Abstrak Artikel
Number of patients with liver disease in the worldis very high. In the early stages, liver disease is difficult todetect. Early diagnosis of the liver disease may help inpreventing and treating sufferers. To diagnose liver diseasecan be done with a blood test. Based on data from thisanalysis, the results can assist in determining patients withliver disease. This study uses data Indian Liver Patient Dataset(ILPD) taken from the UCI Machine Learning Repository. Weused Modified k-Nearest Neighbor to classify into two classes,namely sufferers and non-sufferers. The amounts of data usedin this study were 583 records. Tests performed by dividingthe training data and test data to 50:50, 60:40, 70:30 and80:20. Results of tests performed can classify with a gooddegree of accuracy reached 85.14% with a ratio of 70:30 and k= 3.
Pratinjau PDF
Pastikan PyMuPDF terpasang lalu coba muat ulang.