Early Diagnostic Prediction of Covid-19 using Gradient-Boosting Machine Model
This work addresses diagnostic shortages in developing countries, but it is incremental as it applies an existing method to a new dataset.
The authors tackled the problem of COVID-19 diagnostic delays by developing a gradient-boosting machine model to predict RT-PCR test results using eight binary features, achieving results based on a dataset from the Israeli Ministry of Health.
With the huge spike in the COVID-19 cases across the globe and reverse transcriptase-polymerase chain reaction (RT-PCR) test remains a key component for rapid and accurate detection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). In recent months there has been an acute shortage of medical supplies in developing countries, especially a lack of RT-PCR testing resulting in delayed patient care and high infection rates. We present a gradient-boosting machine model that predicts the diagnostics result of SARS-CoV- 2 in an RT-PCR test by utilizing eight binary features. We used the publicly available nationwide dataset released by the Israeli Ministry of Health.