Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs.

Background Chest radiography remains the most common radiologic examination, and interpretation of its results can be difficult. Purpose To explore the potential benefit of artificial intelligence (AI) assistance in the detection of thoracic abnormalities on chest radiographs by evaluating the performance of radiologists with different levels of expertise, with and without AI assistance. Materials and Methods Patients who underwent both chest radiography and thoracic CT within 72 hours between January 2010 and December 2020 in a French public hospital were screened retrospectively. Radiographs were randomly included until reaching 500 radiographs, with about 50% of radiographs having abnormal findings. A senior thoracic radiologist annotated the radiographs for five abnormalities (pneumothorax, pleural effusion, consolidation, mediastinal and hilar mass, lung nodule) based on the corresponding CT results (ground truth). A total of 12 readers (four thoracic radiologists, four general radiologists, four radiology residents) read half the radiographs without AI and half the radiographs with AI (ChestView; Gleamer). Changes in sensitivity and specificity were measured using paired t tests. Results The study included 500 patients (mean age, 54 years ± 19 [SD]; 261 female, 239 male), with 522 abnormalities visible on 241 radiographs. On average, for all readers, AI use resulted in an absolute increase in sensitivity of 26% (95% CI: 20, 32), 14% (95% CI: 11, 17), 12% (95% CI: 10, 14), 8.5% (95% CI: 6, 11), and 5.9% (95% CI: 4, 8) for pneumothorax, consolidation, nodule, pleural effusion, and mediastinal and hilar mass, respectively (P < .001). Specificity increased with AI assistance (3.9% [95% CI: 3.2, 4.6], 3.7% [95% CI: 3, 4.4], 2.9% [95% CI: 2.3, 3.5], and 2.1% [95% CI: 1.6, 2.6] for pleural effusion, mediastinal and hilar mass, consolidation, and nodule, respectively), except in the diagnosis of pneumothorax (-0.2%; 95% CI: -0.36, -0.04; P = .01). The mean reading time was 81 seconds without AI versus 56 seconds with AI (31% decrease, P < .001). Conclusion AI-assisted chest radiography interpretation resulted in absolute increases in sensitivity for all radiologists of various levels of expertise and reduced the reading times; specificity increased with AI, except in the diagnosis of pneumothorax. © RSNA, 2023 Supplemental material is available for this article.

Strategies to safely rule out pulmonary embolism in COVID-19 outpatients: a multicenter retrospective study.

OBJECTIVES: The objective was to define a safe strategy to exclude pulmonary embolism (PE) in COVID-19 outpatients, without performing CT pulmonary angiogram (CTPA). METHODS: COVID-19 outpatients from 15 university hospitals who underwent a CTPA were retrospectively evaluated. D-Dimers, variables of the revised Geneva and Wells scores, as well as laboratory findings and clinical characteristics related to COVID-19 pneumonia, were collected. CTPA reports were reviewed for the presence of PE and the extent of COVID-19 disease. PE rule-out strategies were based solely on D-Dimer tests using different thresholds, the revised Geneva and Wells scores, and a COVID-19 PE prediction model built on our dataset were compared. The area under the receiver operating characteristics curve (AUC), failure rate, and efficiency were calculated. RESULTS: In total, 1369 patients were included of whom 124 were PE positive (9.1%). Failure rate and efficiency of D-Dimer > 500 µg/l were 0.9% (95%CI, 0.2-4.8%) and 10.1% (8.5-11.9%), respectively, increasing to 1.0% (0.2-5.3%) and 16.4% (14.4-18.7%), respectively, for an age-adjusted D-Dimer level. D-dimer > 1000 µg/l led to an unacceptable failure rate to 8.1% (4.4-14.5%). The best performances of the revised Geneva and Wells scores were obtained using the age-adjusted D-Dimer level. They had the same failure rate of 1.0% (0.2-5.3%) for efficiency of 16.8% (14.7-19.1%), and 16.9% (14.8-19.2%) respectively. The developed COVID-19 PE prediction model had an AUC of 0.609 (0.594-0.623) with an efficiency of 20.5% (18.4-22.8%) when its failure was set to 0.8%. CONCLUSIONS: The strategy to safely exclude PE in COVID-19 outpatients should not differ from that used in non-COVID-19 patients. The added value of the COVID-19 PE prediction model is minor. KEY POINTS: • D-dimer level remains the most important predictor of pulmonary embolism in COVID-19 patients. • The AUCs of the revised Geneva and Wells scores using an age-adjusted D-dimer threshold were 0.587 (95%CI, 0.572 to 0.603) and 0.588 (95%CI, 0.572 to 0.603). • The AUC of COVID-19-specific strategy to rule out pulmonary embolism ranged from 0.513 (95%CI: 0.503 to 0.522) to 0.609 (95%CI: 0.594 to 0.623).

Efficacy of plasma exchange in patients with anti-MDA5 rapidly progressive interstitial lung disease.

BACKGROUND: Rapidly progressive interstitial lung disease (RP-ILD) is a frequent and severe manifestation of anti-MDA5 dermatomyositis (MDA5-DM) associated with poor outcome. The optimal treatment regimen for MDA5-DM RP-ILD is yet to be determined. Specifically, the value of adding plasma exchange (PLEX) to corticosteroids and immunosuppressants remains unclear. We aimed to evaluate the effect of PLEX on the outcome of patients with MDA5-DM RP-ILD. METHODS: This French nationwide multicentre retrospective study included all MDA5-DM RP-ILD patients from 2012 to 2021 admitted to 18 centres. The primary endpoint was one-year transplant-free survival. RESULTS: 51 patients with MDA5-DM RP-ILD (female 67%; mean age at disease onset: 51 ± 11.6 years) were included. Thirty-two (63%) patients required mechanical ventilation and twenty-five (49%) received PLEX. One-year mortality or lung transplant occurred in 63% cases after a median follow-up of 77 [38-264] days. The Cox proportional hazards multivariable model only retained mechanical ventilation but not PLEX (p = 0.7) as independent predictor of the primary endpoint. One-year transplant-free survival rates in PLEX + vs. PLEX-were 20% vs. 54% (p = 0.01), respectively. The Kaplan-Meier estimated probabilities of one-year transplant-free survival was statistically higher in PLEX-compared to PLEX + patients (p = 0.05). PLEX + compared to PLEX-patients more frequently received mechanical ventilation and immunosuppressants suggesting PLEX + patients had a more severe disease. CONCLUSION: MDA5-DM RP-ILD is associated with poor rate of one-year transplant-free survival. The use of PLEX was not associated with a better outcome albeit they were mainly given to more severe patients. While our study reports the largest series of MDA5-DM RP-ILD given PLEX, these results needs to be interpreted with caution owing the numerous selection, indication and interpretation bias. Further studies are needed to evaluate their efficacy in this setting.

Acute and Chronic Sarcoid Arthropathies: Characteristics and Treatments From a Retrospective Nationwide French Study.

Introduction: We aimed to analyze patients with acute and chronic joint involvements in sarcoidosis. Methods: This is a retrospective multicenter analysis of patients with proven sarcoidosis, as defined by clinical, radiological, and histological criteria, with at least one clinical and/or ultrasonographic synovitis. Results: Thirty-nine patients with sarcoid arthropathy were included, and among them 19 had acute sarcoidosis (Lofgren's syndrome). Joint involvement and DAS44-CRP were not significantly different in acute and chronic sarcoid arthropathies. Acute forms were more frequent than chronic sarcoid arthropathy in Caucasians, without any difference of sex or age between these 2 forms. Joint involvement was frequently more symmetrical in acute than chronic forms (100 vs. 70%; p < 0.05), with a more frequent involvement in wrists and ankles in acute forms, whereas the tender and swollen joint counts and the DAS44-CRP were similar between the 2 groups. Skin lesions were significantly more frequent in patients with acute forms [17 (89%) vs. 5 (25%); p < 0.05] and were erythema nodosum in all patients with Löfgren's syndrome and sarcoid skin lesions in those with chronic sarcoidosis. Among 20 patients with chronic sarcoidosis, treatment was used in 17 (85%) cases, and consisted in NSAIDs alone (n = 5; 25%), steroids alone (n = 5; 25%), hydroxychloroquine (n = 2; 20%), methotrexate (n = 3; 15%), and TNF inhibitors (n = 2; 10%). A complete/partial joint response was noted in 14 (70%) cases with a DAS44-CRP reduction of 2.07 [1.85-2.44] (from 3.13 [2.76-3.42] to 1.06 [0.9-1.17]; p < 0.05). Conclusion: Sarcoid arthropathies have different clinical phenotypes in acute and chronic forms and various treatment regimens such as hydroxychloroquine and methotrexate could be used in chronic forms.