Pérez Laencina M, Plasencia Martínez J M, Sánchez Canales M, Jiménez Pulido C, Rodríguez Mondéjar R, Martínez Encarnación L, García Hidalgo C, Galdo Galián D, Hernández Madrid P, Chico Caballero L, Guillén García E, Plasencia Martínez M N, Martínez Romero S, García Molina J, García Santos J M
Facultad de Medicina, Universidad de Murcia, Murcia, Spain.
Servicio de Radiodiagnóstico, Hospital Universitario Morales Meseguer, Murcia, Spain.
Radiologia (Engl Ed). 2025 May-Jun;67(3):273-286. doi: 10.1016/j.rxeng.2025.01.001. Epub 2025 Jan 24.
Our objective is to evaluate how useful an artificial intelligence (AI) tool is to chest radiograph readers with various levels of expertise for the diagnosis of COVID-19 pneumonia when the tool has been trained on a non-COVID-19 pneumonia pathology.
Data was collected for patients who had previously undergone a chest radiograph and digital tomosynthesis due to suspected COVID-19 pneumonia. The gold standard consisted of the readings of two expert radiologists who assessed the presence and distribution of COVID-19 pneumonia on the images. Six medical students, two radiology trainees, and two other expert thoracic radiologists participated as additional readers. Two radiograph readings and a third supported by the AI Thoracic Care Suite tool were performed. COVID-19 pneumonia distribution and probability were assessed along with the contribution made by AI. Agreement and diagnostic performance were analysed.
The sample consisted of 113 cases, of which 56 displayed lung opacities, 52.2% were female, and the mean age was 50.70 ± 14.9. Agreement with the gold standard differed between students, trainees, and radiologists. There was a non-significant improvement for four of the six students when AI was used. The use of AI by students did not improve the COVID-19 pneumonia diagnostic performance but it did reduce the difference in diagnostic performance with the more expert radiologists. Furthermore, it had more influence on the interpretation of mild pneumonia than severe pneumonia and normal radiograph findings. AI resolved more doubts than it generated, especially among students (31.30% vs 8.32%), followed by trainees (14.45% vs 5.7%) and radiologists (10.05% vs 6.15%).
For expert and lesser experienced radiologists, this commercial AI tool has shown no impact on chest radiograph readings of patients with suspected COVID-19 pneumonia. However, it aided the assessment of inexperienced readers and in cases of mild pneumonia.
