Page 49 - AIH-1-4

Artificial Intelligence in Health

ORIGINAL RESEARCH ARTICLE
A multi-adaptive neuro-fuzzy inference

system with variable thresholds for heartbeat
classification

Roghayeh Rafieisangari and Nabiollah Shiri*

Department of Electrical Engineering, Shiraz Branch, Islamic Azad University, Shiraz, Iran

Abstract

Various heart disorders are non-invasively diagnosed using electrocardiograms
(ECGs). An ECG records a variety of waveforms, including P, QRS, and T waves,
which represent the electrical activity of the human heart. Cardiovascular diseases
are diagnosed by examining the length, form, and spacing of these waveforms.
This research develops a multi-adaptive, neuro-fuzzy inference system (MANFIS),
enhanced by a variable threshold approach, to enhance heartbeat classification
accuracy. The MIT-BIH arrhythmia database was utilized, and seven features were
extracted from each record. A subtractive clustering method was employed to
prepare the inputs for the MANFIS, enabling heartbeat classification. By applying
a variable threshold to the MANFIS outputs, classification accuracy was further
enhanced. The proposed method, termed variable-threshold MANFIS, can
separately detect normal sinus rhythm, left bundle branch block, right bundle
branch block, premature ventricular contraction, atrial premature condition,
*Corresponding author: and paced beat. This is achieved using six different ANFIS classifiers, each with
Nabiollah Shiri
(na.shiri@iau.ac.ir) its own threshold. The system was evaluated, achieving an accuracy of 98.33%,
a sensitivity of 93.12%, a specificity of 99.66%, a precision of 98.33, and an
Citation: Rafieisangari R,
Shiri N. A multi-adaptive neuro- F -score of 95.44. A distinct feature of this machine-learning-based model is
1
fuzzy inference system with its controllable threshold, which delivers promising results across all training,
variable thresholds for heartbeat testing, and validation datasets. The proposed diagnostic system is applicable
classification. Artif Intell Health.
2024;1(4):43-60. in new automated medical instrumentation and serves as a valuable tool in
doi: 10.36922/aih.3367 cardiology.
Received: April 4, 2024
Accepted: June 26, 2024 Keywords: Electrocardiograms signals; Feature extraction; Classification; Adaptive neuro-
fuzzy inference system; Subtractive clustering; Variable threshold
Published Online: October 24, 2024
Copyright: © 2024 Author(s).
This is an Open-Access article
distributed under the terms of the
Creative Commons Attribution 1. Introduction
License, permitting distribution,
and reproduction in any medium, The World Health Organization reports that the number one cause of death worldwide
provided the original work is is cardiovascular diseases (CVDs). In recent years, various programs have been
properly cited. implemented in increasingly diverse communities to reduce the incidence of both
Publisher’s Note: AccScience initial and recurrent cardiovascular events. To accomplish this, the electrocardiogram
Publishing remains neutral with (ECG) has emerged as the most widely utilized bio-signal for the early detection of
regard to jurisdictional claims in
published maps and institutional CVDs. The ECG graphically displays the electrical activity of the heart and is used to
affiliations. diagnose a range of heart conditions and anomalies. The ECG signals have been used

Volume 1 Issue 4 (2024) 43 doi: 10.36922/aih.3367