Improving Multi-Sensor Non-Invasive Glucose Detection through AI: A Domain Generalization Approach

Yuyang Sun; Helena Cano-Garcia; Eleonora Razzicchia; Gabriela Gutierrez; Efthymios Kallos; Oana Ancu; Alex Rhodes; Diana-Elena Motei; Richard William Alexander Mackenzie; Panagiotis Kosmas

Improving Multi-Sensor Non-Invasive Glucose Detection through AI: A Domain Generalization Approach

Yuyang Sun, Helena Cano-Garcia, Eleonora Razzicchia, Gabriela Gutierrez, Efthymios Kallos, Oana Ancu, Alex Rhodes, Diana-Elena Motei, Richard William Alexander Mackenzie, Panagiotis Kosmas

Centre for Health and Life Sciences

Research output: Contribution to journal › Article › peer-review

Abstract

Accurate glucose level monitoring is crucial in diabetes management, aiming to ensure glucose levels are within a safe range and reduce the risk of complications. Inter-patient heterogeneity is one of the most important challenges to achieving accurate non-invasive glucose monitoring. This study employs meta-forests, a novel ensemble-based domain generalization approach designed to address this challenge. Our technique is applied to a dataset of 54,280 data points, collected from five subjects over 10 days, using a non-invasive system that integrates near-infrared (NIR) spectroscopy, millimeterwave (mm-wave) sensing, and temperature measurements. Moreover, we significantly enhance model interpretability by incorporating Shapley additive explanations (SHAP) analyses. Importantly, our approach leads to an accuracy for the non-invasive glucose detection system that is comparable to state-of-the-art methods, achieving an average root mean square error (RMSE) of 1.07 mmol/L and a mean absolute percentage error (MAPE) of 9.80% in domainspecific
experiments.

Original language	English
Article number	JBHI-03522-2024.R1
Pages (from-to)	(In-Press)
Journal	IEEE Journal of Biomedical and Health Informatics
Volume	(In-Press)
Publication status	Accepted/In press - 17 Dec 2024

Keywords

Machine learning
domain generalization
millimeter wave radar
infrared sensing
glucose prediction
diabetes
explainable artificial intelligence
interpretability

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Embargoed Document

IEEE_JBHI_Transfer
Accepted author manuscript, 1.85 MB
Embargo ends: 25/04/25

Cite this

@article{06529930c9224ffbae2eddf1a13e07aa,

title = "Improving Multi-Sensor Non-Invasive Glucose Detection through AI: A Domain Generalization Approach",

abstract = "Accurate glucose level monitoring is crucial in diabetes management, aiming to ensure glucose levels are within a safe range and reduce the risk of complications. Inter-patient heterogeneity is one of the most important challenges to achieving accurate non-invasive glucose monitoring. This study employs meta-forests, a novel ensemble-based domain generalization approach designed to address this challenge. Our technique is applied to a dataset of 54,280 data points, collected from five subjects over 10 days, using a non-invasive system that integrates near-infrared (NIR) spectroscopy, millimeterwave (mm-wave) sensing, and temperature measurements. Moreover, we significantly enhance model interpretability by incorporating Shapley additive explanations (SHAP) analyses. Importantly, our approach leads to an accuracy for the non-invasive glucose detection system that is comparable to state-of-the-art methods, achieving an average root mean square error (RMSE) of 1.07 mmol/L and a mean absolute percentage error (MAPE) of 9.80% in domainspecificexperiments.",

keywords = "Machine learning, domain generalization, millimeter wave radar, infrared sensing, glucose prediction, diabetes, explainable artificial intelligence, interpretability",

author = "Yuyang Sun and Helena Cano-Garcia and Eleonora Razzicchia and Gabriela Gutierrez and Efthymios Kallos and Oana Ancu and Alex Rhodes and Diana-Elena Motei and Mackenzie, {Richard William Alexander} and Panagiotis Kosmas",

year = "2024",

month = dec,

day = "17",

language = "English",

volume = "(In-Press)",

pages = "(In--Press)",

journal = "IEEE Journal of Biomedical and Health Informatics",

issn = "2168-2194",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Improving Multi-Sensor Non-Invasive Glucose Detection through AI

T2 - A Domain Generalization Approach

AU - Sun, Yuyang

AU - Cano-Garcia, Helena

AU - Razzicchia, Eleonora

AU - Gutierrez, Gabriela

AU - Kallos, Efthymios

AU - Ancu, Oana

AU - Rhodes, Alex

AU - Motei, Diana-Elena

AU - Mackenzie, Richard William Alexander

AU - Kosmas, Panagiotis

PY - 2024/12/17

Y1 - 2024/12/17

N2 - Accurate glucose level monitoring is crucial in diabetes management, aiming to ensure glucose levels are within a safe range and reduce the risk of complications. Inter-patient heterogeneity is one of the most important challenges to achieving accurate non-invasive glucose monitoring. This study employs meta-forests, a novel ensemble-based domain generalization approach designed to address this challenge. Our technique is applied to a dataset of 54,280 data points, collected from five subjects over 10 days, using a non-invasive system that integrates near-infrared (NIR) spectroscopy, millimeterwave (mm-wave) sensing, and temperature measurements. Moreover, we significantly enhance model interpretability by incorporating Shapley additive explanations (SHAP) analyses. Importantly, our approach leads to an accuracy for the non-invasive glucose detection system that is comparable to state-of-the-art methods, achieving an average root mean square error (RMSE) of 1.07 mmol/L and a mean absolute percentage error (MAPE) of 9.80% in domainspecificexperiments.

AB - Accurate glucose level monitoring is crucial in diabetes management, aiming to ensure glucose levels are within a safe range and reduce the risk of complications. Inter-patient heterogeneity is one of the most important challenges to achieving accurate non-invasive glucose monitoring. This study employs meta-forests, a novel ensemble-based domain generalization approach designed to address this challenge. Our technique is applied to a dataset of 54,280 data points, collected from five subjects over 10 days, using a non-invasive system that integrates near-infrared (NIR) spectroscopy, millimeterwave (mm-wave) sensing, and temperature measurements. Moreover, we significantly enhance model interpretability by incorporating Shapley additive explanations (SHAP) analyses. Importantly, our approach leads to an accuracy for the non-invasive glucose detection system that is comparable to state-of-the-art methods, achieving an average root mean square error (RMSE) of 1.07 mmol/L and a mean absolute percentage error (MAPE) of 9.80% in domainspecificexperiments.

KW - Machine learning

KW - domain generalization

KW - millimeter wave radar

KW - infrared sensing

KW - glucose prediction

KW - diabetes

KW - explainable artificial intelligence

KW - interpretability

M3 - Article

SN - 2168-2194

VL - (In-Press)

SP - (In-Press)

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

M1 - JBHI-03522-2024.R1

ER -

Improving Multi-Sensor Non-Invasive Glucose Detection through AI: A Domain Generalization Approach

Abstract

Keywords

UN SDGs

Embargoed Document

Fingerprint

Cite this