Liver Disease Classification Using the Elbow Method to Determine Optimal K in the K-Nearest Neighbor (K-NN) Algorithm

Diagnosing liver disease in the field of healthcare is not an easy task. However, by utilizing medical records as datasets and applying data mining methods such K-Nearest Neighbor (K-NN), we can analyze extract knowledge automatically. The K-NN method has proven to be more effective compared other it clusters new information selecting nearest neighbors based on value k. In this study, employed Elbow determine optimal k measuring error rate. test results revealed that was found 4, with lowest third test, achieved a training accuracy 80.5% testing 78.9%. After fine-tuning data, were able improve 82.2% for 77.1% testing. fourth encountered overfitting issues due imbalance caused inappropriate resampling, resulting model overly complex prone excessive noise.