Objective
To evaluate whether the initial chest X-ray (CXR) severity assessed by an AI system may have prognostic utility in patients with COVID-19.
Methods
This retrospective single-center study included adult patients presenting to the emergency department (ED) between February 25 and April 9, 2020, with SARS-CoV-2 infection confirmed on real-time reverse transcriptase polymerase chain reaction (RT-PCR). Initial CXRs obtained on ED presentation were evaluated by a deep learning artificial intelligence (AI) system and compared with the Radiographic Assessment of Lung Edema (RALE) score, calculated by two experienced radiologists. Death and critical COVID-19 (admission to intensive care unit (ICU) or deaths occurring before ICU admission) were identified as clinical outcomes. Independent predictors of adverse outcomes were evaluated by multivariate analyses.
Results
Six hundred ninety-seven 697 patients were included in the study: 465 males (66.7%), median age of 62 years (IQR 52–75). Multivariate analyses adjusting for demographics and comorbidities showed that an AI system-based score ≥ 30 on the initial CXR was an independent predictor both for mortality (HR 2.60 (95% CI 1.69 − 3.99; p < 0.001)) and critical COVID-19 (HR 3.40 (95% CI 2.35–4.94; p < 0.001)). Other independent predictors were RALE score, older age, male sex, coronary artery disease, COPD, and neurodegenerative disease.
Conclusion
AI- and radiologist-assessed disease severity scores on CXRs obtained on ED presentation were independent and comparable predictors of adverse outcomes in patients with COVID-19.
Trial registration
ClinicalTrials.gov NCT04318366 (https://clinicaltrials.gov/ct2/show/NCT04318366).
Key Points
• AI system–based score ≥ 30 and a RALE score ≥ 12 at CXRs performed at ED presentation are independent and comparable predictors of death and/or ICU admission in COVID-19 patients.
• Other independent predictors are older age, male sex, coronary artery disease, COPD, and neurodegenerative disease.
• The comparable performance of the AI system in relation to a radiologist-assessed score in predicting adverse outcomes may represent a game-changer in resource-constrained settings.
The nasal cavities are complex anatomical structures with high inter-individual variability that relates to different functions. Different anatomic variants may manifest at this site, mainly belonging to the nasal septum and turbinates. Precise knowledge of the anatomy and variants is fundamental for both radiologists and ENT surgeons. This article provides an overview of the main anatomic variants and their frequency, according to the existing literature, as well as ongoing research on nasal cavity segmentation in order to obtain personal 3D models and to predict post-surgical results.
BackgroundInvasive imaging techniques have been applied for lymphedema (LE) assessment; noncontrast MR lymphography (NCMLR) has potential as an alternative, but its performance is not known in secondary lower limb LE.PurposeTo assess the role of NCMRL for the classification and characterization of secondary lower limb LE.Study TypeRetrospective.PopulationFifty adults with clinically diagnosed secondary LE.Field Strength/Sequence1.5T, 3D T2‐weighted turbo spin‐echo, 3D T2‐weighted turbo spin‐echo short tau inversion recovery.AssessmentThree radiologists assessed the following characteristics on NCMRL: honeycomb pattern, dermal thickening, muscular abnormalities, distal dilated lymphatics, inguinal lymph node number, appearance of iliac lymphatic trunks. An LE grading based on the MR images was assigned. The relationship between imaging findings and clinical staging was evaluated, as well as between dermal backflow at lymphoscintigraphy and MR staging, and between the limb swelling duration and peripheral lymphatics dilatation.Statistical TestsPearson's correlation test and Cramer's V coefficient were computed to measure the strength of association. The Mann–Whitney test was used to compare the limb swelling duration between patients with and without dilated distal vessels. Agreement among raters was assessed through Kendall's W coefficient of correlation.ResultsClinical stage and the MR grading were correlated, with Cramer's V coefficient of 1 for reader 1 (P < 0.05), 0.846 for reader 2 (P < 0.05), and 0.912 (P < 0.05) for reader 3; agreement between interraters was very good (W = 0.0.75; P = 0.05). A honeycomb pattern (P < 0.05), dermal thickening (P < 0.001), muscular abnormalities (P < 0.05), iliac lymphatic trunks appearance (P < 0.05), distal dilated vessels (P < 0.05), and lymph nodes number (P < 0.05) were significantly correlated with LE clinical stage. Dermal backflow at lymphoscintigraphy was described in 10 (20%) patients and showed a significant correlation with the MR grading (P < 0.05).Data ConclusionThese preliminary results suggest that NCMRL may provide information useful for the staging and management of patients affected by secondary lower limb LE.Level of Evidence 4Technical Efficacy Stage 2J. MAGN. RESON. IMAGING 2021;53:458–466.
We observed an important overuse of head CT scans in MHI; the main promoting factor for inappropriate was injury mechanism. 2% of head CT were positive, correlating with signs of suspected skull fracture and motor vehicle accident with high energy impact.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.