Simple Non-Invasive Coronary Artery Disease Detection Using Machine Learning

The rising global prevalence of coronary artery disease (CAD), a severe condition hindering the heart's ability to efficiently pump blood, necessitates innovative solutions for early detection. This study introduces an uncomplicated, non- invasive approach for the early detection of coronary artery disease (CAD). It involves the use of a smart wristband capable of monitoring continuous heart rate. The gathered data is transmitted to an Android mobile application called Cardio-care, which is installed on the user's smartphone. If a user observes any abnormality in their heart rate while using the smart wristband and Cardio-care application, they are encouraged to check for other symptoms of coronary artery disease (CAD) displayed within the Cardio-care application. If an individual has reported experiencing more than three symptoms of coronary artery disease (CAD) within the Cardio- care application, they are strongly advised to proceed with an ECG (Electrocardiogram) evaluation, through ECG kit that contains AD8232 ECG sensor and adhesive electrodes. This non- invasive technique compares the user ECG with standard ECG images by using machine learning algorithms. If the ECG is matched with CAD ECG, then the user is advised to take the treatment from concerned doctor at earliest.