KES
Articles
- Page Path
- HOME > Endocrinol Metab > Ahead-of print > Article
- Original Article Comprehensive Proteomics and Machine Learning Analysis to Distinguish Follicular Adenoma and Follicular Thyroid Carcinoma from Indeterminate Thyroid Nodules
-
Hee-Sung Ahn1,2
, Eyun Song3, Chae A Kim4, Min Ji Jeon4, Yu-Mi Lee5, Tea-Yon Sung5, Dong Eun Song6, Jiyoung Yu1, Ji Min Shin4,7, Yeon-Sook Choi4,7, Kyunggon Kim1,8
, Won Gu Kim4
-
DOI: https://doi.org/10.3803/EnM.2024.2208 [Epub ahead of print]
Published online: April 10, 2025
- 260 Views
- 19 Download
- 0 Crossref
- 0 Scopus
2AMC Sciences, Asan Medical Center, Seoul, Korea
3Division of Endocrinology and Metabolism, Department of Internal Medicine, Korea University College of Medicine, Seoul, Korea
4Division of Endocrinology and Metabolism, Department of Internal Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea
5Department of Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea
6Department of Pathology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea
7Department of Biomedical Sciences, AMIST, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea
8Department of Digital Medicine, BK21 Project, University of Ulsan College of Medicine, Seoul, Korea
-
Corresponding author:
Kyunggon Kim, Tel: +82-2-3010-4633,
Email: kimkyunggon@gmail.com
Won Gu Kim, Tel: +82-2-3010-5883, Fax: +82-2-3010-6962,
Email: wongukim@amc.seoul.kr
Abstract
Background
The preoperative diagnosis of follicular thyroid carcinoma (FTC) is challenging because it cannot be readily distinguished from follicular adenoma (FA) or benign follicular nodular disease (FND) using the sonographic and cytological features typically employed in clinical practice.
Methods
We employed comprehensive proteomics and machine learning (ML) models to identify novel diagnostic biomarkers capable of classifying three subtypes: FTC, FA, and FND. Bottom-up proteomics techniques were applied to quantify proteins in formalin-fixed, paraffin-embedded (FFPE) thyroid tissues. In total, 202 FFPE tissue samples, comprising 62 FNDs, 72 FAs, and 68 FTCs, were analyzed.
Results
Close spectrum-spectrum matching quantified 6,332 proteins, with approximately 9% (780 proteins) differentially expressed among the groups. When applying an ML model to the proteomics data from samples with preoperative indeterminate cytopathology (n=183), we identified distinct protein panels: five proteins (CNDP2, DNAAF5, DYNC1H1, FARSB, and PDCD4) for the FND prediction model, six proteins (DNAAF5, FAM149B1, RPS9, TAGLN2, UPF1, and UQCRC1) for the FA model, and seven proteins (ACTN4, DSTN, MACROH2A1, NUCB1, SPTAN1, TAGLN, and XRCC5) for the FTC model. The classifiers’ performance, evaluated by the median area under the curve values of the random forest models, was 0.832 (95% confidence interval [CI], 0.824 to 0.839) for FND, 0.826 (95% CI, 0.817 to 0.835) for FA, and 0.870 (95% CI, 0.863 to 0.877) for FTC.
Conclusion
Quantitative proteome analysis combined with an ML model yielded an optimized multi‐protein panel that can distinguish FTC from benign subtypes. Our findings indicate that a proteomic approach holds promise for the differential diagnosis of FTC.
Cite- Related articles
-
