This webpage is a tool to rapidly screen for COVID-19 cases via basic hematological parameters alone, through the deployment of an Extreme Gradient Boosting machine learning model. The rationale here is to provide a more cost-effective and faster alternative to the conventionally used qRT-PCR test.
There are two classifier models to choose from, depepending upon feature availibility: one that requires only four parameters, and a second that requires fourteen.
This website is a deployment of an experimental machine learning based approach to screen for COVID-19 cases, research and testing purposes. Thus, medical decisions must NOT only be based on the results of this program, which is not a mature diagnostic tool as the accuracy of this approach is still under testing. As a result, the authors shall not be liable for any claim, damages or any other liabilities.
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." medRxiv (2023): 2023-03.[Under revision]