Show simple item record

dc.contributor.authorAti, Modafar
dc.contributor.authorAl-Bostami, Reem
dc.identifier.citationAti, M., & Al-Bostami, R. (2021, November). Multi Artificial Intelligence Approaches Comparisons for Chronic Disease Prediction. In 2021 IEEE 5th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE) (pp. 315-319). IEEE.en_US
dc.description.abstractChronic diseases are one of the most common causes of death worldwide, contributing to a significant global disease burden. These diseases are critical and persistent. They last for an extended period, shaping and affecting the quality of the individuals’ lives. That’s why it is important to create the appropriate systems in the right places to effectively predict diagnoses and help patients manage their conditions. This research is focused on creating an e-health management system that predicts the diagnosis of chronic diseases. The system eases the diagnosis process and reduces the severity of chronic diseases by detecting them at early stages and monitoring the patients’ health while getting adequate treatments. Six different classification algorithms were compared and evaluated based on performance measures such as accuracy, precision, and recall for chronic disease prediction to develop the system. The algorithms included Decision Tree, Naïve Bayes, Random Forest, SVM, K-Nearest Neighbor, and ANN. The results indicated that the Decision Tree algorithm performed the best with an accuracy of 99.4%, while SVM came second with an accuracy of 96.4%. Based on the output, the model will be supported by a web application developed using Ionic and Angular.en_US
dc.publisherIEEE Xploreen_US
dc.subjectArtificial intelligenceen_US
dc.subjectChronic disease predictionen_US
dc.subjectData miningen_US
dc.subjectMobile applicationen_US
dc.subjectHealth careen_US
dc.subjectChronic diseasesen_US
dc.titleMulti Artificial Intelligence Approaches Comparisons for Chronic Disease Predictionen_US
dc.title.alternativeJournal articleen_US

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record