Deep Learning Enabled Early Predicting Cardiovascular Status Using Highly Sensitive Piezoelectric Sensor of Solution‐Processable Nylon‐11

Abstract Cardiovascular diseases are found as one of the major cause of deaths globally, these can be reduced substantially if early‐stage detection and intervention is possible. Regular monitoring of the arterial pulse is one of the possible solutions, however, existing technologies have put limitations, due instability in continuous monitoring, lack of information in real‐time recording of cardiovascular parameters and bulky instruments. A highly sensitive flexible piezoelectric sensor of nylon‐11 fabricated is introduced from simple solution processable technique. Which consists of a highly sensitive, flexible, conformable piezoelectric film, owing to its high mechanosensitivity (≈225 mV N⁻¹) in the subtle pressure range (0.001–1 kPa), and fast responsivity (≈4 ms), it is tested for assessing risk factors of cardiovascular diseases based on arterial pulse data. It is integrated with the internet of things (IoT) via system on a chip to facilitate remote healthcare monitoring. Deep learning algorithms is further interfaced with sensor for early detect and predict cardiovascular risks, showing an accuracy of >94% for predicting cardiovascular status. This piezoelectric sensor equipped with artificial intelligence and IoT has potential for monitoring the risk analysis of the cardiovascular diseases, daily activities, and facilitate to early predict the anomalous physiological changes in the body.