A Comparative Study of Data Mining Algorithms for Electronic Health Record Analysis

Electronic Health Records (EHRs) have become pivotal in modern healthcare, offering vast, rich datasets suitable for data-driven insights. Data mining techniques can unlock these insights by identifying patterns, trends, and correlations critical for improving patient outcomes, optimizing hospital operations, and enhancing clinical decision-making. This paper presents a comparative study of prominent data mining algorithms—Decision Trees, Support Vector Machines, Naive Bayes, K-Nearest Neighbors, and Random Forest—applied to EHR data. We analyze their performance in terms of accuracy, interpretability, scalability, and computational efficiency. A new hybrid framework is proposed, integrating multiple algorithms to leverage their strengths in EHR analysis. Experimental results show improvements in predictive accuracy and classification efficiency.