Title :
A patient-adaptive neural network ECG patient monitoring algorithm
Author :
Watrous, R. ; Towell, G.
Author_Institution :
Siemens Corp. Res. Inc., Princeton, NJ, USA
Abstract :
A new, patient-adaptive ECG patient monitoring algorithm is described. The algorithm combines a patient-independent neural network classifier with a three-parameter patient model. The patient model is used to modulate the patient-independent classifier via multiplicative connections. Adaptation is carried out by gradient descent in the patient model parameter space. The patient-adaptive classifier was compared with a well-established baseline algorithm on six major databases, consisting of over 3 million heartbeats. When trained on an initial 77 records and tested on an additional 382 records, the patient-adaptive algorithm was found to reduce the number of Vn errors on one channel by a factor of 5, and the number of Nv errors by a factor of 10. We conclude that patient adaptation provides a significant advance in classifying normal vs. ventricular beats for ECG patient monitoring.
Keywords :
adaptive signal processing; electrocardiography; feature extraction; medical expert systems; medical signal processing; neural net architecture; patient monitoring; pattern classification; baseline algorithm on; gradient descent; heartbeats; multiplicative connections; normal beats; patient adaptation; patient model parameter space; patient-adaptive neural network ECG patient monitoring algorithm; patient-independent neural network classifier; rule based expert system; three-parameter patient model; ventricular beats; Clustering algorithms; Computer networks; Context modeling; Databases; Electrocardiography; Heart rate variability; Morphology; Neural networks; Patient monitoring; Testing;
Conference_Titel :
Computers in Cardiology 1995
Conference_Location :
Vienna, Austria
Print_ISBN :
0-7803-3053-6
DOI :
10.1109/CIC.1995.482614