CT imaging of pulmonary embolism in patients with COVID-19 pneumonia: a retrospective analysis.

OBJECTIVES: To describe imaging and laboratory findings of confirmed PE diagnosed in COVID-19 patients and to evaluate the characteristics of COVID-19 patients with clinical PE suspicion. Characteristics of patients with COVID-19 and PE suspicion who required admission to the intensive care unit (ICU) were also analysed. METHODS: A retrospective study from March 18, 2020, until April 11, 2020. Inclusion criteria were patients with suspected PE and positive real-time reverse-transcription polymerase chain reaction (RT-PCR) for SARS-CoV-2. Exclusion criteria were negative or inconclusive RT-PCR and other chest CT indications. CTPA features were evaluated and severity scores, presence, and localisation of PE were reported. D-dimer and IL-6 determinations, ICU admission, and previous antithrombotic treatment were registered. RESULTS: Forty-seven PE suspicions with confirmed COVID-19 underwent CTPA. Sixteen patients were diagnosed with PE with a predominant segmental distribution. Statistically significant differences were found in the highest D-dimer determination in patients with PE and ICU admission regarding elevated IL-6 values. CONCLUSION: PE in COVID-19 patients in our series might predominantly affect segmental arteries and the right lung. Results suggest that the higher the D-dimer concentration, the greater the likelihood of PE. Both assumptions should be assessed in future studies with a larger sample size. KEY POINTS: • On CT pulmonary angiography, pulmonary embolism in COVID-19 patients seems to be predominantly distributed in segmental arteries of the right lung, an assumption that needs to be approached in future research. • Only the highest intraindividual determination of d-dimer from admission to CT scan seems to differentiate patients with pulmonary embolism from patients with a negative CTPA. However, interindividual variability calls for future studies to establish cut-off values in COVID-19 patients. • Further studies with larger sample sizes are needed to determine whether the presence of PE could increase the risk of intensive care unit (ICU) admission in COVID-19 patients.

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

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.