Evaluation of ECG Features for the Classification of Post-Stroke Survivors with a Diagnostic Approach

Kalaivani Rathakrishnan,Se Jin Park,Seung-Nam Min

doi:10.3390/app11010192

Abstract

Stroke is considered as a major cause of death and neurological disorders commonly associated with elderly people. Electrocardiogram (ECG) signals are used as a powerful tool in diagnosing stroke, and the analysis of ECG signals has become the focus of stroke research. ECG changes and autonomic dysfunction are reportedly seen in patients with stroke. This study aimed to analyze the ECG features and develop a classification model with highly ranked ECG features as input variables based on machine-learning techniques for diagnosing stroke disease. The study included 52 stroke patients (mean age 72.7 years, 63% male) and 80 control subjects (mean age 75.5 years, 39% male) for a total of 132 elderly subjects. Resting ECG signals in the lying down position are measured using the BIOPAC MP150 system. The ECG signals are denoised using the discrete wavelet transform (DWT) method, and the features such as heart rate variability (HRV), indices of time and spectral domains and statistical and impulsive metrics, in addition to fiducial features, are extracted and analyzed. Our results showed that the values of the HRV variables were lower in the stroke group, revealing autonomic dysfunction in stroke patients. A statistically significant difference was observed in low-frequency (LF)/high-frequency (HF), time interval measured after the S wave to the beginning of the T wave (ST) and time interval measured from the beginning of the Q wave to the end of the T wave (QT) (p < 0.05) between the groups. Our study also highlighted some of the risk factors of stroke, such as age, male sex and dyslipidemia (p < 0.05), that are statistically significant. The k-nearest neighbors (KNN) model showed the highest classification results (accuracy 96.6%, precision 94.3%, recall 99.1% and F1-score 96.6%) than the random forest, support vector machine (SVM), Naïve Bayes and logistic regression models. Thus, our study reported some of the notable ECG changes in the study participants and also indicated that ECG could aid in diagnosing stroke disease.

Highlights

One of the major diseases associated with the elderly is a stroke and is considered as the second leading cause of death with the third most common cause of disability-adjusted life years (DALYs) [1,2]
The high-density lipoprotein (HDL) level was higher in the stroke group, whereas the low-density lipoprotein (LDL) and total cholesterol levels were found to be lower in the stroke subjects than the controls
We demonstrated the use of a machine-learning algorithms and developed a classification model with highly ranked ECG features obtained from various datasets, such as the heart rate variability (HRV) parameters of the time and spectral domains, statistical and impulsive metric variables and ECG intervals

Summary

Introduction

One of the major diseases associated with the elderly is a stroke and is considered as the second leading cause of death with the third most common cause of disability-adjusted life years (DALYs) [1,2]. In Korea, stroke is a major health burden that will substantially increase in the near future, and Korea is becoming the most rapidly aging society in the world [5]. Another study reported that the stroke mortality rate of Korea sharply increased, after the age of 70 years [2]. Every year, 105,000 people experience a new or recurrent stroke, and more than 26,000 people die due to stroke, which indicates that, every five min, a stroke attacks someone, and in every 20 min, a stroke kills someone in Korea This results in a substantial economic burden to Korea, with the total nationwide cost for stroke care nearly 3.3 billion US dollars in 2005 [1]. An early diagnosis of stroke can enable us to save the lives of people, and the research on stroke patients is very important for the effective utilization of medical resources

Objectives

Methods

Results

Discussion

Conclusion