What is the clinical evidence from this study?

Study design: Other. Population: Arrhythmia. Intervention: Random forest classifier with mutual information feature selection vs. Other state-of-the-art approaches. Primary outcome: Overall accuracy and F1-scores for heartbeat classification.

March 25, 2020Open Access

Investigating Feature Selection and Random Forests for Inter-Patient Heartbeat Classification

JSJose Francisco Saenz-CogolloCenter for Advanced Studies Research and Development in Sardinia MAMaurizio AgelliCenter for Advanced Studies Research and Development in Sardinia

Key Result

A random forest classifier using selected features achieved an overall accuracy of 96.14% and F1-scores up to 97.97% for heartbeat classification on the MIT-BIH Arrhythmia Database.

Structured PICO

Population

MIT-BIH Arrhythmia Database

Intervention

Feature selection using a filter method based on mutual information ranking criterion and a random forest classifier

Comparator

Other state-of-the-art approaches

Outcome

Overall accuracy and F1-scores in the classification of normal beats, supraventricular ectopic beats, and ventricular ectopic beats

A random forest classifier using a small feature vector based on R-R intervals and QRS width achieves high accuracy (96.14%) in inter-patient heartbeat classification.

Abstract

Finding an optimal combination of features and classifier is still an open problem in the development of automatic heartbeat classification systems, especially when applications that involve resource-constrained devices are considered. In this paper, a novel study of the selection of informative features and the use of a random forest classifier while following the recommendations of the Association for the Advancement of Medical Instrumentation (AAMI) and an inter-patient division of datasets is presented. Features were selected using a filter method based on the mutual information ranking criterion on the training set. Results showed that normalized beat-to-beat (R–R) intervals and features relative to the width of the ventricular depolarization waves (QRS complex) are the most discriminative among those considered. The best results achieved on the MIT-BIH Arrhythmia Database were an overall accuracy of 96.14% and F1-scores of 97.97%, 73.06%, and 90.85% in the classification of normal beats, supraventricular ectopic beats, and ventricular ectopic beats, respectively. In comparison with other state-of-the-art approaches tested under similar constraints, this work represents one of the highest performances reported to date while relying on a very small feature vector.

AIに質問

Bookmark

View Full Paper