RESUMEN
Pulmonary parenchymal and vascular damage are frequently reported in COVID-19 patients and can be assessed with unenhanced chest computed tomography (CT), widely used as a triaging exam. Integrating clinical data, chest CT features, and CT-derived vascular metrics, we aimed to build a predictive model of in-hospital mortality using univariate analysis (Mann-Whitney U test) and machine learning models (support vectors machines (SVM) and multilayer perceptrons (MLP)). Patients with RT-PCR-confirmed SARS-CoV-2 infection and unenhanced chest CT performed on emergency department admission were included after retrieving their outcome (discharge or death), with an 85/15% training/test dataset split. Out of 897 patients, the 229 (26%) patients who died during hospitalization had higher median pulmonary artery diameter (29.0 mm) than patients who survived (27.0 mm, p < 0.001) and higher median ascending aortic diameter (36.6 mm versus 34.0 mm, p < 0.001). SVM and MLP best models considered the same ten input features, yielding a 0.747 (precision 0.522, recall 0.800) and 0.844 (precision 0.680, recall 0.567) area under the curve, respectively. In this model integrating clinical and radiological data, pulmonary artery diameter was the third most important predictor after age and parenchymal involvement extent, contributing to reliable in-hospital mortality prediction, highlighting the value of vascular metrics in improving patient stratification.
RESUMEN
Purpose: To determine the performance of a chest radiograph (CXR) severity scoring system combined with clinical and laboratory data in predicting the outcome of COVID-19 patients. Materials and Methods: We retrospectively enrolled 301 patients who had reverse transcriptase-polymerase chain reaction (RT-PCR) positive results for COVID-19. CXRs, clinical and laboratory data were collected. A CXR severity scoring system based on a qualitative evaluation by two expert thoracic radiologists was defined. Based on the clinical outcome, the patients were divided into two classes: moderate/mild (patients who did not die or were not intubated) and severe (patients who were intubated and/or died). ROC curve analysis was applied to identify the cut-off point maximizing the Youden index in the prediction of the outcome. Clinical and laboratory data were analyzed through Boruta and Random Forest classifiers. Results: The agreement between the two radiologist scores was substantial (kappa = 0.76). A radiological score ≥ 9 predicted a severe class: sensitivity = 0.67, specificity = 0.58, accuracy = 0.61, PPV = 0.40, NPV = 0.81, F1 score = 0.50, AUC = 0.65. Such performance was improved to sensitivity = 0.80, specificity = 0.86, accuracy = 0.84, PPV = 0.73, NPV = 0.90, F1 score = 0.76, AUC= 0.82, combining two clinical variables (oxygen saturation [SpO2]), the ratio of arterial oxygen partial pressure to fractional inspired oxygen [P/F ratio] and three laboratory test results (C-reactive protein, lymphocytes [%], hemoglobin). Conclusion: Our CXR severity score assigned by the two radiologists, who read the CXRs combined with some specific clinical data and laboratory results, has the potential role in predicting the outcome of COVID-19 patients.
RESUMEN
Between January and October of 2020, the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus has infected more than 34 million persons in a worldwide pandemic leading to over one million deaths worldwide (data from the Johns Hopkins University). Since the virus begun to spread, emergency departments were busy with COVID-19 patients for whom a quick decision regarding in- or outpatient care was required. The virus can cause characteristic abnormalities in chest radiographs (CXR), but, due to the low sensitivity of CXR, additional variables and criteria are needed to accurately predict risk. Here, we describe a computerized system primarily aimed at extracting the most relevant radiological, clinical, and laboratory variables for improving patient risk prediction, and secondarily at presenting an explainable machine learning system, which may provide simple decision criteria to be used by clinicians as a support for assessing patient risk. To achieve robust and reliable variable selection, Boruta and Random Forest (RF) are combined in a 10-fold cross-validation scheme to produce a variable importance estimate not biased by the presence of surrogates. The most important variables are then selected to train a RF classifier, whose rules may be extracted, simplified, and pruned to finally build an associative tree, particularly appealing for its simplicity. Results show that the radiological score automatically computed through a neural network is highly correlated with the score computed by radiologists, and that laboratory variables, together with the number of comorbidities, aid risk prediction. The prediction performance of our approach was compared to that that of generalized linear models and shown to be effective and robust. The proposed machine learning-based computational system can be easily deployed and used in emergency departments for rapid and accurate risk prediction in COVID-19 patients.