Towards An Optimized Decision Tree Model For Covid-19 Prediction

Résumé: The coronavirus pandemic has had a dramatic impact on worldwide healthcare and economic systems. Interestingly, a lot of interest has been devoted to Machine learning technological innovations, such as Decision Trees, for promoting reliable decision aid support. In this paper, we propose a decision tree-based learning approach to predict COVID19 infections at its earlier stage and to improve the organization of care and patient follow-up. We show how this approach can be exploited in association with a cross-platform mobile application to provide an operational proof-of-concept. Experiments performed on a real COVID-19 dataset show the efficiency of our approach and its significant advantages in a healthcare context.

Publié dans la revue: Models & Optimisation and Mathematical Analysis Journal