A protein-based classifier for differentiating follicular thyroid adenoma and carcinoma

Differentiating follicular thyroid adenoma (FTA) from carcinoma (FTC) remains challenging due to similar histological features separate from invasion. This study developed and validated DNA- and/or protein-based classifiers. A total of 2443 thyroid samples from 1568 patients were obtained from 24 centers in China and Singapore. Next-generation sequencing of a 66-gene panel revealed 41 (62.1%) detectable genes, while 25 were not, showing similar alteration patterns with differing mutation frequencies. Proteomics quantified 10,336 proteins, with 187 dysregulated. A discovery protein-based XGBoost model achieved an AUROC of 0.899 (95% CI, 0.849-0.949), outperforming the gene-based model (AUROC 0.670 [95% CI, 0.612-0.729]). A subsequent 24-protein classifier, developed via targeted mass spectrometry and validated in three independent sets, showed high performance in retrospective cohorts (AUROC 0.871 [95% CI, 0.833-0.910] and 0.853 [95% CI, 0.772-0.934]) and prospective biopsies (AUROC 0.781 [95% CI, 0.563-1.000]). It exhibited a 95.7% negative predictive value for ruling out malignancy. This study presents a promising protein-based approach for the differential diagnosis of FTA and FTC, potentially enhancing diagnostic accuracy and clinical decision-making.

Authors

Institutions

Publication Details

Journal
EMBO Molecular Medicine
Published
2025-05-29
DOI
https://doi.org/10.1038/s44321-025-00242-2
Citations
2
Primary Topic
Thyroid Cancer Diagnosis and Treatment
Type
article
Field-Weighted Citation Impact
2.59

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A protein-based classifier for differentiating follicular thyroid adenoma and carcinoma

M S Chen, Tiannan Guo, Wanyuan Chen, Minghua Ge et al.
2 citations
EMBO Molecular Medicine
Thyroid Cancer Diagnosis and Treatment
2.59
article

A protein-based classifier for differentiating follicular thyroid adenoma and carcinoma

M S Chen, Tiannan Guo, Wanyuan Chen, Minghua Ge, Huanjie Chen, Yongfu Zhao, Zhiyan Liu, N. Gopalakrishna Iyer, Yuxin Du, Qi‐Jun Wu, Yi Zhu, Yingrui Wang, Weigang Ge, Zhiqiang Gui, Haitao Zheng, Zhennan Yuan, Jing Yu, Oi Lian Kon, Bei Wei, Wei Sun, Jiafei Shen, Sathiyamoorthy Selvarajan, Mingzhao Xing, Jiatong Wang, Qiao‐Nan Guo, Fan Wu, Yi-Feng Zhang, Shu Zheng, Haixia Guan, Tingting Gong, Jingqiang Zhu, Xiangfeng Lin, Jianbiao Wang, Guangzhi Wang, Yan Zhou, Kennichi Kakudo, Yangfan Lv, Erik K. Alexander, Chuang Chen, Yaoting Sun, Xue Cai, He Wang, Tong Liu, Hao Zhang, Ting Chen, Zhihong Wang, Li Lu, Xiu Nie, Feng Yang, Jincao Yao, Yi He, Jun Pan, Hong Han, Xiaohong Wu, Nan Yao, Peng Li, Liqin Qian, Dong Xu, Wenjun Wei, Hanqing Liu, Pingping Hu, Yu Wang, Xin Zhu, Yijun Wu, Dingcun Luo
article en
2 citations

Abstract

Differentiating follicular thyroid adenoma (FTA) from carcinoma (FTC) remains challenging due to similar histological features separate from invasion. This study developed and validated DNA- and/or protein-based classifiers. A total of 2443 thyroid samples from 1568 patients were obtained from 24 centers in China and Singapore. Next-generation sequencing of a 66-gene panel revealed 41 (62.1%) detectable genes, while 25 were not, showing similar alteration patterns with differing mutation frequencies. Proteomics quantified 10,336 proteins, with 187 dysregulated. A discovery protein-based XGBoost model achieved an AUROC of 0.899 (95% CI, 0.849-0.949), outperforming the gene-based model (AUROC 0.670 [95% CI, 0.612-0.729]). A subsequent 24-protein classifier, developed via targeted mass spectrometry and validated in three independent sets, showed high performance in retrospective cohorts (AUROC 0.871 [95% CI, 0.833-0.910] and 0.853 [95% CI, 0.772-0.934]) and prospective biopsies (AUROC 0.781 [95% CI, 0.563-1.000]). It exhibited a 95.7% negative predictive value for ruling out malignancy. This study presents a promising protein-based approach for the differential diagnosis of FTA and FTC, potentially enhancing diagnostic accuracy and clinical decision-making.

EMBO Molecular MedicineVol. 17(7)
Qingdao University (CN), Brigham and Women's Hospital (US), Army Medical University (CN), Harbin Medical University (CN), Dalian Medical University (CN), Singapore General Hospital (SG), Sichuan University (CN), Sir Run Run Shaw Hospital (CN), Yuhuangding Hospital (CN), Southern University of Science and Technology (CN), Westlake University (CN), Wuhan University (CN), West China Hospital of Sichuan University (CN), Fudan University Shanghai Cancer Center (CN), Shanghai CASB Biotechnology (China) (CN), Zhejiang Cancer Hospital (CN), Second Affiliated Hospital of Dalian Medical University (CN), Third Affiliated Hospital of Harbin Medical University (CN), Xinqiao Hospital (CN), Qingdao Municipal Hospital (CN), Zhongshan Hospital (CN), Izumi City General Hospital (JP), Shanghai Tenth People's Hospital (CN), National Cancer Centre Singapore (SG), Renmin Hospital of Wuhan University (CN), First Hospital of China Medical University (CN), Shanghai Sixth People's Hospital (CN), Guangdong Academy of Medical Sciences (CN), Affiliated Hangzhou First People's Hospital, Westlake University, School of Medicine (CN), Union Hospital (CN), Hangzhou Medical College (CN), Hangzhou Cancer Hospital (CN), First Affiliated Hospital Zhejiang University (CN), Zhejiang University (CN), China Medical University (CN)
China Postdoctoral Science Foundation, National Key Research and Development Program of China
Peace, Justice and strong institutions
Openalex Percentile: Top 10%
Thyroid Cancer Diagnosis and Treatment
2.59
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.