AUTHOR=Gasulla Óscar , Ledesma-Carbayo Maria J. , Borrell Luisa N. , Fortuny-Profitós Jordi , Mazaira-Font Ferran A. , Barbero Allende Jose María , Alonso-Menchén David , García-Bennett Josep , Del Río-Carrrero Belen , Jofré-Grimaldo Hector , Seguí Aleix , Monserrat Jorge , Teixidó-Román Miguel , Torrent Adrià , Ortega Miguel Ángel , Álvarez-Mon Melchor , Asúnsolo Angel 

TITLE=Enhancing physicians’ radiology diagnostics of COVID-19’s effects on lung health by leveraging artificial intelligence

JOURNAL=Frontiers in Bioengineering and Biotechnology

VOLUME=11

YEAR=2023

URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2023.1010679

DOI=10.3389/fbioe.2023.1010679

ISSN=2296-4185

ABSTRACT=<p><bold>Introduction:</bold> This study aimed to develop an individualized artificial intelligence model to help radiologists assess the severity of COVID-19’s effects on patients’ lung health.</p><p><bold>Methods:</bold> Data was collected from medical records of 1103 patients diagnosed with COVID-19 using RT- qPCR between March and June 2020, in Hospital Madrid-Group (HM-Group, Spain). By using Convolutional Neural Networks, we determine the effects of COVID-19 in terms of lung area, opacities, and pulmonary air density. We then combine these variables with age and sex in a regression model to assess the severity of these conditions with respect to fatality risk (death or ICU).</p><p><bold>Results:</bold> Our model can predict high effect with an AUC of 0.736. Finally, we compare the performance of the model with respect to six physicians’ diagnosis, and test for improvements on physicians’ performance when using the prediction algorithm.</p><p><bold>Discussion:</bold> We find that the algorithm outperforms physicians (39.5% less error), and thus, physicians can significantly benefit from the information provided by the algorithm by reducing error by almost 30%.</p>