Advancements in Photonic Biosensor Technologies and Machine Learning Algorithms for Continuous Glucose Monitoring in Diabetes Management

View at publisher Summarise with VIRAT
Authors: B. Naveen Kumar, Suresh Kallam, Preeta Sharan, M. Kumaresan
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This Continuous glucose management (CGM) is changing due to advances in ML algorithms as well as in photonic biosensor technologies. Various biofluids, such as blood, sweat, saliva, tears, and interstitial fluid, are sensed through noninvasive and accurate photonic biosensors using light methods. CMG devices are paired with machine learning algorithms that provide real-time information, predictive insights, and personalized glycaemic control. The integration of these technologies overcomes the problems of invasive, biofouled, expensive, and time-lag-burdening conventional CGMs. Recently, sensors augmented with nanomaterials have become more accurate and biocompatible. Glycaemic prediction generated early to aid dynamic insulin adjustments to prevent glycaemic excursions is based on ML-driven prediction models. Data-sharable, remote healthcare monitoring capabilities are also offered by wearable biosensors in conjunction with Internet of Things (IoT) devices. But, as with any emerging technology, there remain obstacles to biofouling mitigation, long-term sensor stability, and cost reduction. This study demonstrates the revolutionary potential of photonic biosensing and machine learning for optimal glycaemic control and improved patient outcomes.

Fields of Study & Subjects

Spectroscopy Techniques in Biomedical and Chemical Research Diabetes Management and Research Non-Invasive Vital Sign Monitoring

Publication details

Journal / source
CRC Press eBooks
Pages
368–373
Publication date
31 March 2026
Language
EN
Document type
Book chapter