OP0327 EVALUATION OF THE ARTIFICIAL INTELLIGENCE SYSTEM ACCURACY IN DETERMINING THE RADIOGRAPHIC STAGE OF KNEE OSTEOARTHRITIS

Abstract

Background: Within the last decade, rapid development of artificial neural networks and machine reading programs and their introduction into medical practice is reported [1,2,3]. Recently, an innovative program, based on the artificial intelligence (AI) technologies (a neural network and machine reading) that analyses knee X-ray images for determining the radiographic stage of OA was created. It was launched on the Osteoscan.ru website and is available for use by patients and doctors. Objectives: to validate the system ability to accurately stage OA through machine interpretation of standard knee radiographs. Methods: Initially, 1300 x-rays of both knee joints where used to teach the neural network. Of these, 350 were presented in the form of film scans, 950 in the DICOM format. The accuracy of the system in recognition of OA stage by knee radiographs was evaluated on a quality control sample of 130 cases (of all 1300). Independently, the radiographs were assessed by certified radiologists (considered the “gold standard”) and the System. Results: In 124 out of 130 cases the conclusion of a specialist and the System was the same, which represents 95.4% predictive power. Coincidence or discrepancy is a qualitative attribute, so, the accuracy of the estimation was calculated. Assuming a discrepancy of 0, and coincidence-of 1, μ = 0,954, the standard error sp = 1.8%. It can be concluded that in 95% of cases the accuracy of the system assessment will be in the range from 91.8% to 99%. Conclusion: Osteosan is a program developed on the base of AI technologies, analyzes radiographic images of the knee joints for determining OA stage. It provides high accuracy in OA stage determining by assessing knee radiographs, in 95% of cases, the accuracy of the system varies from 91.8% to 99%.