This webpage serves as a diagnostic tool for the rapid screening of COVID-19 cases using basic hematological parameters. It employs an Extreme Gradient Boosting machine learning model to facilitate detection. The objective is to offer a more cost-effective and time-efficient alternative to the conventional standard quantitative reverse-transcription polymerase chain reaction (qRT-PCR) test.
Two classifier models are available, selected based on feature availability: one requiring only four hematological parameters and another needing fourteen parameters for prediction of COVID-19 disease.
DISCLAIMER
This website implements an experimental machine learning-based approach for screening COVID-19 cases, intended solely for research and testing purposes. Therefore, medical decisions should NOT be based solely on the results generated by this program, as it is not a fully validated diagnostic tool and its accuracy remains under evaluation. Consequently, the authors disclaim any liability for claims, damages, or other legal responsibilities arising from its use.
For further details on this method, please refer to Safdari, A., Bandyopadhyay, D., et al. "The External Validity of Machine Learning-Based Prediction Scores from Hematological Parameters of COVID-19: A Study Using Hospital Records from Brazil, Italy, and Western Europe." PLOS ONE, Public Library of Science (PLoS), 4 Feb. 2025.