PENERAPAN DECISION TREE DENGAN PENYEIMBANGAN DATA IMBALANCE MENGGUNAKAN UPSAMPLING DALAM PREDIKSI PENYAKIT LIVER

Acute liver disease has a significant impact on liver function and is often only detected at an advanced stage due to the lack of patient awareness for early examination. One of the challenges in treating liver disease is the delay in diagnosis, where many patients do not notice the early symptoms until their condition has worsened. Therefore, a predictive system is needed that can identify liver disease patients early on, allowing for regular check-ups and timely treatment. In this study, a classification model was developed using a machine learning approach, specifically the Decision Tree algorithm, by balancing the data in the minority class through upsampling. The research results show that this model is capable of predicting liver disease status with an accuracy rate of 89.22%, a recall of 88.45%, a precision of 83.21%, and an f1-score of 85.78%. In addition, the ROC-AUC value of 0.89 is categorized as a good classification. This model achieved a higher accuracy score than other studies with similar datasets. This system is expected to help improve early detection and expedite the treatment of liver disease patients.