| Sumario: | Diabetes is considered as one of the deadliest and chronic diseases which cause an increase in blood sugar. Many complications occur if diabetes remains untreated and unidentified. The tedious identifying process results in visiting of a patient to a diagnostic centre and consulting doctor. But the rise in machine learning approaches solves this critical problem. The motive of this study is to design a model which can prognosticate the likelihood of diabetes in patients with maximum accuracy. Therefore these machine learning classification algorithms namely Naive Bayes, Logistic regression, Instance Base Method (K-NN), Ensemble Methods (Random Forest & XG-Boost) and Decision Tree are used in this experiment to detect diabetes at an early stage. Experiments are performed on Pima Indians Diabetes Database (PIDD) which is sourced from UCI machine learning repository. The performances of all these algorithms are evaluated on various measures like Precision, Accuracy, F-Measure, and Recall and Confusion Matrix. Accuracy is measured over correctly and incorrectly classified instances. Results obtained show Logistic Regression outperforms with the highest accuracy of 78.30% comparatively other algorithms. These results are verified using Receiver Operating Characteristic (ROC) curves.
|
|---|