Electrocardiogram Classification using Reservoir Computing with Logistic Regression
Escalona-Moran, M. A.; Soriano, M. C.; Fischer, I.; Mirasso, C. R.
IEEE Journal of Biomedical and Health Informatics 19, 892-898 (2015)
An adapted state-of-the-art method of processing information known as Reservoir Computing is used to show its utility on the open and time-consuming problem of heartbeat classification. The MIT-BIH arrhythmia database is used following the guidelines of the Association for the Advancement of Medical Instrumentation. Our approach requires a computationally inexpensive preprocessing of the electrocardiographic signal leading to a fast algorithm and approaching a real-time classification solution. Our multiclass classification results indicate an average specificity of 97.75% with an average accuracy of 98.43%. Sensitivity and positive predicted value show an average of 84.83% and 88.75%, respectively, what makes our approach significant for its use in a clinical context.