Heart Attack Risk Sentiment Analysis Using K-means Clustering With Rapidminer

Abstract

This study discusses the analysis of patient grouping based on heart attack risk by applying the K-Means Clustering algorithm using RapidMiner software. In this modern era, patient health data is very important for early identification and prevention of serious diseases such as heart attack. To understand the patterns of patient characteristics related to this risk, a clustering process was carried out on a heart attack risk dataset obtained from Kaggle, consisting of 8,763 patient data entries. The research stages began with data collection, data preprocessing, and the implementation of the K-Means algorithm with a certain number of clusters (e.g., three), which will group patients based on their risk profiles (e.g., low, moderate, and high risk). The research results are expected to show the distribution of patient data into these clusters, for example, how many patients fall into the high, moderate, and low-risk clusters. With these results, the K-Means algorithm proves effective in identifying groups of patients with similar characteristics, as well as providing useful insights for early detection and intervention of heart attack risk automatically. This research is expected to serve as a basis for the development of a more accurate and adaptive risk identification system for the dynamics of health data