Background: It is very important to determine the risk of patients developing severe or critical COVID-19, but most of the existing risk prediction models are established using conventional regression models. We aim to use machine learning algorithms to develop predictive models and compare predictive performance with logistic regression models.
Methods: The medical record of 161 COVID-19 patients who were diagnosed January–April 2020 were retrospectively analyzed. The patients were divided into two groups: asymptomatic-moderate group (132 cases) and severe or above group (29 cases). The clinical features and laboratory biomarkers of these two groups were compared. Machine learning algorithms and multivariate logistic regression analysis were used to construct two COVID-19 risk stratification prediction models, and the area under the curve (AUC) was used to compare the predictive efficacy of these two models.
Results: A machine learning model was constructed based on seven characteristic variables: high sensitivity C-reactive protein (hs-CRP), procalcitonin (PCT), age, neutrophil count (Neuc), hemoglobin (HGB), percentage of neutrophils (Neur), and platelet distribution width (PDW). The AUC of the model was 0.978 (95% CI: 0.960– 0.996), which was significantly higher than that of the logistic regression model (0.827; 95% CI: 0.724– 0.930) (P =0.002). Moreover, the machine learning model’s sensitivity, specificity, and accuracy were better than those of the logistic regression model.
Conclusion: Machine learning algorithms improve the accuracy of risk stratification in patients with COVID-19. Using detection algorithms derived from these techniques can enhance the identification of critically ill patients.
Keywords: COVID-19, machine learning, prediction model, high sensitivity C-reactive protein, procalcitonin