Non-Invasive Classification of Blood Glucose Level for Early Detection Diabetes Based on Photoplethysmography Signal

Abstract

Monitoring systems for the early detection of diabetes are essential to avoid potential expensive medical costs. Currently, only invasive monitoring methods are commercially available. These methods have significant disadvantages as patients experience discomfort while obtaining blood samples. A non-invasive method of blood glucose level (BGL) monitoring that is painless and low-cost would address the limitations of invasive techniques. Photoplethysmography (PPG) collects a signal from a finger sensor using a photodiode, and a nearby infrared LED light. The combination of the PPG electronic circuit with artificial intelligence makes it possible to implement the classification of BGL. However, one major constraint of deep learning is the long training phase. We try to overcome this limitation and offer a concept for classifying type 2 diabetes (T2D) using a machine learning algorithm based on PPG. We gathered 400 raw datasets of BGL measured with PPG and divided these points into two classification levels, according to the National Institute for Clinical Excellence, namely, “normal” and “diabetes”. Based on the results for testing between the models, the ensemble bagged trees algorithm achieved the best results with an accuracy of 98%.

An In-Ear PPG-Based Blood Glucose Monitor: A Proof-of-Concept Study

“…Figure 6 shows that for all the subjects, the PPG cycles were found to have higher amplitudes and narrower peaks during low glucose periods. Based on this observation and the available literature [ 12 , 13 , 14 , 15 , 16 , 17 , 18 , 29 , 30 , 31 ], we created features that capture this change in the dynamics at different glucose levels, as shown in Figure 7 . In addition to these features, the energy profile of each cycle was calculated using the Teager–Kaiser energy operator (TKEO), a feature commonly used to quantify the instantaneous energy profile in periodic components of signals [ 15 , 16 , 17 , 18 ].…”

“…The principle of PPG is that blood with a higher concentration of glucose will have different absorbance than blood with lower glucose levels. This will affect the shape of the PPG signal which can then be used to indirectly estimate the blood glucose level through a mapping onto a set of features that are fed into the machine learning algorithms [ 12 , 13 , 14 , 15 , 17 , 18 , 29 ].…”

“…The NIR region of the electromagnetic spectrum lies between 700–2500 nm. It penetrates the skin in the mm range, depending on the wavelength [ 11 ], and has been adopted for the development of continuous non-invasive BGM devices at various body locations [ 12 , 13 , 14 , 15 , 16 , 17 , 18 ]. These devices mainly derive the glucose level from features extracted from photoplethysmography (PPG) waveforms, which can be acquired from any part of the skin that has blood vessels [ 19 ]—most commonly from the fingers, wrist, and earlobes.…”

Sense and Learn: Recent Advances in Wearable Sensing and Machine Learning for Blood Glucose Monitoring and Trend-Detection

“…A recent study demonstrated the application of a PPG device in the classification of blood glucose levels into normal and diabetic ( Susana et al, 2022 ). With PPG signal and blood glucose data collected from 80 participants, the study reported an accuracy of 98% with a decision tree based classifier.…”

Noninvasive Method for Measuring the Blood Glucose Level Using a Narrow Band Microstrip Antenna

“…Microwave filters or antennas are employed for monitoring glucose levels in the blood [24][25]. This is a non-invasive technology that has been developed.…”