METHOD AND DEVICE FOR HEART, CARDIOVASCULAR AND RESPIRATORY MONITORING USING HIDDEN MARKOV MODELS AND NEURONAL NETWORKS

摘要

The invention relates to a method and a device for heart, cardiovascular and respiratory monitoring using Hidden Markov models and neuronal networks. A simple acoustic sensor system, e.g. an airborne sound microphone, is used to identify heart, respiratory and flow sounds in the chest region of a patient, which sounds are then digitized in a PC by means of an analog-to-digital converter. An adaptive software is trained, based on methods of signal processing and artificial intelligence, such as Hidden Markov models and neuronal networks, in such a manner as to identify pathological and non-pathological sound classes and to associate them, following a subsequent statistical evaluation thereof, with clinical pictures, e.g. cardiac arrhythmia, circulatory disorders or respiratory diseases.