Author(s)

Pélagie Hounguè, Annie Ghylaine Bigirimana

Laboratory of Data Science and Digital Inclusion, Institut de Mathématiques et de Sciences Physiques, Université d’Abomey-Calavi, Abomey-Calavi, Bénin.

Diabetes is a chronic disease. In 2019, it was the ninth leading cause of death with an estimated 1.5 million deaths. Poorly controlled, diabetes can lead to serious health problems. That explains why early diagnosis of diabetes is very important. Several approaches that use Artificial Intelligence, specifically Deep Learning, have been widely used with promising results. The contribution of this paper is in two-folds: 1) Deep Neural Network (DNN) approach is used on Pima Indian dataset to predict diabetes using 10 k-fold cross validation and 89% accuracy is obtained; 2) comparative analysis of previous work is provided on diabetes prediction using DNN with the tested model. The results showed that 10 k-fold cross-validation could decrease the efficiency of diabetes prediction models using DNN.

Deep Learning, Artificial Intelligence, Deep Neural Network, k-Fold Cross-Validation, Diabete Mellitus

Hounguè, P. and Bigirimana, A. (2022) Leveraging Pima Dataset to Diabetes Prediction: Case Study of Deep Neural Network. Journal of Computer and Communications, 10, 15-28. doi: 10.4236/jcc.2022.1011002.