Computers in biology and medicine
-
Comparative Study
Comparison of AR-based algorithms for respiratory sounds classification.
Respiratory sounds of pathological and healthy subjects were analyzed via autoregressive (AR) models with a view to construct a diagnostic aid based on auscultation. Using the AR vectors, two reference libraries, pathological and healthy, were built. ⋯ Performances of the classifiers were tested for different model orders. The best classification results were obtained for model order 6.
-
A pseudo steady-state model is proposed to analyze the effects of a vessel-length, blood-flow velocities, and the concentration levels of Va/Xa/phospholipid complex on the formation of thrombin in an arterial vessel. The outlet concentrations of thrombin are calculated in either physiological or pathological coagulation process. Among those factors, blood-flow velocity is the most important factor which affects the amount of thrombin formation. The model and its results might be used as a reference for those who clinically manage coagulation problems of patients with severe sepsis.