Non-invasive blood glucose monitoring technology has been advanced

Recently, Nie Zedong’s team from the Minimally Invasive Center of the Institute of Medical Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, has made new progress in non-invasive blood glucose monitoring technology based on physiological information, and the relevant research results were published in IEEE Neural Network and Learning System Collection.

This study reveals the applicability of analyzing blood glucose changes based on wearable non-invasive devices, which is expected to be applied to the management of chronic diseases in diabetes and the assessment of high-risk groups. In the study, Li Jingzhen, assistant researcher of Shenzhen Advanced Institute, was the first author of the paper, and Nie Zedong, a researcher of Shenzhen Advanced Institute, was the corresponding author of the paper.

With the improvement of people’s living standards and the acceleration of China’s population aging, the prevalence of diabetes is increasing year by year. Active glucose monitoring is one of the important means to effectively reduce diabetes and delay complications. At present, blood glucose monitoring is mainly through fingertip blood sampling or implantable blood glucose monitoring devices (CGMS) based on electrochemical detection technology, however, these methods have the disadvantages of pain, short service life, and high cost, which limit patient compliance.

Therefore, the development of a non-invasive, comfortable and convenient non-invasive monitoring technology is of great significance and clinical value to promote blood glucose monitoring. 

Relevant studies have shown that changes in blood glucose concentration will stimulate the autonomic nervous system of the human body, causing changes in physiological information such as electrocardiogram (ECG) and photoplethysmography (PPG), while considering that ECG and PPG can be obtained through smart wearable devices, which have the advantages of fast use and low cost.

In this regard, the researchers proposed a non-invasive glucose monitoring technology based on ECG and PPG multimodal fusion, which uses numerical calculation methods and deep learning algorithms to obtain the spatiotemporal characteristics of the above physiological information, and adopts the Choquet integral algorithm based on variable weights to achieve decision-making fusion of different modalities.

The scientific research team used non-invasive blood glucose monitoring technology to collect blood glucose data from volunteers Image source: scientific research team

The researchers used this technology to obtain a total of 103 days of data from 21 volunteers, and after 10-fold cross-validation, the MARD value of the proposed multimodal fusion algorithm in blood glucose monitoring reached 13.42%, and the A+B region of the consistency error grid was greater than 99%.

“MARD is the core indicator to evaluate the accuracy of CGM (continuous glucose monitoring) products, and most of the international standards for MARD are less than 15% as the CGM marketing standard, the smaller the value, the closer the blood glucose reading is to the reference value, that is, the higher the accuracy of blood glucose measurement.” Nie Zedong introduced that the proportion of error grid A + B area at the level of the measurement point is greater than 99%, which means that 99% of the data has clinical accuracy, and the larger the value, the higher the accuracy of blood glucose measurement.

It is understood that this achievement provides an important theoretical basis and technical support for non-invasive blood glucose monitoring based on wearable health devices and household health equipment, and has broad application prospects. (Source: China Science News, Diao Wenhui)

Related paper information:

Source link

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button