Search

Interpreting radiographs in emergency settings is stressful and a burden for radiologists. The main objective was to assess the performance of three commercially available artificial intelligence (AI) algorithms for detecting acute peripheral fractures on radiographs in daily emergency practice. Radiographs were collected from consecutive patients admitted for skeletal trauma at our emergency department over a period of 2 months. Three AI algorithms—SmartUrgence, Rayvolve, and BoneView—were used to analyze 13 body regions. Four musculoskeletal radiologists determined the ground truth from radiographs. The diagnostic performance of the three AI algorithms was calculated at the level of the radiography set. Accuracies, sensitivities, and specificities for each algorithm and two-by-two comparisons between algorithms were obtained. Analyses were performed for the whole population and for subgroups of interest (sex, age, body region). A total of 1210 patients were included (mean age 41.3 ± 18.5 years; 742 [61.3%] men), corresponding to 1500 radiography sets. The fracture prevalence among the radiography sets was 23.7% (356/1500). Accuracy was 90.1%, 71.0%, and 88.8% for SmartUrgence, Rayvolve, and BoneView, respectively; sensitivity 90.2%, 92.6%, and 91.3%, with specificity 92.5%, 70.4%, and 90.5%. Accuracy and specificity were significantly higher for SmartUrgence and BoneView than Rayvolve for the whole population (P <.0001) and for subgroups. The three algorithms did not differ in sensitivity (P =.27). For SmartUrgence, subgroups did not significantly differ in accuracy, specificity, or sensitivity. For Rayvolve, accuracy and specificity were significantly higher with age 27-36 than ≥53 years (P =.0029 and P =.0019). Specificity was higher for the subgroup knee than foot (P =.0149). For BoneView, accuracy was significantly higher for the subgroups knee than foot (P =.0006) and knee than wrist/hand (P =.0228). Specificity was significantly higher for the subgroups knee than foot (P =.0003) and ankle than foot (P =.0195). The performance of AI detection of acute peripheral fractures in daily radiological practice in an emergency department was good to high and was related to the AI algorithm, patient age, and body region examined. [ABSTRACT FROM AUTHOR]

L'infection ostéoarticulaire est une infection sévère, tout particulièrement lorsqu'elle intéresse le rachis. Elle est protéiforme : spondylodiscite, spondylite, arthrites zygapophysaires et abcès épiduraux. Elle justifie toujours une prise en charge diagnostique et thérapeutique rapide, parfois urgente. Elle touche avec prédilection le sujet de plus de 70 ans. Un terrain fragilisé, une mauvaise tolérance clinique générale, la présence de signes neurologiques, la localisation au rachis cervical sont des facteurs de gravité. L'imagerie a pour objectifs de faire le diagnostic positif de l'infection du rachis, de préciser l'extension discale, vertébrale, paraspinale et épidurale, d'évaluer les répercussions méningées et radiculo-médullaires et d'aider à l'isolement de l'agent pathogène grâce à une biopsie percutanée. Les agents pathogènes les plus fréquents sont le staphylocoque doré, les streptocoques, les mycobactéries du groupe tuberculosis. Musculoskeletal infection is a severe infection, especially when it involves the spine. It is multifaceted: spondylodiscitis, spondylitis, arthritis, and epidural abscesses. It always necessitates fast diagnostic and therapeutic interventions. It affects elderly subjects. A poor clinical status, a poor clinical tolerance, the presence of neurological signs, and location of the disease at the cervical spine, are factors of severity. Imaging aims at making a positive diagnosis of infection, at depicting extension of the disease, and help to isolate the pathogen. The most common pathogens remain Staphylococcus aureus, Streptococci, Mycobacterium tuberculosis. [ABSTRACT FROM AUTHOR]