External validation of an artificial intelligence solution for the detection of elbow fractures and joint effusions in children.

PURPOSE: The purpose of this study was to conduct an external validation of an artificial intelligence (AI) solution for the detection of elbow fractures and joint effusions using radiographs from a real-life cohort of children. MATERIALS AND METHODS: This single-center retrospective study was conducted on 758 radiographic sets (1637 images) obtained from consecutive emergency room visits of 712 children (mean age, 7.27 ± 3.97 [standard deviation] years; age range, 7 months and 10 days to 15 years and 10 months), referred for a trauma of the elbow. For each set, fracture and/or effusion detection by eleven senior radiologists (reference standard) and AI solution was recorded. Diagnostic performance of the AI solution was measured via four different approaches: fracture detection (presence/absence of fracture as binary variable), fracture enumeration, fracture localization and lesion detection (fracture and/or a joint effusion used as constructed binary variable). RESULTS: The sensitivity of the AI solution for each of the four approaches was >89%. Greatest sensitivity of the AI solution was obtained for lesion detection (95.0%; 95% confidence interval: 92.1-96.9). The specificity of the AI solution ranged between 63% (for lesion detection) and 77% (for fracture detection). For all four approaches, the negative predictive values were >92% and the positive predictive values ranged between 54% (for fracture enumeration and localization) and 73% (for lesion detection). Specificity was lower for plastered children for all approaches (P < 0.001). CONCLUSION: The AI solution demonstrates high performances for detecting elbow's fracture and/or joint effusion in children. However, in our context of use, 8% of the radiographic sets ruled-out by the algorithm concerned children with a genuine traumatic elbow lesion.

The Prognostic Value of Olfactory Dysfunction in Patients with COVID-19: The COVIDORA Study.

BACKGROUND: Among all studies describing COVID-19 clinical features during the first wave of the pandemic, only a few retrospective studies have assessed the correlation between olfac-tory dysfunction (OD) and the evolution of disease severity. The main aim was to assess whether OD is a predictive factor of COVID-19 severity based on the patient's medical management (outpa-tient care, standard hospital admission, and ICU admission). METHODS: A national, prospective, mul-ticenter cohort study was conducted in 20 public hospitals and a public center for COVID-19 screen-ing. During the first wave of the pandemic, from 6 April to 11 May 2020, all patients tested positive for COVID-19 confirmed by RT-PCR underwent two follow-up ENT consultations within 10 days of symptom onset. The main outcome measures were the evolution of medical management (out-patient care, standard hospital admission, and ICU admission) at diagnosis and along the clinical course of COVID-19 disease. RESULTS: Among 481 patients included, the prevalence of OD was 60.7%, and it affected mostly female patients (74.3%) under 65 years old (92.5%), with fewer comor-bidities than patients with normal olfactory function. Here, 99.3% (290/292) of patients with OD presented with non-severe COVID-19 disease. Patients reporting OD were significantly less hospi-talized than the ones managed as outpatients, in either a standard medical unit or an ICU. Conclu-sions: As regards the clinical course of COVID-19 disease, OD could predict a decreased risk of hospitalization during the first wave of the pandemic.

External validation of a commercially available deep learning algorithm for fracture detection in children.

PURPOSE: The purpose of this study was to conduct an external validation of a fracture assessment deep learning algorithm (Rayvolve®) using digital radiographs from a real-life cohort of children presenting routinely to the emergency room. MATERIALS AND METHODS: This retrospective study was conducted on 2634 radiography sets (5865 images) from 2549 children (1459 boys, 1090 girls; mean age, 8.5 ± 4.5 [SD] years; age range: 0-17 years) referred by the pediatric emergency room for trauma. For each set was recorded whether one or more fractures were found, the number of fractures, and their location found by the senior radiologists and the algorithm. Using the senior radiologist diagnosis as the standard of reference, the diagnostic performance of deep learning algorithm (Rayvolve®) was calculated via three different approaches: a detection approach (presence/absence of a fracture as a binary variable), an enumeration approach (exact number of fractures detected) and a localization approach (focusing on whether the detected fractures were correctly localized). Subgroup analyses were performed according to the presence of a cast or not, age category (0-4 vs. 5-18 years) and anatomical region. RESULTS: Regarding detection approach, the deep learning algorithm yielded 95.7% sensitivity (95% CI: 94.0-96.9), 91.2% specificity (95% CI: 89.8-92.5) and 92.6% accuracy (95% CI: 91.5-93.6). Regarding enumeration and localization approaches, the deep learning algorithm yielded 94.1% sensitivity (95% CI: 92.1-95.6), 88.8% specificity (95% CI: 87.3-90.2) and 90.4% accuracy (95% CI: 89.2-91.5) for both approaches. Regarding age-related subgroup analyses, the deep learning algorithm yielded greater sensitivity and negative predictive value in the 5-18-years age group than in the 0-4-years age group for the detection approach (P < 0.001 and P = 0.002) and for the enumeration and localization approaches (P = 0.012 and P = 0.028). The high negative predictive value was robust, persisting in all of the subgroup analyses, except for patients with casts (P = 0.001 for the detection approach and P < 0.001 for the enumeration and localization approaches). CONCLUSION: The Rayvolve® deep learning algorithm is very reliable for detecting fractures in children, especially in those older than 4 years and without cast.