Uli Simarmata, Cindy (2025) Penerapan Data Mining Untuk Klasifikasi Penyakit Kanker Darah Menggunakan Metode Decision Tree. Other thesis, Universitas Islam Riau.

Text 203510512.pdf - Submitted Version Restricted to Registered users only Download (9MB) | Request a copy

Abstract

Blood cancer is one of the most serious diseases with a high mortality rate worldwide, including in Indonesia. Early detection and accurate diagnosis are crucial to prevent delays in treatment, which often become the main cause of the severity in patients. Data mining provides classification methods that can be utilized to detect blood cancer. In this study, the Decision Tree algorithm was selected as the classification method, implemented with testing using k-fold crossvalidation. The study aims to develop a classification system to identify blood cancer using clinical patient data, such as age, hemoglobin, leukocytes, platelets, erythrocytes, hematocrit, MCV, MCH, MCHC, RDW-CV, RDW-SD, PDW, MPV, P-LCR, basophils, eosinophils, neutrophils, lymphocytes, and monocytes. results showed that testing using k-fold cross-validation with 10 folds resulted in an average accuracy of 95%, precision 96% recall 96%, and f1-score 96%. Thus, the Decision Tree method is proven to be optimal and effective for determining the classification of blood cancer.

Actions (login required)

View Item