For monitoring or control of the artificial heart, it is very important to measure hemodynamic parameters such as cardiac output and blood pressure. It is required to obtain these parameters without direct measurement because the direct measurement using sensors positioned inside the body must cause many problems. The present study tried to estimate, without direct measurement, the waveform of cardiac output or blood pressure by means of an artificial neural network (NN) or a linear time series model (ARX model) on the basis of the data obtained from a mock circulatory system driven by an artificial heart. It was revealed that the NN may be superior to the ARX model from the view point of versatility which will be important on an application stage of the total artificial heart.
|Number of pages||10|
|Journal||Biomedical Engineering - Applications, Basis and Communications|
|Publication status||Published - 1996 Jan 1|
ASJC Scopus subject areas
- Biomedical Engineering