APPLICATION OF PATTERN-RECOGNITION AND IMAGE CLASSIFICATION TECHNIQUES TO DETERMINE CONTINUOUS CARDIAC-OUTPUT FROM THE ARTERIAL-PRESSURE WAVE-FORM
APPLICATION OF PATTERN-RECOGNITION AND IMAGE CLASSIFICATION TECHNIQUES TO DETERMINE CONTINUOUS CARDIAC-OUTPUT FROM THE ARTERIAL-PRESSURE WAVE-FORM
复制标题
DOI：
10.1109/10.324522
复制
发表时间：
1994-10-01
影响因子：
4.6
通讯作者：
SCHUKIN, VG
中科院分区：
文献类型：
--
作者：
MARTIN, JF;VOLFSON, LB;SCHUKIN, VG
动脉压波形的形状是每搏输出量、心率以及许多其他心血管参数的非线性函数。此前人们曾试图利用这种关系从动脉压波形推导出心输出量（CO）。这些经典的“脉搏轮廓”方法采用了简化的线性假设，结果是它们无法在足够广泛的血流动力学条件下准确估算心输出量。我们将模式识别和图像处理技术应用于从动脉压波形推导心输出量的问题，从而避免了简化假设的需要。利用计算机模拟来开发基本的模式识别算法，并将其性能与已发表的经典“脉搏轮廓”方法进行比较。随后利用动物模型来证明这一概念。在涵盖广泛血流动力学条件的20多万次个体心跳中，与超声血流探头测定的心输出量相比，计算所得心输出量的平均误差为2.8%，标准差为9.8%。
The shape of the arterial pressure waveform is a nonlinear function of stroke volume, heart rate and many other cardiovascular parameters. Previous attempts have been made to exploit this relationship and derive cardiac output (CO) from the arterial pressure waveform. These classical ''pulse-contour'' methods utilized simplifying linear assumptions, as a result they failed to adequately estimate CO over a sufficiently wide range of hemodynamic conditions. We have applied pattern recognition and image processing techniques to the problem of deriving CO from the arterial pressure waveform, thereby eliminating the need for simplifying assumptions. Computer simulations were used to develop the basic pattern recognition algorithms and compare their performance with that of published classical ''pulse-contour'' methods. Animal models were subsequently used to demonstrate proof of the concept. For over 200, 000 individual heart beats, covering a wide range of hemodynamic conditions, the mean error, in calculated CO compared to ultrasonic how probe de termined CO, was 2.8% with a standard deviation of 9.8%.