TY - JOUR T1 - Comparative analysis of the detecting nodule or mass in the lungs on the chest X-ray by the doctor and the automatic digital X-ray analysis program> JF - European Respiratory Journal JO - Eur Respir J DO - 10.1183/13993003.congress-2021.PA1863 VL - 58 IS - suppl 65 SP - PA1863 AU - Uliana Smolnikova AU - Pavel Gavrilov Y1 - 2021/09/05 UR - http://erj.ersjournals.com/content/58/suppl_65/PA1863.abstract N2 - Objectives: Efficiency mark of using automated lung disease detection system for the analysis of digital X-ray with nodule or mass in the lungs in comparison with similar statistical indicators of radiologistsMethods: Research based on the recognition and analysis of digital X-ray through one of the publicly available automatic digital X-ray analysis program and online-testing of 516 radiologists. We used PA digital chest X-ray of 100 people whose health status was confirmed by histological and CT data, the ratio of norm:pathology-94:6% (6 patients with nodule or mass). During testing, it was necessary to classify the images into 2 categories:norm/pathologyResults: The tendency to increase underdiagnosis with an increase in work experience correlates with a gradual decrease in sensitivity and negative predictive value. Whereas the overdiagnosis, on the contrary, decreases with an increase in work experience, which is also reflected in the growth of specificity and positive predictive value. The diagnostic efficiency of the system is similar to the statistical indicators of radiologists.Conclusions: Results indicate the possibility of using the automatic digital X-ray analysis program as an auxiliary “second reading” and need further improvement as a potentially effective way to identify nodule and mass in the lungs Doctor, work experience 0-5yr.Doctor, work experience 5-10yr.Doctor, work experience<10yr.SystemSensitivity,%65,457,755,866,7Specificity,%80,682,784,191,5Positive predictive value,%17,717,518,333,3Negative predictive value,%97,396,896,797,7Underdiagnosis,%33,942,344,233,3Overdiagnosis,%2017,315,98,5FootnotesCite this article as: European Respiratory Journal 2021; 58: Suppl. 65, PA1863.This abstract was presented at the 2021 ERS International Congress, in session “Prediction of exacerbations in patients with COPD”.This is an ERS International Congress abstract. No full-text version is available. Further material to accompany this abstract may be available at www.ers-education.org (ERS member access only). ER -