A prediction model of outcome of SARS‑CoV‑2 pneumonia based on laboratory fndings

Abstract

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has resulted in thousands of deaths in the world. Information about prediction model of prognosis of SARS-CoV-2 infection is scarce.We used machine learning for processing laboratory fndings of 110 patients with SARSCoV-2 pneumonia (including 51 non-survivors and 59 discharged patients).The maximum relevance minimum redundancy (mRMR) algorithm and the least absolute shrinkage and selection operator logistic regression model were used for selection of laboratory features. Seven laboratory features selected in the model were: prothrombin activity, urea, white blood cell, interleukin-2 receptor, indirect bilirubin, myoglobin, and fbrinogen degradation products.The signature constructed using the seven features had 98% [93%, 100%] sensitivity and 91% [84%, 99%] specifcity in predicting outcome of SARS-CoV-2 pneumonia.Thus it is feasible to establish an accurate prediction model of outcome of SARS-CoV-2 pneumonia based on laboratory fndings.