Are the variations in ECG morphology associated to different blood glucose levels? implications for non-invasive glucose monitoring for T1D paediatric patients.

AIMS: Recent clinical trials and real-world studies highlighted those variations in ECG waveforms and HRV recurrently occurred during hypoglycemic and hyperglycemic events in patients with diabetes. However, while several studies have been carried out for adult age, there is lack of evidence for paediatric patients. The main aim of the study is to identify the correlations of variations in ECG Morphology waveforms with blood glucose levels in a paediatric population. METHODS: T1D paediatric patients who use CGM were enrolled. They wear an additional non-invasive wearable device for recording physiological data and respiratory rate. Glucose metrics, ECG parameters and HRV features were collected, and Wilcoxon rank-sum test and Spearman's correlation analysis were used to explore if different levels of blood glucose were associated to ECG morphological changes. RESULTS: Results showed that hypoglycaemic events in paediatric patients with T1D are strongly associated with variations in ECG morphology and HRV. CONCLUSIONS: Results showed the opportunity of using the ECG as a non-invasive adding instrument to monitor the hypoglycaemic events through the integration of the ECG continuous information with CGM data. This innovative approach represents a promising step forward in diabetes management, offering a more comprehensive and effective means of detecting and responding to critical changes in glucose levels.

Development of an artificial intelligence system to identify hypoglycaemia via ECG in adults with type 1 diabetes: protocol for data collection under controlled and free-living conditions.

INTRODUCTION: Hypoglycaemia is a harmful potential complication in people with type 1 diabetes mellitus (T1DM) and can be exacerbated in patients receiving treatment, such as insulin therapies, by the very interventions aiming to achieve optimal blood glucose levels. Symptoms can vary greatly, including, but not limited to, trembling, palpitations, sweating, dry mouth, confusion, seizures, coma, brain damage or even death if untreated. A pilot study with healthy (euglycaemic) participants previously demonstrated that hypoglycaemia can be detected non-invasively with artificial intelligence (AI) using physiological signals obtained from wearable sensors. This protocol provides a methodological description of an observational study for obtaining physiological data from people with T1DM. The aim of this work is to further improve the previously developed AI model and validate its performance for glycaemic event detection in people with T1DM. Such a model could be suitable for integrating into a continuous, non-invasive, glucose monitoring system, contributing towards improving surveillance and management of blood glucose for people with diabetes. METHODS AND ANALYSIS: This observational study aims to recruit 30 patients with T1DM from a diabetes outpatient clinic at the University Hospital Coventry and Warwickshire for a two-phase study. The first phase involves attending an inpatient protocol for up to 36 hours in a calorimetry room under controlled conditions, followed by a phase of free-living, for up to 3 days, in which participants will go about their normal daily activities unrestricted. Throughout the study, the participants will wear wearable sensors to measure and record physiological signals (eg, ECG and continuous glucose monitor). Data collected will be used to develop and validate an AI model using state-of-the-art deep learning methods. ETHICS AND DISSEMINATION: This study has received ethical approval from National Research Ethics Service (ref: 17/NW/0277). The findings will be disseminated via peer-reviewed journals and presented at scientific conferences. TRIAL REGISTRATION NUMBER: NCT05461144.