| Title |
A Prediction of Coronary Perfusion Pressure Using the Extracted Parameter From Ventricular Fibrillation ECG Wave |
| Authors |
장승진(Jang Seung-Jin) ; 황성오(Hwang Sung-Oh) ; 윤영로(Yoon Young-Ro) ; 이현숙(Lee Hyun-Sook) |
| Abstract |
Coronary Perfusion Pressure(CPP) is known for the most important parameter related to the Return of Spontaneous Circulation (ROSC), however, clinically measuring CPP is difficult either invasive or non-invaisive method. En this paper, we analyze the correlation between the extracted parameter from VF ECG wave and the CPP with the statistical method, and predict CPP value using the extracted parameters within significance level. the extracted parameters are median frequency(MF), peak frequency(PF), average segment amplitude(ASA), MSA(maximum segment amplitude), Two parameters, MF, and ASA are selected in order to predict CPP value with general regression neural network, and then we evaluated the agreement statistics between the simulated CPP and the measured CPP. In conclusion, the mean and variance of the difference between the simulated CPP and the measured CPP are 8.9716¡¾1.3526 mmHg, and standard deviation 6.4815 mmHg with one hundred-times training and test results. the simulated CPP and the measured CPP are agreed with the overall accuracy 90.68 % and kappa coefficient 81.14 % as a discriminant parameter of ROSC. |