多个人工智能（AI）系统已被批准通过超声表征对甲状腺结节进行风险分层。我们试图验证这样一个人工智能系统 Koios DS（Koios Medical，芝加哥，伊利诺伊州）的能力，以帮助改善不确定甲状腺结节的风险分层。回顾性单机构数据集由 28 个细胞学不确定的甲状腺结节编制而成。分子检测和手术切除，手术病理学分为恶性或良性。使用 Koios DS 回顾性评估结节。选择结节后，记录自动化和 AI 适配器衍生的甲状腺成像报告和数据系统 (TI-RADS) 水平，并使用 Cohen κ 统计评估与放射科医生衍生水平的一致性。比较了放射科医生和人工智能适配器之间的恶性肿瘤分类性能。使用 AI 适配器重新评估活检阈值。在该队列中，7 个（25%）结节在手术病理学上为恶性。结节大小中位数为 2.4 厘米（四分位数范围：1.8-2.9 厘米）。放射科医生和自动 TI-RADS 水平的中位数均为 4，κ 0.25（“公平一致”）。放射科医生对恶性肿瘤的分类提供了敏感性 100%、特异性 33.3%、阳性预测值 (PPV) 33.3% 和阴性预测值 (NPV) 100%，而 AI 适配器的敏感性为 85.7%，特异性为 76.2%，PPV 54.5%，净现值 94.1%。使用 AI 适配器，28 例活检中的 14 例将被推迟，其中 13 例手术良性。对于不确定的甲状腺结节，Koios 自动检测和放射科医生得出的 TI-RADS 水平一致。使用 AI 适配器进行的恶性肿瘤重新分类可以以最小的 NPV 成本改进 PPV。通过添加 AI 适配器进行风险分层可以实现更准确的患者咨询，并避免在细胞学上不确定的特定病例中进行活检。版权所有 © 2024 Elsevier Inc. 保留所有权利。

Multiple artificial intelligence (AI) systems have been approved to risk-stratify thyroid nodules through sonographic characterization. We sought to validate the ability of one such AI system, Koios DS (Koios Medical, Chicago, IL), to aid in improving risk stratification of indeterminate thyroid nodules.A retrospective single-institution dataset was compiled of 28 cytologically indeterminate thyroid nodules having undergone molecular testing and surgical resection, with surgical pathology categorized as malignant or benign. Nodules were retrospectively evaluated with Koios DS. After nodule selection, automated and AI-adapter-derived Thyroid Imaging Reporting and Data System (TI-RADS) levels were recorded, and agreement with radiologist-derived levels was assessed using Cohen's κ statistic. The performance of malignancy classification was compared between the radiologist and AI-adapter. Biopsy thresholds were re-evaluated using the AI-adapter.In this cohort, 7 (25%) nodules were malignant on surgical pathology. The median nodule size was 2.4 cm (interquartile range: 1.8-2.9 cm). Median radiologist and automated TI-RADS levels were both 4, with κ 0.25 ("fair agreement"). Malignancy classification by the radiologist provided sensitivity 100%, specificity 33.3%, positive predictive value (PPV) 33.3%, and negative predictive value (NPV) 100%, compared with the AI-adapter's performance with sensitivity 85.7%, specificity 76.2%, PPV 54.5%, and NPV 94.1%. Using the AI-adapter, 14 of 28 biopsies would have been deferred, 13 of which were surgically benign.Koios automated and radiologist-derived TI-RADS levels were in consistent agreement for indeterminate thyroid nodules. Malignancy reclassification with the AI-adapter improved PPV at minimal cost to NPV. Risk stratification with the addition of the AI-adapter may allow for more accurate patient counseling and the avoidance of biopsies in select cases that would otherwise be cytologically indeterminate.Copyright © 2024 Elsevier Inc. All rights reserved.