Classification of Drug Data Usage Using the K-Means Deep Algorithm to Minimize Drug Stock Shortages (Case Study: South Cikarang Community Health Center)

Efficient utilization of medicines is essential for effective health service delivery, especially in community health centers. This research explores the application of the K-Means clustering algorithm to categorize drug usage data and minimize stock shortages. This research, conducted at the South Cikarang Community Health Center, analyzed drug use patterns to identify drugs with high and low demand. Through data collection, cleaning, and pre-processing, medication use data is converted into a format suitable for clustering analysis. The clustering method approach can be applied to analyze the level of drug use produced by utilizing data sets to record the process of drug data results. The K-Means algorithm model applied has results that show new insights, namely grouping usage levels based on 2 clusters; cluster 1 (C0) is a high potential category consisting of 3.4 data from the tested dataset, and cluster 2 (C1) is Low Potential. Consists of 7.2 tested data, right? Collaborative testing can also produce collaborative testing results that show an average figure of 0.545.