Background: Artificial intelligence algorithms could be used to risk-stratify thyroid nodules and may reduce the subjectivity of ultrasonography. One such algorithm is AIBx which has shown good performance. However, external validation is crucial prior to clinical implementation. Materials and methods: Patients harboring thyroid nodules 1–4 cm in size, undergoing thyroid surgery from 2014 to 2016 in a single institution, were included. A histological diagnosis was obtained in all cases. Medullary thyroid cancer, metastasis from other cancers, thyroid lymphomas, and purely cystic nodules were excl uded. Retrospectively, transverse ultrasound images of the nodules were analyzed by AI Bx, and the results were compared with histopathology and Thyroid Imaging Reporting and Data System (TIRADS), calculated by experienced physicians. Results: Out of 329 patients, 257 nodules from 209 individuals met the eligibility criteria. Fifty-one nodules (20%) were malignant. AIBx had a negative pre dictive value (NPV) of 89.2%. Sensitivity, specificity, and positive predictive values (PPV) were 78.4, 44.2, and 25.8%, respectively. Considering both TIRADS 4 and TIRADS 5 nod ules as malignant lesions resulted in an NPV of 93.0%, while PPV and specificity w ere only 22.4 and 19.4%, respectively. By combining AIBx with TIRADS, no malignant nodul es were overlooked. Conclusion: When applied to ultrasound images obtained in a different setti ng than used for training, AIBx had comparable NPVs to TIRADS. AIBx per formed even better when combined with TIRADS, thus reducing false negative assessm ents. These data support the concept of AIBx for thyroid nodules, and this tool may help less experienced operators by reducing the subjectivity inherent to thyroid ultr asound interpretation.
Full Text Finder