Status prediction and risk stratification of COVID-19 by machine and statistical learning analysis of routine laboratory tests

Abstract

The COVID-19 pandemic has placed a huge stress on an already overburdened health system. Diagnosis is based on detection of a positive RT-PCR test which may be delayed during peaks. Rapid diagnosis and risk stratification of high risk patients allows for prioritisation of resources for patient care. The study aims were to classify patients as COVID-19 positive or negative, and to further classify patients as severe or not severe based on outcomes using machine learning on routine laboratory tests. Data was extracted for all individuals who had at least one SARS-CoV-2 PCR test done via the NHLS between the periods of 1 March 2020 to 7 July 2020. Exclusion criteria: those 18 years, and those with indeterminate PCR tests. Results for 15437 patients (3301 positive and 12136 negative) were used to fit 6 machine learning models namely the logistic regression (LR) (the base model), decision trees (DT), random forest (RF), extreme gradient boosting (XGB), convolutional neural network (CNN) and self-normalising neural network (SNN). Model development was carried out by splitting the data into training and testing set of a ratio 70:30, together with 10- fold cross validation re-sampling technique. For risk stratification admission to high care or ICU was the outcome for severe disease. Performance of the models varied with diagnostic sensitivity ranging from 85.25% for SNN to 97.73% for the RF models. Area under curve ranged from 70% for DT to 93% for LR, with accuracy ranging from 84% for LR to 88% for SNN. For risk stratification: sensitivity was best for RF at 75% and accuracy of 75% for CNN. Area under curve ranged from 57% for CNN to 75% for RF. The models performed better on diagnostics as compared to risk stratification. In both tasks RF and SNN were the best performing models. Machine Learning (ML) can be incorporated into the laboratory information system and offers promise for early identification and risk stratification of COVID-19 patients, particularly in areas of resource-poor settings.