Evaluation of Diagnostic Accuracy of the System for Pulmonary Tuberculosis Screening Based on Artificial Neural Networks

The objective of the study: to evaluate the applicability of the automated system for detection of chest diseases during a regular mass screening of the population through assessment of universe parameters of diagnostic accuracy. Subjects and methods. A retrospective diagnostic study was conducted. The inde x-t est (the method being studied) implied distinction and analysis of X-r ay films using the software based on convolutional neural networks of U- N ET type, which were modified and trained for specific purposes. The reference method used was the double revision of the previously classified X-r ay films by two qualified roentgenologists with work experience of 8-1 0 years. Two depersonalized samplings of digital X-r ay films were used: Sample 1 ( n = 140), the ratio of the norm and pathology made 50 : 50; Sample 2 ( n = 150), the ratio of the norm and pathology made 95 : 5. Results. The following parameters were set up for Samples 1 and 2 respectively: sensitivity ‒ 87.2 and 75.0%, specificity ‒ 60.0 and 53.5%, the prognostic value of the positive result ‒ 68.6 and 8.3%, the prognostic value of the negative result ‒ 82.4 and 97.5%, the area under characteristic curve ‒ 0.74 and 0.64. Conclusions. The index test can be used only for mass regular screening in the population with low pr e-t est chances of pathology, which is confirmed by the prognostic value of the negative result (97.5%). This technology was recommended for the semiautomatic formation of pulmonary tuberculosis risk groups for consequent verification of the results by a roentgenologist.