School of Chinese Medicine, China Medical University, Taichung, Taiwan.
Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan.
J Med Syst. 2018 Apr 21;42(6):103. doi: 10.1007/s10916-018-0942-5.
Heart rate variability (HRV) is often used to assess the risk of cardiovascular disease, and data on this can be obtained via electrocardiography (ECG). However, collecting heart rate data via photoplethysmography (PPG) is now a lot easier. We investigate the feasibility of using the PPG-based heart rate to estimate HRV and predict diseases. We obtain three months of PPG-based heart rate data from subjects with and without hypertension, and calculate the HRV based on various forms of time and frequency domain analysis. We then apply a data mining technique to this estimated HRV data, to see if it is possible to correctly identify patients with hypertension. We use six HRV parameters to predict hypertension, and find SDNN has the best predictive power. We show that early disease prediction is possible through collecting one's PPG-based heart rate information.
心率变异性（HRV）通常用于评估心血管疾病的风险，并且可以通过心电图（ECG）获得相关数据。然而，通过光电容积脉搏波描记法（PPG）来收集心率数据现在变得更加容易。我们研究了使用基于 PPG 的心率来估计 HRV 和预测疾病的可行性。我们从患有和不患有高血压的受试者中获得了三个月的基于 PPG 的心率数据，并根据各种时间和频域分析形式计算了 HRV。然后，我们将数据挖掘技术应用于该估计的 HRV 数据，以确定是否可以正确识别高血压患者。我们使用六个 HRV 参数来预测高血压，发现 SDNN 具有最佳的预测能力。我们表明，通过收集个人的基于 PPG 的心率信息，可以实现早期疾病预测。
