The rapid growth of healthcare data has created opportunities for applying Machine Learning (ML) techniques to improve disease prediction and early diagnosis. Diabetes is one of the most prevalent chronic diseases worldwide, and early detection plays a critical role in preventing severe complications. This study focuses on developing a predictive framework for diabetes detection using multiple machine learning algorithms applied to patient health records. A dataset consisting of relevant medical attributes was utilized to train and evaluate six different ML algorithms, namely Artificial Neural Networks (ANN), Extreme Gradient Boosting (XGBoost), AdaBoost, K-Nearest Neighbours (KNN), Support Vector Machine (SVM), and Decision Tree (DT). The performance of these algorithms was analyzed and compared based on their prediction accuracy and effectiveness in identifying diabetes. Comparative evaluation helps determine the most reliable and efficient model for diabetes prediction. Furthermore, the proposed approach supports the development of an application where users can input medical parameters and obtain prediction results. The outcomes of this study demonstrate the potential of machine learning techniques in assisting healthcare professionals in early diagnosis and decision-making. By leveraging predictive analytics, the system can support medical practitioners in detecting diabetes at an early stage and improving patient care.
Building similarity graph...
Analyzing shared references across papers
Loading...
IJDIM
Building similarity graph...
Analyzing shared references across papers
Loading...
IJDIM (Tue,) studied this question.
www.synapsesocial.com/papers/69d893eb6c1944d70ce04d37 — DOI: https://doi.org/10.5281/zenodo.19452055
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: