Chest radiograph at admission predicts early intubation among inpatient COVID-19 patients.

OBJECTIVE: The 2019 Coronavirus (COVID-19) results in a wide range of clinical severity and there remains a need for prognostic tools which identify patients at risk of rapid deterioration and who require critical care. Chest radiography (CXR) is routinely obtained at admission of COVID-19 patients. However, little is known regarding correlates between CXR severity and time to intubation. We hypothesize that the degree of opacification on CXR at time of admission independently predicts need and time to intubation. METHODS: In this retrospective cohort study, we reviewed COVID-19 patients who were admitted to an urban medical center during March 2020 that had a CXR performed on the day of admission. CXRs were divided into 12 lung zones and were assessed by two blinded thoracic radiologists. A COVID-19 opacification rating score (CORS) was generated by assigning one point for each lung zone in which an opacity was observed. Underlying comorbidities were abstracted and assessed for association. RESULTS: One hundred forty patients were included in this study and 47 (34%) patients required intubation during the admission. Patients with CORS ≥ 6 demonstrated significantly higher rates of early intubation within 48 h of admission and during the hospital stay (ORs 24 h, 19.8, p < 0.001; 48 h, 28.1, p < 0.001; intubation during hospital stay, 6.1, p < 0.0001). There was no significant correlation between CORS ≥ 6 and age, sex, BMI, or any underlying cardiac or pulmonary comorbidities. CONCLUSIONS: CORS ≥ 6 at the time of admission predicts need for intubation, with significant increases in intubation at 24 and 48 h, independent of comorbidities. KEY POINTS: • Chest radiography at the time of admission independently predicts time to intubation within 48 h and during the hospital stay in COVID-19 patients. • More opacities on chest radiography are associated with several fold increases in early mechanical ventilation among COVID-19 patients. • Chest radiography is useful in identifying COVID-19 patients whom may rapidly deteriorate and help inform clinical management as well as hospital bed and ventilation allocation.

DeepCOVID-XR: An Artificial Intelligence Algorithm to Detect COVID-19 on Chest Radiographs Trained and Tested on a Large U.S. Clinical Data Set.

Background There are characteristic findings of coronavirus disease 2019 (COVID-19) on chest images. An artificial intelligence (AI) algorithm to detect COVID-19 on chest radiographs might be useful for triage or infection control within a hospital setting, but prior reports have been limited by small data sets, poor data quality, or both. Purpose To present DeepCOVID-XR, a deep learning AI algorithm to detect COVID-19 on chest radiographs, that was trained and tested on a large clinical data set. Materials and Methods DeepCOVID-XR is an ensemble of convolutional neural networks developed to detect COVID-19 on frontal chest radiographs, with reverse-transcription polymerase chain reaction test results as the reference standard. The algorithm was trained and validated on 14 788 images (4253 positive for COVID-19) from sites across the Northwestern Memorial Health Care System from February 2020 to April 2020 and was then tested on 2214 images (1192 positive for COVID-19) from a single hold-out institution. Performance of the algorithm was compared with interpretations from five experienced thoracic radiologists on 300 random test images using the McNemar test for sensitivity and specificity and the DeLong test for the area under the receiver operating characteristic curve (AUC). Results A total of 5853 patients (mean age, 58 years ± 19 [standard deviation]; 3101 women) were evaluated across data sets. For the entire test set, accuracy of DeepCOVID-XR was 83%, with an AUC of 0.90. For 300 random test images (134 positive for COVID-19), accuracy of DeepCOVID-XR was 82%, compared with that of individual radiologists (range, 76%-81%) and the consensus of all five radiologists (81%). DeepCOVID-XR had a significantly higher sensitivity (71%) than one radiologist (60%, P < .001) and significantly higher specificity (92%) than two radiologists (75%, P < .001; 84%, P = .009). AUC of DeepCOVID-XR was 0.88 compared with the consensus AUC of 0.85 (P = .13 for comparison). With consensus interpretation as the reference standard, the AUC of DeepCOVID-XR was 0.95 (95% CI: 0.92, 0.98). Conclusion DeepCOVID-XR, an artificial intelligence algorithm, detected coronavirus disease 2019 on chest radiographs with a performance similar to that of experienced thoracic radiologists in consensus. © RSNA, 2020 Supplemental material is available for this article. See also the editorial by van Ginneken in this issue.

Incidentally discovered COVID-19 in low-suspicion patients-a threat to front line health care workers.

PURPOSE: The COVID-19 pandemic has been responsible for thousands of deaths worldwide. Testing remains at a premium, and criteria for testing remains reserved for those with lower respiratory infection symptoms and/or a known high-risk exposure. The role of imaging in COVID-19 is rapidly evolving; however, few algorithms include imaging criteria, and it is unclear what should be done in low-suspicion patients with positive imaging findings. METHODS: From 03/01/2020-03/20/2020, a retrospective review of all patients with suspected COVID-19 on imaging was performed. Imaging was interpreted by a board-certified, fellowship-trained radiologist. Patients were excluded if COVID-19 infection was suspected at the time of presentation, was the reason for imaging, or if any lower respiratory symptoms were present. RESULTS: Eight patients with suspected COVID-19 infection on imaging were encountered. Seven patients received testing due to suspicious imaging findings with subsequent lab-confirmed COVID-19. No patients endorsed prior exposure to COVID-19 or recent international travel. COVID-19 was suggested in six patients incidentally on abdominal CT and two on chest radiography. At the time of presentation, no patients were febrile, and seven endorsed gastrointestinal symptoms. Five COVID-19 patients eventually developed respiratory symptoms and required intubation. Two patients expired during the admission. CONCLUSIONS: Patients with imaging findings suspicious for COVID-19 warrant prompt reverse transcription polymerase chain reaction (RT-PCR) testing even in low clinical suspicion cases. The prevalence of disease in the population may be underestimated by the current paradigm of RT-PCR testing with the current clinical criteria of lower respiratory symptoms and exposure risk.

Pulmonary Mucormycosis: Risk Factors, Radiologic Findings, and Pathologic Correlation.

Pulmonary mucormycosis (PM) is an uncommon fungal infection most often seen in immunocompromised patients. The fungus grows on decaying food, soil, and animal excrement. Patients usually become infected by inhalation of spores. The most common risk factors include diabetes mellitus, hematologic malignancy, and solid organ or stem cell transplant. PM can have a nonspecific appearance at imaging. For example, early imaging may show peribronchial ground-glass opacity. Later, the disease progresses to consolidation, nodules, or masses. Because patients are usually immunocompromised, the differential diagnosis often includes invasive pulmonary aspergillosis (IPA). Various radiologic findings suggestive of PM have been identified to help differentiate it from IPA. For example, the reverse halo sign is more closely associated with PM than with IPA. The reverse halo sign is an area of ground-glass opacity surrounded by a rim of consolidation. In addition, the presence of pleural effusions and more than 10 nodules is more suggestive of PM than it is of IPA. PM can progress rapidly in neutropenic patients. Identification of the hyphae in tissue by using endobronchial or percutaneous sampling can allow differentiation from IPA and help confirm the diagnosis of mucormycosis. Because of the high mortality rate associated with PM, early identification of the disease is critical for an improved likelihood of survival. A multimodality treatment approach with antifungal agents and surgical débridement has been shown to improve outcomes. The authors review the risk factors for PM, describe its imaging appearance and disease process, and describe the treatment of the disease. ©RSNA, 2020.