K-means clustering combined with exploratory data analysis provides a fast and proficient computational method for predicting cardiopathy using clinical variables.
The enormous volume of data which is generated by healthcare industries needs to be managed and analyzed properly in order to derive meaningful information. These decisions are more accurate than intuition. Big data houses various hidden knowledge's or patterns which are required for decision making. Exploratory data analysis (EDA) gains insights into the data: discovers errors, locates proper data, verifies assumptions, extracts key variables, and examines correlations between factors. EDA is a data analytics method which excludes mathematical modelling and inferences. Data analytics is a lowcost technology and has a vital role in health care industries, various sources include emergency situations, biomedical research, epidemics, pandemics etc. In present work, we took Cleveland cardiopathy dataset and then utilized K-means method to identify risk variables that cause cardiopathy. Age, hypertension, sugarlevel, chest discomfort, Electrocardiogram at relaxation, heart palpitation, and three forms of angina are among the 209 records in the collection and it was found that Kmeans method is the most effective one because of its speed and the proficiency of its output, it gives output in about 8sec so, for the prediction of cardiopathy K-means clustering method is employed by analyzing data in association with a visualization dashboard, and the data that is visualized in tableau demonstrates that the forecast is correct.
Malik et al. (Fri,) studied this question.