An Artificial Intelligence-Enhanced Blood Pressure Monitor Wristband Based on Piezoelectric Nanogenerator

Abstract

Hypertensive patients account for about 16% to 37% of the global population, and about 9.4 million people die each year from hypertension and its complications. Blood pressure is an important indicator for diagnosing hypertension. Currently, blood pressure measurement methods are mainly based on mercury sphygmomanometers in hospitals or electronic sphygmomanometers at home. However, people's blood pressure changes with time, and using only the blood pressure value at the current moment to judge hypertension may cause misdiagnosis. Continuous blood pressure measurement can monitor sudden increases in blood pressure, and can also provide physicians with long-term continuous blood pressure changes as a diagnostic reference. In this article, we design an artificial intelligence-enhanced blood pressure monitoring wristband. The wristband's sensors are based on piezoelectric nanogenerators, with a high signal-to-noise ratio of 29.7 dB. Through the transformer deep learning model, the wristband can predict blood pressure readings, and the loss value is lower than 4 mmHg. By wearing this blood pressure monitoring wristband, we realized three days of continuous blood pressure monitoring of the subjects. The blood pressure monitoring wristband is lightweight, has profound significance for the prevention and treatment of hypertension, and has wide application prospects in medical, military, aerospace and other fields.

Keywords: artificial intelligence; biosensors; deep learning; piezoelectric nanogenerator; self-powered.

Figure 1

The overview of BPPW. (A) The structure of BPPW and the materials used in each part. (B) The photograph of subjects wearing BPPW. (C) The photograph of BPPW; the whole length of BPPW is 26 cm. (D) The design concept of BPPW.

Figure 2

The working principle of BPPW. (A) The structure and materials used of sensor in BPPW. (B) The pulse wave travels from the heart to the wrist. (C) The generation principle of the PENG based sensor used in BPPW. (D) Comparison between BPPW and PRAS, the upper is the BPPW signal and the bottom is the PRAS signal. The open-circuit voltage (E), short-circuit current (F) and the charge (G) output of the BPPW.

Figure 3

The influence of microstructure differences of structural layers on sensor output. (A) The influence of the four structures type on the output, these four structure types including no microstructure type, cylindrical type, prismatic type and no structure layer type. (B) The influence of the microstructure length on the output. (C) The influence of microstructure spacing on the output. (D) The circuit diagram of the BPPW. (E–H) The finite element analysis of potential generation for four microstructures.

Figure 4

The output performance of the BPPW. (A) Robustness test results of BPPW. (B) BPPW monitors the subjects’ blood pressure and the readings of the sphygmomanometer at different times of the day. (C) The difference in time between two sensors at different locations.

Figure 5

The application of BPPW. (A) The process of BPPW’s deep learning model establishment. (B) The sample distribution of the training model. (C) The loss value decreases with the increase in training epochs. (D) A potential hypertensive patient wears a BPPW for three consecutive days, and BPPW predicts his blood pressure. According to BPPW’s prediction, at 12:00 and 16:00 on the first day and at 20:00 on the third day, the subjects’ diastolic blood pressure values all exceeded the normal blood pressure range.