Department of CSIE, National Cheng Kung University, Tainan 701, Taiwan.
School of Chinese Medicine, China Medical University, Taichung 404, Taiwan.
Sensors (Basel). 2020 Aug 17;20(16):4618. doi: 10.3390/s20164618.
In traditional Chinese medicine (TCM), pulse diagnosis is one of the most important methods for diagnosis. A pulse can be felt by applying firm fingertip pressure to the skin where the arteries travel. The pulse diagnosis has become an important tool not only for TCM practitioners but also for several areas of Western medicine. Many pulse measuring devices have been proposed to obtain objective pulse conditions. In the past, pulse diagnosis instruments were single-point sensing methods, which missed a lot of information. Later, multi-point sensing instruments were developed that resolved this issue but were much higher in cost and lacked mobility. In this article, based on the concept of sensor fusion, we describe a portable low-cost system for TCM pulse-type estimation using a smartphone connected to two sensors, including one photoplethysmography (PPG) sensor and one galvanic skin response (GSR) sensor. As a proof of concept, we collected five-minute PPG pulse information and skin impedance on 24 acupoints from 80 subjects. Based on these collected data, we implemented a fully connected neural network (FCN), which was able to provide high prediction accuracy (>90%) for patients with a TCM wiry pulse.
在中医(TCM)中,脉诊是诊断的最重要方法之一。通过在动脉经过的皮肤处施加坚实的指尖压力,可以感觉到脉搏。脉诊不仅成为中医从业者的重要工具,也成为许多西方医学领域的重要工具。已经提出了许多脉搏测量设备来获得客观的脉搏状况。过去,脉搏诊断仪器是单点感应方法,错过了很多信息。后来,开发了多点感应仪器来解决这个问题,但成本高得多,缺乏机动性。在本文中,基于传感器融合的概念,我们描述了一种使用智能手机连接到两个传感器的中医脉象估计的便携式低成本系统,其中包括一个光电容积脉搏波(PPG)传感器和一个皮肤电导传感器(GSR)。作为概念验证,我们从 80 名受试者的 24 个穴位上采集了五分钟的 PPG 脉搏信息和皮肤阻抗。基于这些采集到的数据,我们实现了一个全连接神经网络(FCN),它能够为中医弦脉患者提供高精度 (>90%)的预测。