Theoretical Framework on Automatic Content Analysis Approach to Arrhythmia Clustering

Heart disease is one of the causes of death worldwide. One of the heart diseases is Arrhythmia. Therefore, early detection of arrhythmia is very important to reduce mortality. Studies to obtain Arrhythmia detection methods that can help doctors classify more quickly have also been carried out by many researchers both from within and outside the country. However, a fix and agreeable classification of arrhythmia is still lacking. This study explores the possible arrhythmia classification using Automatic Content Analysis from research article collection. The method used is the end-to-end life cycle automation system is the approach used in this research; however, only four of the seven stages of gathering, framework design, and platform design were used in this report this study obtained a result by using the K-Elbow Visualizer from the Yellowbrick library to calculate the ideal number of clusters for the K-means method. The elbow plots were examined, and the locations of the elbows can be used to determine the ideal number of clusters for additional clustering analysis. 4 clusters were obtained in this elbow-based study.