Comparison of Data Mining Techniques in Healthcare Data
The goal of this paper is to assist patient data scientists in obtaining a clear and straightforward comprehension of how to use clinical datamining technology to promote the production of research results that benefit doctors and patients.
Abstract
Data gathering technology is developed. A shrinking research area in medical science, demonstrating excellent results in assessing physician dangers and aid healthcare data in diagnostic judgment study development. As a result, data analysis has distinct benefits in clinical trials and large-scale research, particularly in big social datasets. This study compares five free and open-source data mining techniques: Decision tree, Regression, Support Vector Machine (SVM), Clustering analysis, and Association rules are some of the perspectives described by using 100 records as a sample. Our objective is to reveal the most accurate tool and technique for the classification task. Analysis may use the results to rapidly achieve a good result. Our experimental results show that there is no single tool or technique that always achieves the best result, but some achieve better results more often than others. In this paper, Decision Tree achieved the best result. The goal of this paper is to assist patient data scientists in obtaining a clear and straightforward comprehension of how to use clinical datamining technology to promote the production of research results that benefit doctors and patients.