An ECG T-wave anomalies detection using a lightweight classification model for wireless body sensors

Abstract

Various wearable devices are foreseen to be the key components in the future for vital signs monitoring as they offer a non-invasive, remote and real-time medical monitoring means. Among those, Wireless Body Sensors (WBS) for cardiac monitoring are of prominent help to early detect CardioVascular Diseases (CVD) by analyzing 24/24 and 7/7 collected cardiac data. Today, most of these WBS systems for CVD detection, include only limited automatic anomalies detection, particularly regarding ECG anomalies. Severe CVD, such as Myocardial Infarction or Ischemia, needs to achieve an advanced analysis of ECG waves known as P, Q, R, S and T. In particular, the T-wave and its specific changes. In this paper, we focus on T-wave anomalies detection in a context of WBS. Our study suggests an accurate and lightweight Twave changes detection model which suits well an ECG monitoring system based on WBS architecture. We performed a comparative study of 7 well-known supervised learning classification models, on real ECG data sets from 7 different leads. We compared the results from both perspectives of classification and processing times. Our results show that the C4.5 Decision Tree technique performs better results with 92.54% Accuracy, 96.06% Sensibility, 55.41% Specificity and 7.41% Error Rate.

Effect of oral clonidine premedication on PR interval in patients undergoing rhinoplasty and functional endoscopic sinus surgery (FESS)

“…12 27 A 2014 study on 40 patients undergoing cataract surgeries revealed that intravenous clonidine (4 μg/kg) administered 30 min before surgery resulted in a lower prevalence of arrhythmias and a reduced myocardial attack rate compared to the placebo group. 28 A separate investigation encompassed five hypertensive cases assessed four weeks after clonidine therapy (0.2 mg/day), revealing insignificant changes in electrocardiography or echocardiography. 5 Similarly, a 2008 study at Isfahan University of Medical Sciences involving 88 patients aged over 50, scheduled for surgery, demonstrated that administering 0.1 mg clonidine to the first group, as opposed to a placebo to the second group, resulted in a higher frequency of electrocardiographic changes in the second group.…”

ML-ECG-COVID: A Machine Learning-Electrocardiogram Signal Processing Technique for COVID-19 Predictive Modeling

“…The application of artificial intelligence [8] methods in Cardiovascular Medicine is transformative since it has enhanced the interpretation of large ECG datasets signals not visually clear to expert ECG interpreters. To illustrate the effectiveness of Machine Learning in cardiovascular diagnostics, the study of a cardiac monitoring system using Big-ECG [9] investigates the heart rate of stroke patients compared to healthy volunteers and using Random Trees model for classification stroke group and healthy volunteers their model achieved an accuracy of 95.6%.…”

Methodological identification of anomalies episodes in ECG streams: a systematic mapping study

“…Similarly, the Myocardial infraction detection algorithm MI detection algorithm surpasses the accuracy of traditional algorithms, achieving an impressive 98% accuracy rate [4]. It has been specifically designed for the detection of abnormalities in the ST segment and T-wave [5][6][7][8][9][10][11]. The MI detection algorithm is particularly focused on distinguishing between ST-segment elevation (STEMI) and non-ST segment elevation (NSTEMI) cases [12][13][14][15][16].…”