The added value of using artificial intelligence in adult chest X-rays for nodules and masses detection in daily radiology practice

Abstract Background Pulmonary nodule detection in CXR is challenging. Recently, the use of artificial intelligence (AI) has been a major attraction. The current study aimed to evaluate diagnostic performance AI pulmonary nodules or masses on compared radiologist’s interpretation and assess its impact reporting process. included 150 patients who had interpreted by radiologists software. Results CT detected 99 cases (66%) while visual model analysis, as well AI, among 92 (61.3%) 93 (62%) combined visual/AI model. A total 216 were (64.4% solid 31.5% GG). Only 188 170 analysis. As per case classification showed highest area under curve (AUC) (0.890, 95% CI) (0.875, CI), respectively, followed Regarding nodules’ texture, model’s sensitivity for was 91.4% which greater than models alone, GG nodules, higher models. probability score using significantly alone ( P value = 0.001). Conclusions regarding helps more accurate decision-making increases affecting patient’s morbidity mortality.