Zgheib, RitaKamalov, FiruzChahbandarian, GhazarEl Labban, Osman2021-12-072021-12-07© 20212021Zgheib, R., Kamalov, F., Chahbandarian, G., & Labban, O. E. (2021). Diagnosing COVID-19 on limited data: A comparative study of machine learning methods. In DS Huang, KH Jo, J. Li, V. Gribova & A. Hussain (Eds.), Intelligent Computing Theories and Application. ICIC 2021. Lecture Notes in Computer Science, Vol. 12837. (pp. 616–627). Springer, Cham. https://doi.org/10.1007/978-3-030-84529-2_52978-303084528-503029743http://hdl.handle.net/20.500.12519/476https://doi.org/10.1007/978-3-030-84529-2_52Given the enormous impact of COVID-19, effective and early detection of the virus is a crucial research question. In this paper, we compare the effectiveness of several machine learning algorithms in detecting COVID-19 virus based on patient’s age, gender, and nationality. The results of the experiments show that neural networks, support vector machines, and gradient boosting decision tree models achieve an 89% accuracy, and the random forest model produces an 87% accuracy in the identification of the COVID-19 cases. © 2021, Springer Nature Switzerland AG.enLicense to reuse abstract has been provided by Springer Nature and Copyright Clearance Center.COVID-19 detectionGBDTNeural networkRandom forestSVMConference PaperCopyright : © 2021, Springer Nature Switzerland AG.