Machine learning-based smart wearable system for cardiac arrest monitoring using hybrid computing

Abstract

Every year, the percentage of people affected by cardiovascular diseases increases drastically. Out of them, a heart attack is the most prominent and painful disease. According to the World Health Organization, approximately 17.5 million people lose their lives yearly due to this disease, which is alarming. The remarkable advancement in wearable technology has opened doors to propose many effective smart solutions to tackle this disease efficiently. Furthermore, early diagnosis of heart attack proliferates the compatibility of meditation and expedites the diagnostic recommendation by clinical experts. Considering this problem’s sensitivity, we proposed a wearable smart and early Heart Attack diagnosis system and adopted a decentralized computational phenomenon using hybrid computing architecture. It reflects better response time and minimal latency to detect a heart attack in its preliminary stage for homage patients. The proposed system can monitor and trigger the patient current heart status classified on required heart diagnosis parametric sensors assembled on the patient’s body with the help of an android application. In this study, three models are developed using the Support Vector Machine (SVM), Adaptive Boosting (AdaBoost), and Random Forest (RF) algorithms for the classification. Performance measures: accuracy, error rate, and response time are used to evaluate the proposed system. Our research findings promise that it can be implemented on patients diagnosed with the risk of a heart attack to monitor their heart health remotely and prevent sudden heart failure without impeding a person’s everyday life.