非侵入式連續橈動脈血壓波形量測使用粒子群聚最佳化法

Abstract

血壓波形是重要的生理資訊，隱含著心臟血管功能的 重要訊息。中醫脈診更是橈動脈血壓作用於血管壁 ，呈 現於把脈觸感用以做疾病診斷。橈動脈血壓波形常見於 醫院加護病房或手術房，均以侵入式為之，本論文提出 非侵入的方法建立連續橈動脈血壓波形 ，可使用於居家 照護，沒有造成血栓、感染的危險。以手指光學血液容 積信號，配合粒子群聚最佳化法及 fuzzy C-means 建立最 佳波形轉換函數庫，使不同特徵的光學血液容積信號均 有最佳轉移函數，以獲的精確的橈動脈血壓波形，波型 相似性達 0.89，優於 ARX 模型。The blood pressure waveform is an important physiology information, implicit the important information of the cardiovascular functions. Chinese medicine Pulse diagnosis is also the radial artery blood pressure waveform at the afferent wall, occurring to do touch in order to disease diagnosis. The radial artery blood pressure waveform is familiar at the hospital intensive care unit(ICU) or the surgical operation room all taking invasively. A noninvasive method in measuring blood pressure waveforms is proposed in this paper, based on which we can use the signals of fingertip photoplethysmogram to reconstruct radial pressure waveforms. Characteristics of various photoplethysmogram will be categorized into 3 clusters by using fuzzy C-mean clustering. A particle swarm optimization scheme is then esblihed to search for an optimal transfer function model for estimating the radial pressure waveforms. Experiment results show that correlation ratio of the transformed waveforms can be as high as 0.89, much better than the results via the ARX technique