A. Izworski, J. Bulka, and I. Wochlik (Poland)
Intelligent Data Base System, Medical Informatics, Neural Networks, ABR Signal
The paper presents the currently realized data base system for analysis of ABR's registered during screening and di agnostic examinations. The objective of the project is the construction of a unified acquisition technique for audi tory brainstem response (ABR) signals and elaboration of a processing method capable of their automated analysis. The unification of signal acquisition (which are at present collected and registered in somewhat different ways in various research centers) should be an essential step to wards the introduction of country-wide database of ABR signals. Furthermore the automation of the analysis of ABR signals is oriented towards the detection of wave V in the ABR signals, what is of critical importance for evaluation of hearing abilities of the examined patients (mainly newborns/infants). For that task automated classi fication of ABR signals is proposed, with application of artificial neural networks (for assisting the diagnosis particularly in cases when less-experienced physicians are involved). In the final stage the combination of the present research topic with remote access to the database it will be possible to create a diagnostic advisory system, kind of expert system, covering the area of whole Poland and of fering the possibility of considerable unification and ob jectivisation of the ABR studies.
Important Links:
Go Back
