Implementation of the Adaboost Method to Increase the Accuracy of Early Diabetes Predictions to Prevent Death Decision Tree-Based

Alam, Laskar

Advance Sustainable Science, Engineering and Technology (ASSET)
Vol 6, No 2 (2024): February - April

This research discusses the importance of early diabetes prediction and efforts to increase prediction accuracy using a Decision Tree Learning Algorithm and integration of the Adaboost Method. This study uses a data set from Kaggle with 520 records, 16 attributes, and one positive or negative diabetes class. The evaluation method used is the Confusion Matrix. The research results showed that the Decision Tree algorithm achieved an accuracy of 94.23%, but after integrating the Adaboost Method, the accuracy increased to 97.31%. The implications of these findings emphasize the importance of predictive approaches in early disease detection and highlight the potential of the Adaboost method in improving the accuracy of diabetes prediction.