Non-Invasive Glucose Monitoring Using Optical Sensor and Machine Learning Techniques for Diabetes Applications

Abstract

Diabetes is a major public health challenge affecting more than 451 million people. Physiological and experimental factors influence the accuracy of non-invasive glucose monitoring, and these need to be overcome before replacing the finger prick method. Also, the suitable employment of machine learning techniques can significantly improve the accuracy of glucose predictions. One aim of this study is to use light sources with multiple wavelengths to enhance the sensitivity and selectivity of glucose detection in an aqueous solution. Multiple wavelength measurements have the potential to compensate for errors associated with inter-and intra-individual differences in blood and tissue components. In this study, the transmission measurements of a custom built optical sensor are examined using 18 different wavelengths between 410 and 940 nm. Results show a high correlation value (0.98) between glucose concentration and transmission intensity for four wavelengths (485, 645, 860 and 940 nm). Five machine learning methods are investigated for glucose predictions. When regression methods are used, 9% of glucose predictions fall outside the correct range (normal, hypoglycemic or hyperglycemic). The prediction accuracy is improved by applying classification methods on sets of data arranged into 21 classes. Data within each class corresponds to a discrete 10 mg/dL glucose range. Classification based models outperform regression, and among them, the support vector machine is the most successful with F1-score of 99%. Additionally, Clarke error grid shows that 99.75% of glucose readings fall within the clinically acceptable zones. This is an important step towards critical diagnosis during an emergency patient situation.

Non-invasive blood glucose sensing by machine learning of optic fiber-based speckle pattern variation

“…Supervised ML algorithms process sample data, referred to as training data, to make predictions on unknown data without being explicitly programmed to achieve the intended goal. 14 We used several classification algorithms to classify glucose levels. The Naïve Bayes algorithm gives the best results compared with other algorithms such as support-vector machines (SVMs), neural networks, and -nearest neighbors (KNN).…”

“…In Ref. 14 , Shokrekhodaei et al. used non-invasive optical sensors with multiple wavelength measurements for glucose monitoring using machine learning (ML) algorithms .…”

Artificial Intelligence (AI) and Internet of Medical Things (IoMT) Assisted Biomedical Systems for Intelligent Healthcare

“…Non-invasive glucose sensing is an emerging area for continuous glucose monitoring and has the potential to replace the conventional finger-prick-sensing approach. ML-based optical sensors for monitoring glucose levels [ 24 ] using different wavelengths of light sources have been demonstrated. More than 21 different light sources with varying wavelengths were used, and five different ML approaches have been implemented for glucose analysis and prediction.…”

A Single Wavelength Mid-Infrared Photoacoustic Spectroscopy for Noninvasive Glucose Detection Using Machine Learning

“…In May 2021, Shokrekhodaei et al employed both regression and classification models in VIS-NIR transmission spectroscopy for in vitro glucose detection in aqueous solutions [44]. Five different methods were used, namely MLR and feed-forward NN for regression models, while K-nearest neighbor (KNN), decision tree (DT), and support vector machine (SVM) were used as classification models.…”