PATIENT CLUSTERING OPTIMIZATION WITH K-MEANS IN HEALTHCARE DATA ANALYSIS

Abstract

 The technique known as K-Means is used in this study to optimize patient clustering for health care information analysis. Adopting an interpretivist mindset, a deductive method is utilized to improve the algorithm's efficiency and assess its resilience. Secondary data collection is used in descriptive research designs to enable in-depth analysis. The findings emphasize demographically-based patient cohorts, designed algorithms performance, along with algorithmic reliability. Accurate clustering is ensured by validation procedures, and the approach is compared to other approaches in a comparative analysis. Analyzing critically reveals both advantages and disadvantages. Scalability, hybrid models, along with interdisciplinary cooperation are encouraged in the recommendations. Subsequent research endeavors ought to explore sophisticated methodologies, dynamic aggregation, unsupervised machine learning, and ethical implications.