Enhancing Physicians’ Radiology Diagnostics of COVID 19's Effects on Lung Health by Leveraging Artificial Intelligence

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. 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). 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. 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%.Funding Information: This work was partially supported by grants from the MECENAZGO, the Programa de Actividades de I+D de la Comunidad de Madrid en Biomedicina (B2017/BMD-3804), Madrid, Spain and co-financed by the European Development Regional Fund “A way to achieve Europe” (ERDF) B2020/MITICADCM funded as part of the Union response to the pandemic of COVID-19 (REACT-UE).Declaration of Interests: The authors declare themselves free of competing interests.Ethics Approval Statement: This study was conducted according to basic principles of ethics (autonomy, harmless, benefit, and distributive justice). The protocol was in line with the standards of Good Clinical Practice and the principles of the last Declaration of Helsinki (2013) and the Oviedo Convention (1997). Ethics committee approval was obtained from the University Hospital Príncipe de Asturias (HUPA-04062020).