No abstract

No abstract

The cuffless blood pressure (BP) monitoring device has attracted much attention because of its comfortable and real‐time monitoring. Inspired by the physical structure of the human epidermis, an ultra‐sensitive flexible resistive sensor with a double strain layer and crack structure is prepared by screen printing in this study. The strain material of the sensor is mainly prepared by blending Poly(3,4‐ethylenedioxythiophene) :poly(styrenesulfonate) (PEDOT:PSS) with waterborne polyurethane and reduced graphene oxide. The sensor exhibits a high gauge factor (GF, ≈1682), fast response (≈48 ms), and long‐term stability (> 2000 cycles) at low strain (≈0–5%). The sensor is placed on the human radial artery and can accurately measure the pulse wave. The features of the pulse wave are automatically extracted using a convolutional neural network. Then the features are corrected using a long short‐term memory neural network, and the current BP value is predicted using a fully connected network layer. The BP result meets the A‐level standards of the Association for the Advancement of Medical Instrumentation and the British Hypertension Society. This study provides an efficient device and method for continuous and non‐invasive BP monitoring.

No abstract

No abstract