forest method, the resulting models can predict glucose levels over a 30-min time span with an average error as minimal as 18.60 mg/dL for six-hour data and 26.21 mg/dL for a 45-minute prediction horizon, offering also a good performance in the prediction delay.