Abstract
Association Rule Mining (ARM), one of the most widely used techniques in data mining, has become increasingly important in the medical domain, especially for enhancing diagnostic processes and improving decision-making in healthcare. ARM is primarily employed to discover interesting and hidden relationships among large datasets, which in the case of healthcare, often consist of electronic health records (EHRs), clinical notes, laboratory results, imaging data, and patient demographic information. For instance, ARM has been applied in the detection of early signs of diabetes by linking lifestyle patterns and blood glucose levels, or in identifying the co-occurrence of cardiovascular symptoms that increase the likelihood of hypertension or heart failure. These discovered patterns help clinicians recognize probable conditions at earlier stages, thereby supporting preventive healthcare and reducing the risk of misdiagnosis.

This publication has 23 references indexed in Scilit: