机器学习辅助诊断系统用于意义不明确的甲状腺结节
该研究分析了5年期间因细针穿刺意义不明确的甲状腺结节(Bethesda III、IV、V类)接受手术的180例患者共194个结节,基于ACR TI-RADS的8项超声参数构建支持向量机模型,以手术病理为参考标准。测试集中模型将14个结节判为良性,其中13个正确(敏感度93.8%,特异度56.5%);Bethesda III和IV类的阴性预测值分别为93.9%和93.8%。作者认为该模型的高阴性预测值提示,对于判为良性的Bethesda III和IV类结节,或可避免手术切除。
要点
- 测试集中模型判为良性的14个结节中13个正确,敏感度93.8%、特异度56.5%。
- Bethesda III类阴性预测值93.9%,Bethesda IV类阴性预测值93.8%。
- 作者认为高阴性预测值提示Bethesda III和IV类判为良性的结节或可避免手术切除。
核心结论
- 基于超声的支持向量机模型对Bethesda III和IV类意义不明确的甲状腺结节具有较高的阴性预测值(分别为93.9%和93.8%),作者认为这提示了一条可能避免对判为良性的该类结节行手术切除的路径。
研究设计与样本
- 单中心(原文未明确说明中心数)回顾性分析5年研究期间接受手术的180例患者共194个细针穿刺意义不明确的甲状腺结节(Bethesda III、IV、V类);数据集随机分为训练集155个结节和测试集39个结节;所有结节按ACR TI-RADS手动评分组成、回声、形态、边缘和强回声灶,并记录结节大小、年龄和性别;以手术组织病理为参考标准,采用代价敏感方法构建包含上述8个参数的支持向量机模型。
诊断标准与关键数值
- 手术病理确定90个(46.4%)结节为恶性、104个(53.6%)为良性;测试集中模型将14个结节判为良性,其中13个正确(敏感度93.8%,特异度56.5%);按Bethesda分组,模型对Bethesda III类和IV类的阴性预测值分别为93.9%和93.8%。
临床应用与阅片要点
- 作者认为,该支持向量机超声模型的高阴性预测值提示了一条可能避免对判为良性的Bethesda III和IV类意义不明确结节行手术切除的路径。
局限性
- 原文为摘要,未报告研究局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
To develop an ultrasound-based machine learning classifier to diagnose benignity within indeterminate thyroid nodules (ITNs) by fine-needle aspiration, 180 patients with 194 ITNs (Bethesda classes III, IV and V) undergoing surgery over a 5-y study period were analyzed. The data set was randomly divided into training and testing data sets with 155 and 39 ITNs, respectively. All nodules were evaluated by ultrasound using the American College of Radiology Thyroid Imaging Reporting and Data System by manually scoring composition, echogenicity, shape, margin and echogenic foci. Nodule size, participant age and patient sex were recorded. A support vector machine (SVM) model with a cost-sensitive approach was developed using the aforementioned eight parameters with surgical histopathology as the reference standard. Surgical pathology determined 90 (46.4%) ITNs were malignant and 104 (53.6%) were benign. The SVM model classified 14 nodules as benign in the testing data set, of which 13 were correct (sensitivity = 93.8%, specificity = 56.5%). Considering malignancy prevalence by Bethesda group, the negative predictive values of this model for Bethesda III and IV categories were 93.9% and 93. 8%, respectively. The high negative predictive value of the SVM ultrasound-based model suggests a pathway by which surgical excision of Bethesda III and IV ITNs classified as benign may be avoided.
引用
- Chen, Chen, Li, et al. Machine Learning-Assisted Diagnostic System for Indeterminate Thyroid Nodules. Ultrasound Med Biol. 2022. PMID: 35660106. doi:10.1016/j.ultrasmedbio.2022.03.020
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。