Abstract
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.
Highlights
IntroductionBedside ultrasound examinations performed during hospitalization have hinted the prognostic value of indirect signs of impaired pulmonary circulation, such as right ventricular longitudinal strain and increased end-diastolic chamber size [29,30]
Best multilayer perceptrons (MLP) is depicted in panel b of Figure 4. In this retrospective multicenter study, we developed a predictive model of inhospital mortality for COVID-19 patients, using clinical and radiological data acquired on
In this retrospective multicenter study, we developed a predictive model of in-hospital mortality for COVID-19 patients, using clinical and radiological data acquired on emergency department admission
Summary
Bedside ultrasound examinations performed during hospitalization have hinted the prognostic value of indirect signs of impaired pulmonary circulation, such as right ventricular longitudinal strain and increased end-diastolic chamber size [29,30]. These parameters are encumbered by operator dependency and potential overlap with other pre-existing causes of right ventricular dysfunction [31]; the routine performance of echocardiography in the triage of COVID-19 patients during pandemic peaks could prove challenging, due to the high volume of patients referred to emergency departments. Rather than identifying thrombotic phenomena as a byproduct of pulmonary embolism, ever-increasing evidence points to a direct origin of thrombosis in arterial lung vasculature [14,32,33], highlighting the need for a more accurate characterization of these phenomena in their true location [34]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have