Decision Support System for the Diagnosis of Thyroid Cancer

A retrospective study of the results of the examination of 220 patients who underwent fine-needle aspiration biopsy of thyroid nodules has been conducted. Possibilities of using the TI-RADS (Thyroid Imaging Reporting and Data System) scale as a standardized ultrasonographic thyroid examination protocol have been considered. A new approach for determining the relationship between the results of ultrasonographic examination and cytological examination of the thyroid nodules based on computer simulations has been proposed. Using the approaches of the global optimization criterion, neural networks and TI-RADS systems, a diagram of the thyroid cancer diagnosing process in BPWin Process Modeller has been created. We have also developed a methodology for estimating the uncertainty of experimental studies. Based on the research results, a structural scheme of the decision support system was developed to model the procedure for the diagnosis of thyroid cancer and the principles of functioning of the corresponding information processing technology, taking into account quality criteria, risk theory and artificial neural network techniques.