<![CDATA[Drug inventory planning is a crucial aspect in logistics management in first-level health care facilities, as the availability of the right type and quantity of drugs greatly affects the quality of service and patient safety. However, in practice, there are still various problems, such as the mismatch between the amount of stock and the real need for limitations in the use of historical data on drug transactions, and the lack of optimal systems in identifying drug use patterns in a structured and data-based manner. This condition has the potential to cause stockouts and overstock, which has an impact on delays in the delivery of therapy, wasted budgets, and increased risk of expired drugs. In addition, the lack of analysis of drug use combinations also hinders more accurate decision-making in inventory planning and control. Based on these problems, this study aims to apply the Multi-Level Association Rule Mining (MLARM) method in identifying combinations of drug use based on transaction data at health facilities. The results of the study showed that the MLARM method was effective in identifying patterns of drug use associations at various levels of the hierarchy. At the drug class level, it was found that there was a relationship between hard drugs, over-the-counter drugs, and limited over-the-counter drugs which reflected the use of combinations between drug classes in health services. At the group level of therapy, the association involves analgesics, antibiotics, antihistamines, corticosteroids, and decongestants. Meanwhile, at the level of drug names, specific combinations were found, such as Mms with Kalk, Fe with Paracetamol, Ctm with Paracetamol, and Mefenamic Acid with Amoxicillin. This information can be used to support more optimal management of drug supplies and reduce the risk of stockout and overstock.]]>
