Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Diabetes is classified as a chronic disorder characterized by elevated blood glucose levels resulting from insufficient insulin synthesis or inadequate responsiveness of body cells to insulin. The prevailing protocol at healthcare facilities involves the acquisition of necessary data for the diagnosis of diabetes through a range of diagnostic procedures, followed by the administration of treatment in accordance with the outcomes of those tests. The task of generating precise outcomes using diabetes prediction models is challenging due to limited data availability and the existence of outliers. This study presents a proposed prediction model for diabetes that involves preprocessing techniques applied to the raw data, followed by the utilization of Ensemble Classifiers. The Ensemble Classifiers consist of a combination of catboost, LDA, LR, Random Forest, and GBC. By employing pre-processing approaches and ensemble methodologies, we have achieved improved performance i.e. 90.62% accuracy. The weights of ML models are evaluated using their Area Under Curve (AUC) and receiver operating characteristic curve (ROC) results. This proposed approach helps for clinical trials and help to take precautions at early stage of diabetes.