Featured Application The present study demonstrates that semi-automatic segmentation enables the identification of regions of interest affected by SARS-CoV-2 infection for the extraction of prognostic features from chest CT scans without suffering from the inter-operator variability typical of segmentation, hence offering a valuable and informative second opinion. Machine Learning methods allow identification of the prognostic features potentially reusable for the early detection and management of other similar diseases. (1) Background: Chest Computed Tomography (CT) has been proposed as a non-invasive method for confirming the diagnosis of SARS-CoV-2 patients using radiomic features (RFs) and baseline clinical data. The performance of Machine Learning (ML) methods using RFs derived from semi-automatically segmented lungs in chest CT images was investigated regarding the ability to predict the mortality of SARS-CoV-2 patients. (2) Methods: A total of 179 RFs extracted from 436 chest CT images of SARS-CoV-2 patients, and 8 clinical and 6 radiological variables, were used to train and evaluate three ML methods (Least Absolute Shrinkage and Selection Operator [LASSO] regularized regression, Random Forest Classifier [RFC], and the Fully connected Neural Network [FcNN]) for their ability to predict mortality using the Area Under the Curve (AUC) of Receiver Operator characteristic (ROC) Curves. These three groups of variables were used separately and together as input for constructing and comparing the final performance of ML models. (3) Results: All the ML models using only RFs achieved an informative level regarding predictive ability, outperforming radiological assessment, without however reaching the performance obtained with ML based on clinical variables. The LASSO regularized regression and the FcNN performed equally, both being superior to the RFC. (4) Conclusions: Radiomic features based on semi-automatically segmented CT images and ML approaches can aid in identifying patients with a high risk of mortality, allowing a fast, objective, and generalizable method for improving prognostic assessment by providing a second expert opinion that outperforms human evaluation.

Lorenzo Spagnoli, Maria Francesca Morrone, Enrico Giampieri, Giulia Paolani, Miriam Santoro, Nico Curti, et al. (2022). Outcome Prediction for SARS-CoV-2 Patients Using Machine Learning Modeling of Clinical, Radiological, and Radiomic Features Derived from Chest CT Images. APPLIED SCIENCES, 12(9), 1-14 [10.3390/app12094493].

Outcome Prediction for SARS-CoV-2 Patients Using Machine Learning Modeling of Clinical, Radiological, and Radiomic Features Derived from Chest CT Images

Lorenzo Spagnoli;Enrico Giampieri;Giulia Paolani;Miriam Santoro;Nico Curti;Federica Ciccarese;Giulio Vara;Rita Golfieri;Michele Bartoletti;Pierluigi Viale;
2022

Abstract

Featured Application The present study demonstrates that semi-automatic segmentation enables the identification of regions of interest affected by SARS-CoV-2 infection for the extraction of prognostic features from chest CT scans without suffering from the inter-operator variability typical of segmentation, hence offering a valuable and informative second opinion. Machine Learning methods allow identification of the prognostic features potentially reusable for the early detection and management of other similar diseases. (1) Background: Chest Computed Tomography (CT) has been proposed as a non-invasive method for confirming the diagnosis of SARS-CoV-2 patients using radiomic features (RFs) and baseline clinical data. The performance of Machine Learning (ML) methods using RFs derived from semi-automatically segmented lungs in chest CT images was investigated regarding the ability to predict the mortality of SARS-CoV-2 patients. (2) Methods: A total of 179 RFs extracted from 436 chest CT images of SARS-CoV-2 patients, and 8 clinical and 6 radiological variables, were used to train and evaluate three ML methods (Least Absolute Shrinkage and Selection Operator [LASSO] regularized regression, Random Forest Classifier [RFC], and the Fully connected Neural Network [FcNN]) for their ability to predict mortality using the Area Under the Curve (AUC) of Receiver Operator characteristic (ROC) Curves. These three groups of variables were used separately and together as input for constructing and comparing the final performance of ML models. (3) Results: All the ML models using only RFs achieved an informative level regarding predictive ability, outperforming radiological assessment, without however reaching the performance obtained with ML based on clinical variables. The LASSO regularized regression and the FcNN performed equally, both being superior to the RFC. (4) Conclusions: Radiomic features based on semi-automatically segmented CT images and ML approaches can aid in identifying patients with a high risk of mortality, allowing a fast, objective, and generalizable method for improving prognostic assessment by providing a second expert opinion that outperforms human evaluation.
2022
Lorenzo Spagnoli, Maria Francesca Morrone, Enrico Giampieri, Giulia Paolani, Miriam Santoro, Nico Curti, et al. (2022). Outcome Prediction for SARS-CoV-2 Patients Using Machine Learning Modeling of Clinical, Radiological, and Radiomic Features Derived from Chest CT Images. APPLIED SCIENCES, 12(9), 1-14 [10.3390/app12094493].
Lorenzo Spagnoli; Maria Francesca Morrone; Enrico Giampieri; Giulia Paolani; Miriam Santoro; Nico Curti; Francesca Coppola; Federica Ciccarese; Giulio...espandi
File in questo prodotto:
File Dimensione Formato  
applsci-12-04493-v2.pdf

accesso aperto

Tipo: Versione (PDF) editoriale
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 2.29 MB
Formato Adobe PDF
2.29 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/906800
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 7
social impact