Protein Biomarker-Driven Machine Learning for Accurate Diagnosis of Invasive Encapsulated Follicular Variant Papillary Thyroid Carcinoma.
DOI:
https://doi.org/10.48047/Keywords:
Follicular pattern thyroid tumors, Thyroid carcinoma, Machine learning, Proteomics, Histological diagnosis.Abstract
Background: Differentiating follicular-pattern thyroid tumors remains diagnostically
challenging, despite established criteria. The 5th edition of the World Health Organization
Classification of Endocrine and Neuroendocrine Tumors reclassified invasive encapsulated
follicular variant papillary thyroid carcinoma (ieFVPTC) as a distinct entity. Accurate
distinction of ieFVPTC from low-risk follicular-pattern tumors is crucial due to their shared
morphological features. Proteomics, with its potential for protein biomarker detection and
quantification, offers a promising approach. This study investigated the utility of a machine
learning-derived protein biomarker panel for ieFVPTC identification using formalin-fixed
paraffin-embedded (FFPE) samples.
