Added value of an artificial intelligence solution for fracture detection in the radiologist's daily trauma emergencies workflow - 29/11/22
Bienvenido a EM-consulte, la referencia de los profesionales de la salud.
Artículo gratuito.
Conéctese para beneficiarse!
Highlights |
• | Artificial intelligence significantly increases the detection rate of fractures by radiologists in daily trauma emergencies, whatever their level of experience. |
• | Artificial intelligence allows a mean reading saving time of 10 to 16 s per examination. |
• | Artificial intelligence is not yet able to describe the full spectrum of abnormalities described by radiologists, which are present in 46% of patients. |
Abstract |
Purpose |
The main objective of this study was to compare radiologists' performance without and with artificial intelligence (AI) assistance for the detection of bone fractures from trauma emergencies.
Materials and methods |
Five hundred consecutive patients (232 women, 268 men) with a mean age of 37 ± 28 (SD) years (age range: 0.25–99 years) were retrospectively included. Three radiologists independently interpreted radiographs without then with AI assistance after a 1-month minimum washout period. The ground truth was determined by consensus reading between musculoskeletal radiologists and AI results. Patient-wise sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) for fracture detection and reading time were compared between unassisted and AI-assisted readings of radiologists. Their performances were also assessed by receiver operating characteristic (ROC) curves.
Results |
AI improved the patient-wise sensitivity of radiologists for fracture detection by 20% (95% confidence interval [CI]: 14–26), P< 0.001) and their specificity by 0.6% (95% CI: -0.9–1.5; P = 0.47). It increased the PPV by 2.9% (95% CI: 0.4–5.4; P = 0.08) and the NPV by 10% (95% CI: 6.8–13.3; P < 0.001). Thanks to AI, the area under the ROC curve for fracture detection of readers increased respectively by 10.6%, 10.2% and 9.9%. Their mean reading time per patient decreased by respectively 10, 16 and 12 s (P < 0.001).
Conclusions |
AI-assisted radiologists work better and faster compared to unassisted radiologists. AI is of great aid to radiologists in daily trauma emergencies, and could reduce the cost of missed fractures.
El texto completo de este artículo está disponible en PDF.Keywords : Artificial intelligence, Bone fracture, Emergency radiology, Musculoskeletal, Radiography
Abbreviations : AI, AUROC, CE, CI, CT, FDA, PPV, NPV, ROC, SD
Esquema
Vol 103 - N° 12
P. 594-600 - décembre 2022 Regresar al número
Artículo precedente
- Combination of clinical and spectral-CT parameters for predicting lymphovascular and perineural invasion in gastric cancer
- Tiezhu Ren, Wenjuan Zhang, Shenglin Li, Liangna Deng, Caiqiang Xue, Zhengxiao Li, Suwei Liu, Jiachen Sun, Junlin Zhou
- Efficacy and safety of prostate artery embolization for patients with lower urinary tract symptoms and indwelling urinary catheter: A retrospective multicenter study
- Julien Frandon, Asmaa Belaouni, Olivier Pellerin, Nicolas Thiounn, Chris Serrand, Stéphane Droupy, François Petitpierre, Hélène Vernhet-Kovacsik, Thibaut Murez, Vincent Vidal, Julien Ghelfi, Gaele Pagnoux, Ricardo Codas, Hélène de Forges, Jean-Paul Beregi, Marc Sapoval
Bienvenido a EM-consulte, la referencia de los profesionales de la salud.