Mortality Prediction of COVID-19 Patients Using Radiomic and Neural Network Features Extracted from a Wide Chest X-ray Sample Size: A Robust Approach for Different Medical Imbalanced Scenarios

Applied Sciences

Stefania Croci¹  Gastone Castellani²  Laura Verzellesi³  Daniel Remondini³  Valeria Trojani⁴  Carlo Di Castelnuovo⁴  Marco Bertolini⁴  Greta Meglioli⁴  Davide Giosuè Lippolis⁴  Andrea Nitrosi⁴  Roberto Sghedoni⁴  Mauro Iori⁴  Andrea Botti⁴  Giulia Besutti⁵  Filippo Monelli⁵  Carlo Salvarani⁶ 

[1] Clinical Immunology, Allergy and Advanced Biotechnologies Unit, Azienda USL-IRCCS di Reggio Emilia, 42123 Reggio Emilia, Italy;Department of Experimental, Diagnostic and Specialty Medicine–DIMES, 40126 Bologna, Italy;Department of Physics and Astronomy-DIFA, University of Bologna, 40126 Bologna, Italy;Medical Physics Unit, Azienda USL-IRCCS di Reggio Emilia, 42123 Reggio Emilia, Italy;Radiology Unit, Azienda USL-IRCCS di Reggio Emilia, 42123 Reggio Emilia, Italy;Rheumatology Unit, Azienda USL-IRCCS di Reggio Emilia, 42123 Reggio Emilia, Italy;

关键词: machine learning;    radiomics;    COVID-19;    X-ray radiography;    under-sampling;   

DOI  :  10.3390/app12083903

来源: DOAJ

【 摘 要 】

Aim: The aim of this study was to develop robust prognostic models for mortality prediction of COVID-19 patients, applicable to different sets of real scenarios, using radiomic and neural network features extracted from chest X-rays (CXRs) with a certified and commercially available software. Methods: 1816 patients from 5 different hospitals in the Province of Reggio Emilia were included in the study. Overall, 201 radiomic features and 16 neural network features were extracted from each COVID-19 patient’s radiography. The initial dataset was balanced to train the classifiers with the same number of dead and survived patients, randomly selected. The pipeline had three main parts: balancing procedure; three-step feature selection; and mortality prediction with radiomic features through three machine learning (ML) classification models: AdaBoost (ADA), Quadratic Discriminant Analysis (QDA) and Random Forest (RF). Five evaluation metrics were computed on the test samples. The performance for death prediction was validated on both a balanced dataset (Case 1) and an imbalanced dataset (Case 2). Results: accuracy (ACC), area under the ROC-curve (AUC) and sensitivity (SENS) for the best classifier were, respectively, 0.72 ± 0.01, 0.82 ± 0.02 and 0.84 ± 0.04 for Case 1 and 0.70 ± 0.04, 0.79 ± 0.03 and 0.76 ± 0.06 for Case 2. These results show that the prediction of COVID-19 mortality is robust in a different set of scenarios. Conclusions: Our large and varied dataset made it possible to train ML algorithms to predict COVID-19 mortality using radiomic and neural network features of CXRs.

【 授权许可】

Unknown