Predicting in-Hospital Mortality of Patients with COVID-19 Using Machine Learning Techniques

Abstract

The present work aims to identify the predictors of COVID-19 in-hospital mortality testing a set of Machine Learning Techniques (MLTs), comparing their ability to predict the outcome of interest. The model with the best performance will be used to identify in-hospital mortality predictors and to build an in-hospital mortality prediction tool. The study involved patients with COVID-19, proved by PCR test, admitted to the “Ospedali Riuniti Padova Sud” COVID-19 referral center in the Veneto region, Italy. The algorithms considered were the Recursive Partition Tree (RPART), the Support Vector Machine (SVM), the Gradient Boosting Machine (GBM), and Random Forest. The resampled performances were reported for each MLT, considering the sensitivity, specificity, and the Receiving Operative Characteristic (ROC) curve measures. The study enrolled 341 patients. The median age was 74 years, and the male gender was the most prevalent. The Random Forest algorithm outperformed the other MLTs in predicting in-hospital mortality, with a ROC of 0.84 (95% C.I. 0.78–0.9). Age, together with vital signs (oxygen saturation and the quick SOFA) and lab parameters (creatinine, AST, lymphocytes, platelets, and hemoglobin), were found to be the strongest predictors of in-hospital mortality. The present work provides insights for the prediction of in-hospital mortality of COVID-19 patients using a machine-learning algorithm.

COVID Mortality Prediction with Machine Learning Methods: A Systematic Review and Critical Appraisal

“…A total of 19/24 studies adopted binary features [20][21][22][24][25][26][27][30][31][32][33][34][35][36][37][38][40][41][42][43]]. 1/24 study dichotomized continuous feature's value in a binary form [28].…”

“…A total of 6/24 papers [20,23,29,34,42,43] used a Support vector machine (SVM) for mortality prediction, a nonlinear statistical data supervised ML tool that achieved high performance in survival prediction tasks [3,47]. Subudhi et al used Support Vector Classifier (SVC), a linear supervised ML algorithm [40].…”

Predicting Hemodynamic Failure Development in PICU Using Machine Learning Techniques

“…For example, the gradient boosting (GB) model showed the highest ROC (0.79 (0.77–0.80)) for the 30-day mortality prediction in mechanically ventilated patients, followed by the random forest model (0.78 (0.76–0.80)). Other studies conducted to predict the ICU mortality outcome in COVID−19 patients confirmed that the random forest model, followed by the GB predictive tool, outperformed the other MLTs [ 37 ]. Furthermore, the XGB model performs better, in comparison with the other MLTs, in predicting the adverse outcome of critically ill influenza patients admitted to the ICU [ 38 ].…”

Machine Learning to Predict In-Hospital Mortality in COVID-19 Patients Using Computed Tomography-Derived Pulmonary and Vascular Features

“…The CT data of 674 patients from six hospitals in northern Italy were used to extract pulmonary parenchymal and vascular features. While machine learning models centered on clinical and imaging data have been proposed to aid both COVID-19 diagnosis and severity stratification [55][56][57][58][59], the inclusion of vascular features stems from an ever-larger corpus of observations that link vascular (particularly endothelial) impairment in COVID-19 [4][5][6][7][8][9] to pulmonary thromboembolism [11][12][13][16][17][18][19][20]23] and gross damage to pulmonary arterial vessels [25][26][27].…”