ABSTRACT
Continuous and non-invasive measurement of blood pressure (BP) is of great importance particularly for patients in critical state. To achieve continuous and cuffless BP monitoring, pulse transit time (PTT) has been reported as a potential parameter. Nevertheless, this approach remains very sensitive, cumbersome and disagreeable in ambulatory measurement. This paper proposes a new approach to estimate blood pressure through PCG signal by exploring the correlation between PTT and diastolic duration (S21). In this purpose, an artificial neural network was developed using as input data: (systolic duration, diastolic duration, heart rate, sex, height and weight). According to the NN decision, the mean blood pressure was measured and consequently the systolic and the diastolic pressures were estimated. The proposed method is evaluated on 37 subjects. The obtained results are satisfactory, where, the error in the estimation of the systolic and the diastolic pressures compared to the commercial blood pressure device was in the order of 6 .48 ± 4.48 mmHg and 3 .91 ± 2.58 mmHg, respectively, which are very close to the AAMI standard, 5 ± 8 mmHg. This shows the feasibility of estimating of blood pressure using PCG.