Application of Non-inductive Intelligent Physical Sign Monitoring Equipment Based on Flexible Electronic Devices in the Diagnosis and Treatment of Cardiovascular Diseases

In the diagnosis, treatment, and rehabilitation of cardiovascular diseases, accurate monitoring of key physiological signs provides the fundamental basis for clinicians to assess patient status and formulate treatment strategies. Traditional monitoring instruments used to acquire physiological data, such as electrocardiogram (ECG) monitors and polysomnography systems, require physical connections through electrode leads or ECG patches, which may increase patient discomfort and the risk of adverse events. Therefore, the development of monitoring devices with non-invasive and multi-parameter sensing capabilities is of significant importance for clinical care, nursing practice, and long-term health management.

This project focuses on the development and clinical evaluation of a non-invasive intelligent monitoring device for human physiological signals. The device is designed in the form of a mattress installed on a conventional hospital bed to enable real-time, accurate, continuous, and non-invasive monitoring of important physiological parameters in cardiovascular patients, including heart rate, respiration, body temperature, and body posture. Monitoring data will be integrated with hospital information systems and patient-side digital platforms to support clinical decision-making, disease management, and remote health monitoring.

A clinical evaluation will be conducted prior to product commercialization to determine whether the monitoring performance of the mattress-based system is non-inferior to that of conventional bedside ECG monitoring systems. Large-scale, long-term, and continuous physiological data from cardiovascular patients will be collected and analyzed in real-world clinical settings. Advanced technologies, including artificial intelligence and cloud-based data processing, will be applied to store, analyze, and interpret physiological signals. These data will enable the generation of personalized health monitoring reports and corresponding clinical recommendations.

The results of this study are expected to provide essential clinical evidence supporting the development and industrialization of the non-invasive intelligent monitoring system. In addition, the study will generate key data required for device research and development, quality control standards, regulatory evaluation, and medical device registration certification, ultimately facilitating the stepwise translation of the technology into clinical practice.