Dataset Information

Monitoring blood pressure and cardiac function without positioning via a deep learning-assisted strain sensor array.

ABSTRACT: Continuous and reliable monitoring of blood pressure and cardiac function is of great importance for diagnosing and preventing cardiovascular diseases. However, existing cardiovascular monitoring approaches are bulky and costly, limiting their wide applications for early diagnosis. Here, we developed an intelligent blood pressure and cardiac function monitoring system based on a conformal and flexible strain sensor array and deep learning neural networks. The sensor has a variety of advantages, including high sensitivity, high linearity, fast response and recovery, and high isotropy. Experiments and simulation synergistically verified that the sensor array can acquire high-precise and feature-rich pulse waves from the wrist without precise positioning. By combining high-quality pulse waves with a well-trained deep learning model, we can monitor blood pressure and cardiac function parameters. As a proof of concept, we further constructed an intelligent wearable system for real-time and long-term monitoring of blood pressure and cardiac function, which may contribute to personalized health management, precise and early diagnosis, and remote treatment.

SUBMITTER: Li S

PROVIDER: S-EPMC10421034 | biostudies-literature | 2023 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Monitoring blood pressure and cardiac function without positioning via a deep learning-assisted strain sensor array.

Li Shuo S Wang Haomin H Ma Wei W Qiu Lin L Xia Kailun K Zhang Yong Y Lu Haojie H Zhu Mengjia M Liang Xiaoping X Wu Xun-En XE Liang Huarun H Zhang Yingying Y

Science advances 20230811 32

Continuous and reliable monitoring of blood pressure and cardiac function is of great importance for diagnosing and preventing cardiovascular diseases. However, existing cardiovascular monitoring approaches are bulky and costly, limiting their wide applications for early diagnosis. Here, we developed an intelligent blood pressure and cardiac function monitoring system based on a conformal and flexible strain sensor array and deep learning neural networks. The sensor has a variety of advantages, ...[more]

PMID: 37566652

Similar Datasets

Project description:Wearable strain sensors have been widely used for human activity monitoring. Most reported strain sensors have mainly focused on material engineering, high stretchability and large gauge factors. Few works have focused on strain sensor's robustness and reliability, including low hysteresis, good long-term stability, good electrode material stability, and low coupling effects under multi-input signals, which are the factors that limit practical strain sensor applications. To develop a high-performance strain sensor, we propose a flexible capacitive sensor structure with three-dimensional (3D) interdigital electrodes fabricated by vertically aligned carbon nanotubes. Compared with a traditional resistive strain sensor and a capacitive strain sensor with vertical sandwich electrodes, a strain sensor with horizontal parallel interdigital electrodes can benefit from low cross talk in terms of the normal force and improve substrate transparency. Additionally, embedding 3D electrodes into the substrate improves ultrahigh robustness with a low-pressure coupling effect under normal force. Moreover, compared with other reported works, the electrode variation under strain is small (less than 1.6%), which means that the perturbation of inert properties on device performance is small. Finally, the fabricated strain sensor achieves an ultralow hysteresis (0.35%), excellent pressure-insensitive performance (less than 0.8%), fast response (60 ms), good long-term stability, and good transparency. As an application example, a flexible strain sensor was successfully demonstrated as a wearable device for the precise monitoring of different types of human activities, including bending of the finger, knee, elbow, wrist, and neck with large strain signals and small strain signals generated by a mouth-opening activity. This excellent performance indicates that the flexible strain sensor is a promising candidate for human motion detection, soft robotics, and medical care.

Dataset Information

Monitoring blood pressure and cardiac function without positioning via a deep learning-assisted strain sensor array.

Publications

Monitoring blood pressure and cardiac function without positioning via a deep learning-assisted strain sensor array.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets