Zheng Yuxin, Zhang Yajiao, Lu Kefeng, Wang Jiafeng, Li Linlin, Xu Dong, Liu Junping, Lou Jiangyan
Second Clinical College, Zhejiang University of Traditional Chinese Medicine, Hangzhou, China.
Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou, China.
Quant Imaging Med Surg. 2024 Sep 1;14(9):6311-6324. doi: 10.21037/qims-24-601. Epub 2024 Aug 20.
Follicular thyroid carcinoma (FTC) and follicular thyroid adenoma (FTA) present diagnostic challenges due to overlapping clinical and ultrasound features. Improving the diagnosis of FTC can enhance patient prognosis and effectiveness in clinical management. This study seeks to develop a predictive model for FTC based on ultrasound features using machine learning (ML) algorithms and assess its diagnostic effectiveness.
Patients diagnosed with FTA or FTC based on surgical pathology between January 2009 and February 2023 at Zhejiang Provincial Cancer Hospital and Zhejiang Provincial People's Hospital were retrospectively included. A total of 562 patients from Zhejiang Provincial Cancer Hospital comprised the training set, and 218 patients from Zhejiang Provincial People's Hospital constituted the validation set. Subsequently, clinical parameters and ultrasound characteristics of the patients were collected. The diagnostic parameters were analyzed using the least absolute shrinkage and selection operator and multivariate logistic regression screening methods. Next, a comparative analysis was performed using seven ML models. The area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, specificity, positive predicted value (PPV), negative predicted value (NPV), precision, recall, and comprehensive evaluation index (F-score) were calculated to compare the diagnostic efficacy among the seven models and determine the optimal model. Further, the optimal model was validated, and the SHapley Additive ExPlanations (SHAP) approach was applied to explain the significance of the model variables. Finally, an individualized risk assessment was conducted.
Age, echogenicity, thyroglobulin antibody (TGAb), echotexture, composition, triiodothyronine (T3), thyroglobulin (TG), margin, thyroid-stimulating hormone (TSH), calcification, and halo thickness >2 mm were influential factors for diagnosing FTC. The XGBoost model was identified as the optimal model after a comprehensive evaluation. The AUC of this model in the validation set was 0.969 [95% confidence interval (CI), 0.946-0.992], while its precision sensitivity, specificity, and accuracy were 0.791, 0.930, 0.913 and 0.917, respectively.
XGBoost model based on ultrasound features was constructed and interpreted using the SHAP method, providing evidence for the diagnosis of FTC and guidance for the personalized treatment of patients.
滤泡性甲状腺癌（FTC）和滤泡性腺瘤（FTA）因临床及超声特征重叠，给诊断带来挑战。提高FTC的诊断水平可改善患者预后及临床管理效果。本研究旨在利用机器学习（ML）算法，基于超声特征建立FTC预测模型并评估其诊断效能。
回顾性纳入2009年1月至2023年2月期间在浙江省肿瘤医院和浙江省人民医院经手术病理确诊为FTA或FTC的患者。浙江省肿瘤医院的562例患者组成训练集，浙江省人民医院的218例患者构成验证集。随后收集患者的临床参数和超声特征。采用最小绝对收缩和选择算子及多因素逻辑回归筛选方法分析诊断参数。接下来，使用7种ML模型进行对比分析。计算受试者工作特征（ROC）曲线下面积（AUC）、准确率、灵敏度、特异度、阳性预测值（PPV）、阴性预测值（NPV）、精确率、召回率及综合评价指标（F值），以比较7种模型的诊断效能并确定最优模型。进一步对最优模型进行验证，并应用SHapley加性解释（SHAP）方法解释模型变量的重要性。最后进行个体化风险评估。
年龄、回声、甲状腺球蛋白抗体（TGAb）、回声质地、成分、三碘甲状腺原氨酸（T3）、甲状腺球蛋白（TG）、边缘、促甲状腺激素（TSH）、钙化及晕环厚度>2mm是诊断FTC的影响因素。综合评估后，XGBoost模型被确定为最优模型。该模型在验证集中的AUC为0.969[95%置信区间（CI），0.946 - 0.992]，其精确率、灵敏度、特异度及准确率分别为0.791、0.930、0.913和0.917。
构建了基于超声特征的XGBoost模型并采用SHAP方法进行解释，为FTC诊断提供依据，为患者个体化治疗提供指导。
