Article record

机器学习辅助的表面增强拉曼光谱技术用于干燥人血清分析以快速诊断甲状腺乳头状癌及中央区淋巴结转移

Machine learning-assisted surface-enhanced Raman spectroscopy technique in dried human blood serum analysis for rapid diagnosis of papillary thyroid carcinoma and central lymph node metastasis.

AI/ML咽喉科IF 3Q2

文献信息

PMID	42910436
原文	在 PubMed 查看原文 ↗
发表日期	2026
作者	Wenwen Zhang 查看其他 10 位作者 Jiazheng Liu；Jiawei Tang；Ziyi Zhou；Jingyi Mou；Luan Luan；Yunyun Xie；Yongxuan Hong；Jie Chen；Liang Wang；Zhao Liu
作者单位	Department of Clinical Medicine, School of the 1st Clinical Medicine, Xuzhou Medical University, Xuzhou, Jiangsu Province, China. xylzhao9999@163.com. 查看其他 8 条单位信息 Department of Thyroid and Breast Surgery, Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu Province, China.；Department of Thyroid and Hernia Surgery, Xuzhou Central Hospital Affiliated to Southeast University, Xuzhou, Jiangsu province, China.；Marshall Centre for Interventions in Infectious Disease, University of Western Australia, Perth, Western Australia, Australia.；School of Medical Informatics and Engineering, Xuzhou Medical University, Xuzhou, Jiangsu, China.；Department of Breast Surgery, The First Affiliated Hospital of Nanjing Medical University, Nanjing, Jiangsu Province, China.；Medical Technology School, Xuzhou Medical University, Xuzhou, Jiangsu Province, China.；School of Medicine, South China University of Technology, Guangzhou, Guangdong Province, China.；Laboratory Medicine, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, Guangdong Province, China.
期刊	Analytical methods : advancing methods and applications
SCI 分区	Q2
IF	3
研究类型	AI/ML · 临床
所属专科	咽喉科

中文摘要

中央区淋巴结是甲状腺乳头状癌（PTC）最常见的转移部位。预防性中央区颈淋巴结清扫术具有不可忽视的风险（例如喉返神经损伤和淋巴漏），因此需要一种创伤更小的术前预测中央区淋巴结转移（CLNM）状态的方法。在本研究中，采集了150例健康对照（HC）和150例PTC患者的血清样本，其中包括75例CLNM和75例中央区淋巴结转移阴性（NCLNM）患者。使用多种机器学习（ML）模型分析表面增强拉曼光谱（SERS）光谱，以对PTC进行分类并预测CLNM。支持向量机（SVM）在HC与PTC分类中达到最高准确率（99.76%），而随机森林（RF）在CLNM与NCLNM分类中表现最佳（95.91%）。为解释这些模型，基于SHapley Additive exPlanations（SHAP）的可解释性分析识别出持续对模型预测有贡献的光谱模式。这些结果支持基于血清的、微创的PTC中央区淋巴结转移预测，并可能有助于术前风险分层。

英文摘要

Central lymph nodes are the most frequent metastatic site in papillary thyroid carcinoma (PTC). Prophylactic central neck dissection carries nontrivial risks (e.g., recurrent laryngeal nerve injury and lymphatic leakage), creating a need for less invasive preoperative prediction of central lymph node metastasis (CLNM) status. In this study, serum samples were collected from 150 healthy controls (HC) and 150 patients with PTC, including 75 CLNM and 75 central lymph node metastasis-negative (NCLNM). Surface-enhanced Raman spectroscopy (SERS) spectra were analyzed using multiple machine-learning (ML) models to classify PTC and predict CLNM. Support Vector Machine (SVM) achieved the highest accuracy for HC vs. PTC (99.76%), while Random Forest (RF) performed best for CLNM vs. NCLNM (95.91%). To interpret these models, SHapley Additive exPlanations (SHAP)-based interpretability analysis identified spectral patterns that consistently contributed to model predictions. These results support serum-based, minimally invasive prediction of central lymph node metastasis in PTC and may assist preoperative risk stratification.