A robust and parsimonious machine learning method to predict ICU admission of COVID-19 patients

Abstract

In this article, we discuss the development of prognostic machine learning (ML) models for COVID-19 progression, by focusing on the task of predicting ICU admission within (any of) the next 5 days. On the basis of 6,625 complete blood count (CBC) tests from 1,004 patients, of which 18% were admitted to intensive care unit (ICU), we created four ML models, by adopting a robust development procedure which was designed to minimize risks of bias and over-fitting, according to reference guidelines. The best model, a support vector machine, had an AUC of .85, a Brier score of .14, and a standardized net benefit of .69: these scores indicate that the model performed well over a variety of prediction criteria. We also conducted an interpretability study to back up our findings, showing that the data on which the developed model is based is consistent with the current medical literature. This also demonstrates that CBC data and ML methods can be used to predict COVID-19 patients' ICU admission at a relatively low cost: in particular, since CBC data can be quickly obtained by means of routine blood exams, our models could be used in resource-constrained settings and provide health practitioners with rapid and reliable indications.

Keywords: COVID-19; Complete blood count; Machine learning; Prognostic models; eXplainable AI.

Fig. 1

Percentage of missing values in the dataset

Fig. 2

Scatter plot of the lymphocytes and neutrophils counts for the patients in the severity and normal clusters (see Section 2.2)

Fig. 3

Results of the nested CV for all the evaluated models

Fig. 4

ROC curves for the evaluated ML models

Fig. 5

Calibration curves for the evaluated ML models

Fig. 6

Decision curves for the evaluated ML models

Fig. 7

Shapley value–based interpretability analysis of the developed SVM model. For the sex variable, 1 denotes a male patient while 0 a female patient