MultiCOVID: a multi modal deep learning approach for COVID-19 diagnosis

• Published in: Scientific reports Vol. 13; no. 1; p. 18761
• Main Authors: Hardy-Werbin, Max, Maiques, José Maria, Busto, Marcos, Cirera, Isabel, Aguirre, Alfons, Garcia-Gisbert, Nieves, Zuccarino, Flavio, Carbullanca, Santiago, Del Carpio, Luis Alexander, Ramal, Didac, Gayete, Ángel, Martínez-Roldan, Jordi, Marquez-Colome, Albert, Bellosillo, Beatriz, Gibert, Joan
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 31.10.2023; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114; 692/53; 692/699; 692/700; Algorithms; Blood; Blood tests; Congestive heart failure; Coronaviruses; COVID-19; Deep learning; Diagnosis; Heart failure; Humanities and Social Sciences; multidisciplinary; Pneumonia; Prediction models; Science; Science (multidisciplinary); Severe acute respiratory syndrome; Severe acute respiratory syndrome coronavirus 2; Thorax
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-023-46126-8

The rapid spread of the severe acute respiratory syndrome coronavirus 2 led to a global overextension of healthcare. Both Chest X-rays (CXR) and blood test have been demonstrated to have predictive value on Coronavirus Disease 2019 (COVID-19) diagnosis on different prevalence scenarios. With the objective of improving and accelerating the diagnosis of COVID-19, a multi modal prediction algorithm (MultiCOVID) based on CXR and blood test was developed, to discriminate between COVID-19, Heart Failure and Non-COVID Pneumonia and healthy (Control) patients. This retrospective single-center study includes CXR and blood test obtained between January 2017 and May 2020. Multi modal prediction models were generated using opensource DL algorithms. Performance of the MultiCOVID algorithm was compared with interpretations from five experienced thoracic radiologists on 300 random test images using the McNemar–Bowker test. A total of 8578 samples from 6123 patients (mean age 66 ± 18 years of standard deviation, 3523 men) were evaluated across datasets. For the entire test set, the overall accuracy of MultiCOVID was 84%, with a mean AUC of 0.92 (0.89–0.94). For 300 random test images, overall accuracy of MultiCOVID was significantly higher (69.6%) compared with individual radiologists (range, 43.7–58.7%) and the consensus of all five radiologists (59.3%, P  < .001). Overall, we have developed a multimodal deep learning algorithm, MultiCOVID, that discriminates among COVID-19, heart failure, non-COVID pneumonia and healthy patients using both CXR and blood test with a significantly better performance than experienced thoracic radiologists.