A polynomial based algorithm for detection of embolism

The Transcranial Doppler ultrasound can be used to detect asymptomatic circulating cerebral emboli. Emboli indicate particles that can plug the arterial system. Asymptomatic emboli signals help to discover critical stroke events by taking the embolus activities into consideration. Cerebral emboli detection is searched deeply in the literature. But none of them proposed a polynomial method to generalize the solution of the emboli detection. High Dimensional Model Representation (HDMR) philosophy is an effective way of generating an analytical model for a given multivariate data modeling problem, that is, HDMR can be used in constructing a general polynomial model for detecting embolism. In this study, emboli related data set was collected from \(35\) different patients. HDMR based methods and various data mining techniques were used to detect emboli through that data set. The Euclidean Matrix Based Indexing HDMR method has an important superiority in terms of generating a polynomial model which can then be used in other emboli detection problems without a training process. The method also shows satisfactory results in generalizing the emboli characteristics when compared with the other methods.