Swan Kristine Z, Thomas Johnson, Nielsen Viveque E, Jespersen Marie Louise, Bonnema Steen J
Department of ORL, Head- and Neck Surgery, Aarhus University Hospital, Aarhus, Denmark.
Department of Endocrinology, Mercy Hospital, Springfield, Missouri, USA.
Eur Thyroid J. 2022 Mar 8;11(2):e210129. doi: 10.1530/ETJ-21-0129.
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.
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 excluded. Retrospectively, transverse ultrasound images of the nodules were analyzed by AIBx, and the results were compared with histopathology and Thyroid Imaging Reporting and Data System (TIRADS), calculated by experienced physicians.
Out of 329 patients, 257 nodules from 209 individuals met the eligibility criteria. Fifty-one nodules (20%) were malignant. AIBx had a negative predictive 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 nodules as malignant lesions resulted in an NPV of 93.0%, while PPV and specificity were only 22.4 and 19.4%, respectively. By combining AIBx with TIRADS, no malignant nodules were overlooked.
When applied to ultrasound images obtained in a different setting than used for training, AIBx had comparable NPVs to TIRADS. AIBx performed even better when combined with TIRADS, thus reducing false negative assessments. 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 ultrasound interpretation.
人工智能算法可用于对甲状腺结节进行风险分层，并可能降低超声检查的主观性。一种这样的算法是AIBx，它已显示出良好的性能。然而，在临床应用之前进行外部验证至关重要。
纳入2014年至2016年在单一机构接受甲状腺手术、甲状腺结节大小为1 - 4厘米的患者。所有病例均获得组织学诊断。排除甲状腺髓样癌、其他癌症转移、甲状腺淋巴瘤和纯囊性结节。回顾性地，由AIBx分析结节的横向超声图像，并将结果与组织病理学以及由经验丰富的医生计算的甲状腺影像报告和数据系统（TIRADS）进行比较。
在329例患者中，来自209名个体的257个结节符合纳入标准。51个结节（20%）为恶性。AIBx的阴性预测值（NPV）为89.2%。敏感性、特异性和阳性预测值（PPV）分别为78.4%、44.2%和25.8%。将TIRADS 4类和TIRADS 5类结节均视为恶性病变时，NPV为93.0%，而PPV和特异性分别仅为22.4%和19.4%。通过将AIBx与TIRADS相结合，没有遗漏恶性结节。
当应用于与训练所用不同的超声图像时，AIBx的NPV与TIRADS相当。AIBx与TIRADS联合使用时表现更佳，从而减少假阴性评估。这些数据支持将AIBx用于甲状腺结节的概念，并且该工具可能通过降低甲状腺超声解读中固有的主观性来帮助经验较少的操作人员。
