Apparatus and method for the detection and treatment of arrhythmias using a neural network

An arrhythmia control apparatus comprising:

• means for acquiring physiological signals representative of hearty activity of the patient;
• means for processing said physiological signals, said processing means including a plurality of neural networks coupled to said acquiring means for receiving the physiological signals, classifying said signals into pathological and non-pathological categories, and selecting therapy to be applied to the heart fi a pathological condition is determined to be present in the heart, said plurality of neural networks being arranged in series so that the output of one of said networks comprises the input of another of said networks, a first one of said plurality of neural networks extracting a series of features from said physiological signals, a second one of said plurality of neural networks being serially connected to said first neural network to receive said extracted features and classify said physiological signals into pathological and non-pathological categories based on said features, and a third one of said plurality of neural networks being serially connected to said second neural network and, in the event a pathological condition is determined to be present by said second network, selecting a therapy to be delivered to the heart based on such pathological condition;
• and,
• therapy means coupled to said processing means for delivering to the heart the therapy selected by said processing means.

A method of controlling arrhythmias in a patient's heart, comprising the steps of:

• acquiring physiological signals representative of heart activity of the patient;
• providing a processing means, including a plurality of neural networks, for receiving said physiological signals;
• operating said neural networks in such a manner that the output of one of said networks comprises the input of another of said networks;
• providing therapy means for delivering one of a plurality of different therapies to the heart;
• inputting said physiological signals into one of said neural networks;
• processing said physiological signals in said neural networks to detect whether an arrhythmia is present in the patient's heart and to select a therapy to be applied to the heart if said processing means determines an arrhythmia to be present;
• selecting, in one of said neural networks, the therapy to be delivered to the heart in the event a pathological condition is determined to be present in the heart;
• and
• delivering to the heart the therapy selected by said processing means.

A method of controlling arrhythmias in a patient's heart, comprising the steps of:

• acquiring physiological signals representative of heart activity of the patient;
• providing a processing means, including a plurality of neural networks, for receiving said physiological signals;
• operating said neural networks in such a manner that the output of one of said networks comprises the input of another of said networks;
• providing therapy means for delivering one of a plurality of different therapies to the heart;
• inputting said physiological signals into one of said neural networks;
• processing said physiological signals in said neural networks to detect whether an arrhythmia is present in the patient's heart and to select a therapy to be applied to the heart if said processing means determines an arrhythmia to be present;
• said processing step including the sub-steps of extracting a series of features from said physiological signals in a first one of said neural networks, receiving said extracted features and classifying said physiological signals into pathological and non-pathological categories based on said features in a second one of said neural networks, and in the event a pathological condition is determined to be present by said second neural network, selecting a therapy to be delivered to the heart based on such pathological condition;
• and,
• delivering to the heart the therapy selected by said processing means.