Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Indonesian Journal of Artificial Intelligence and Data Mining
Hikmah, Maulida
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Discovering Prescription Patterns in Type 2 Diabetes Based on Demographic Attributes Using Association Rules Yani, Putri; Hikmah, Maulida; Mahdiana, Deni
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 3 (2025): November 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i3.38082

Abstract

Type 2 diabetes mellitus (T2DM) is a chronic disease that requires effective long-term therapeutic management. Appropriate and continuous treatment is crucial to prevent complications and improve patients’ quality of life. In clinical practice, prescription patterns vary significantly and are influenced by demographic and clinical characteristics. This study aimed to analyze prescription patterns of T2DM patients based on demographic and clinical attributes, and to identify frequently co-prescribed drug combinations using the Apriori algorithm. A total of 3,500 prescription records were obtained from RSUD H. Damanhuri Barabai. The analysis was conducted in two stages: (1) association between demographic factors (age, gender, blood pressure) and prescribed drugs, and (2) association among drugs regardless of patient demographics. With minimum support of 3%, confidence thresholds of 60% and 35%, and lift greater than 1.5, fifteen valid rules were identified in the demographic-to-drug analysis, and nine rules in the drug combination analysis. Strong patterns were observed, such as the prescription of Empagliflozin and Insulin Degludec for hypertensive patients aged 40–49, and the co-prescription of Acarbose and Glimepiride. These findings demonstrated that the Apriori algorithm was effective in identifying meaningful prescription patterns. Beyond methodological contributions, the results provide practical value for hospitals by supporting pharmacy managers in drug procurement planning, optimizing stock management, and designing distribution strategies that anticipate patient needs based on prescription trends.
Co-Authors Deni Mahdiana putri yani, putri