Reliability and validity of an artificial intelligence-assisted system for the detection of abnormalities in chest and bone radiographs in an emergency department
Raissa de Fátima Silva Afonso1,7, Pilar Gallardo-Rodríguez1,7, Begoña Espinosa2,7, Alejandro Bautista2, Javier Serrano2, Mónica Veguillas2, María Corell2, Raúl Garrido Chamorro2, Juan Arenas Jiménez3,7, Celia Astor Rodríguez3, Álvaro Abellón Fernández3, Álvaro Palazón Ruíz de Tremiño3, María Javiera Garfias Baladrón3, Víctor Marquina Arribas3, Pablo Chico-Sánchez1,7,8, Paula Gras Valenti1,7,8, Miguel Cabrer González4, Carlos Martínez Riera5, David Moliner Mateu5, José María Salinas Serrano6, Emilio Vivancos Rubio5,9, Bernardo Valdivieso Martínez5, Luis Concepción-Aramendia3,7,8 José Sanchez-Payá1,7 Pere Llorens2,7,8
Affiliation of the authors
1Servicio de Medicina Preventiva, Hospital General Doctor Balmis, Alicante, Spain. 2Servicio de Urgencias, Unidad de Corta Estancia y Hospitalización a Domicilio, Hospital General Doctor Balmis, Alicante, Spain. 3Servicio de Radiodiagnóstico, Hospital General Doctor Balmis, Alicante, Spain. 4Plataforma digital Idonia, Barcelona, Spain. 5Secretaría Autonómica de Planificación, Información, y Transformación Digital, Conselleria de Sanitat, Generalitat Valenciana. 6Servicio de Informática, Hospital San Juan, Alicante, Spain. 7Instituto de Investigación Sanitaria y Biomédica de Alicante, ISABIAL, Spain. 8Universidad de Alicante, Alicante, Spain. 9Valencian Research Institute for Artificial Intelligence (VRAIN), Spain.
Silva Afonso RF, Gallardo-Rodríguez P, Espinosa B, Bautista A, Serrano J, Veguillas M, et al. Reliability and validity of an artificial intelligence-assisted system for the detection of abnormalities in chest and bone radiographs in an emergency department. Emergencias. 2025;37:420-6
Summary
Introduction. To evaluate the diagnostic performance of two commercial artificial intelligence (AI) systems—ChestView for chest radiographs (CXR) and BoneView for bone radiographs (BXR)—in an emergency department (ED), and compare their validity with that of observers with different professional profiles and levels of experience: emergency physicians, radiology trainees, and expert radiologists.
Method.
We conducted a diagnostic test evaluation study on a random selection of 346 CXRs and 261 BXRs requested in the ED. Examinations were independently analysed by the AI systems and the various observers. The reference diagnosis (gold standard) was established by consensus among 3 radiologists, resorting to additional imaging tests or clinical information when necessary. Sensitivity, specificity, and positive and negative (NPV) predictive values were then calculated and compared.
Results.
For CXRs, AI (ChestView) showed overall sensitivity (64.4%) significantly higher than that of emergency physicians (49.2%; P = .018), although lower than that of the expert radiologist (83.9%; P < .001). Performance was notable for the detection of nodules/masses (sensitivity 80.0%) and pneumothorax (NPV, 99.7%), but lower for consolidations (sensitivity, 40.4%). For BXRs, AI (BoneView) achieved sensitivity for fracture detection (87.5%) higher than that of the expert radiologist (77.1%), with an NPV of 96.9%. However, its performance was lower for detecting dislocations (sensitivity 60.0%) and joint effusions (25.0%).
Conclusions.
The evaluated AI systems demonstrate clinically relevant performance in the emergency setting, significantly enhancing the diagnostic capacity of emergency physicians. Their high sensitivity for fracture detection and high NPV for pulmonary nodules, pneumothorax, and fractures establish them as a high-impact safety tool.
