Une approche de prédiction médicale basée sur les données cliniques utilisant des algorithmes d’apprentissage automatique
No Thumbnail Available
Date
2021
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In this work, we have designed four models to predict diabetes in order to reduce the
risk and the occurrence of complications of this disease on the health of the patient. To design
these models, we used four machine learning algorithms, i.e. K nearest neighbors KNN,
Decision trees DT, Support Vector Machine SVM, and Logistic Regression LR. The
performance of the obtained models was tested according to the accuracy of each model. The
highest accuracy rates were obtained in the decision tree model in both the split method
(Train / Test Split) and k_fold cross validation splitting model.
Keywords: machine Learning, K nearest neighbors, Decision trees, Support vector machine,
Logistic Regression, diabetes prediction, medical prediction.