Machine learning-reinforced noninvasive biosensors for healthcare

Abstract

The emergence and development of noninvasive biosensors largely facilitate the collection of physiological signals and the processing of health-related data. The utilization of appropriate machine learning algorithms improves the accuracy and efficiency of biosensors. Machine learning-reinforced biosensors are started to use in clinical practice, health monitoring, and food safety, bringing a digital revolution in healthcare. Herein, the recent advances in machine learning-reinforced noninvasive biosensors applied in healthcare are summarized. First, different types of noninvasive biosensors and physiological signals collected are categorized and summarized. Then machine learning algorithms adopted in subsequent data processing are introduced and their practical applications in biosensors are reviewed. Finally, the challenges faced by machine learning-reinforced biosensors are raised, including data privacy and adaptive learning capability, and their prospects in real-time monitoring, out-of-clinic diagnosis, and onsite food safety detection are proposed.