Electrocardiogram Analysis for Kratom Users Utilizing Deep Residual Learning Network and Machine Learning

Abstract

Kratom (Mitragyna speciosa Korth) is a common tropical plant found in Southeast Asia. Its leaves possess medicinal properties and are used to treat various ailments. However, the effects of kratom extract in terms of biological domains are still concerning. Although considerable studies have been conducted on the effects of kratom usage over the last few years, no study using in silico analysis of kratom users’ electrocardiogram (ECG) has been reported to date. This study aims to examine the long-term effects of kratom consumption using the ECG signals and deep learning (DL) network and machine learning techniques. Raw ECG signals were used as input for training and detecting abnormalities, and a deep residual learning network (DRLN) model was implemented to develop a feature extractor from single-lead datasets; the extracted features were used to train conventional machine learning classifiers. The confounding ECG abnormality factors, namely, age, sex, smoking, alcohol consumption, and exercise, were analyzed for association using the chi-square test. The main results of our study showed that kratom usage is not associated with ECG abnormalities. However, the ECG signal was affected more by gender than by the other factors; it exhibited the highest sensitivity and specificity (score = 0.63). While this study is limited to ECG abnormalities, the results indicate that long-term usage of kratom for its health benefits may be considered a safe and natural practice.