Risk Factors for Lymphatic Filariasis in Endemic Areas of Papua Using Binary Logistic Regression Based on Synthetic Minority Over-sampling Technique

Neglected tropical diseases (NTDs), such as lymphatic filariasis (LF), are a significant issue in Indonesia. The high percentage of LF in Papua highlights the urgency of addressing LF in the area due to its devastating impact on the health and economy of the poor. Moreover, imbalanced outcome variable categories are a common issue in logistic regression analysis using medical data. One of the solutions to this problem is using Synthetic Minority Over-sampling Technique (SMOTE). Therefore, this study aims to provide an overview of LF cases in endemic areas of Papua and identify the factors that influence its occurrence using binary logistic regression analysis and the SMOTE method. The data utilized was the LF diagnosis status of individuals in endemic areas of Papua Province, Indonesia as contained in the Riset Kesehatan Dasar (Riskesdas) 2018. It was found that the SMOTE approach in binary logistic regression analysis can be used to address data imbalance. The following factors are significant: sex, age, occupation, education level, use of mosquito bite preventive measures, use of latrines for defecation, and participation in Mass Drug Administration (MDA).