Expert system to support the diagnosis of thyroid nodules

This paper presents the SADNT-System to Support the Diagnosis of Thyroid Nodules (TNs). TNs are common clinical problems, involving a great number of diseases with different biological behaviors, from a goiter to a cancer. The SADNT is an expert system (ES) integrated to a database, that uses production rules, certainty factors (CFs) and qualitative reasoning for the computational representation of knowledge. The SADNT integrates information referring to the patient´s clinical data (history and physical examination) and the complementary exams (ultrasound, laboratory tests, cytology and thyroid scan) aiming to support the clinician in the diagnosis of TNs. This system is composed by two ES: an ES that is based on clinical data which supplies the initial diagnosis in terms of the chance of the nodule to be malign; a second ES integrates the results of the complementary exams to the diagnostic provided by the first ES, to give a final diagnosis. The SADNT was evaluated by the expert of the domain and the results of the simulations met the expectations. The representation of the knowledge through the production rules has been appropriate for the problem presented here. A system that integrates the information of the several types of exams and procedures, avoiding that relevant information of not being appraised, is an important tool for supporting the diagnosis of TNs