Article Impact Level: HIGH Data Quality: STRONG Summary of Advanced Materials, 2410312. https://doi.org/10.1002/adma.202410312 Xin Wang et al.
Points
- Researchers developed a self-adaptive pressure sensing platform (PSP) for continuous, non-invasive pulse and blood pressure monitoring, addressing variability in pulse signals.
- The PSP integrates traditional Chinese medicine principles, measuring pulse characteristics at “Cun, Guan, Chi” positions and adapting to floating, moderate, and sinking pulses for optimal data collection.
- A flexible pressure sensor array generates a 3D map of pulse data, capturing signals from multiple wrist points and depths, improving accuracy compared to traditional single-point sensors.
- The platform uses a machine learning regression model trained on pulse data to accurately predict systolic, diastolic, and mean arterial pressure, providing individualized monitoring.
- The PSP has the potential for real-time health monitoring and personalized care for cardiovascular conditions. Ongoing refinements aim to advance flexible sensing technology and digital TCM.
Summary
A team of researchers developed a novel, self-adaptive pressure sensing platform (PSP) to enhance the accuracy of continuous, non-invasive pulse and blood pressure monitoring. Traditional wearable pulse sensors face challenges due to the variability of pulse waves, which can differ among individuals and fluctuate over time, especially in those with cardiovascular disease. Inspired by the principles of pulse diagnosis in traditional Chinese medicine (TCM), the researchers integrated a fully printed flexible pressure sensor array with a machine learning-based regression model to predict blood pressure. The PSP design was validated in multiple human subjects, showcasing its ability to reliably monitor pulse rate, width, and length and predict systolic, diastolic, and mean arterial pressure.
Incorporating the TCM concepts of “Cun, Guan, Chi” positions and pulse characteristics like “floating, moderate, sinking,” the platform adapts to varying pulse signals to detect the optimal reading, even during activities or sedentary states. The sensor array creates a 3D map of pulse data across time and at various depths of the wrist. The system’s machine learning model, trained on this data, accurately predicts blood pressure levels, providing a more individualized and precise monitoring method. This innovation improves upon traditional pulse sensors, which typically collect data from a single wrist point, by capturing more comprehensive data across multiple wrist locations.
The PSP system’s proof-of-concept demonstrates its potential for long-term health monitoring, offering personalized and adaptive solutions for patients with cardiovascular conditions. The technology is expected to pave the way for future flexible sensing devices that can monitor health in real time and support the development of digital TCM. Researchers plan to refine the device and machine learning integration to improve healthcare monitoring and provide more accurate, individualized patient care.
Link to the article: https://onlinelibrary.wiley.com/doi/10.1002/adma.202410312
References Wang, X., Wu, G., Zhang, X., Lv, F., Yang, Z., Nan, X., Zhang, Z., Xue, C., Cheng, H., & Gao, L. (2024). Traditional chinese medicine (Tcm)‐inspired fully printed soft pressure sensor array with self‐adaptive pressurization for highly reliable individualized long‐term pulse diagnostics. Advanced Materials, 2410312. https://doi.org/10.1002/adma.202410312
