Related Experiment Video For albumin
Updated: May 27, 2025
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
Routine Blood Tests as Predictive Tools for Differentiating Follicular Thyroid Carcinoma From Follicular Adenoma
Jiaxi Wang1, Jingwei Wang2, Hanqing Liu3
1Department of Breast and Thyroid Surgery, Renmin Hospital of Wuhan University, Wuhan, People's Republic of China.
Background:
Thyroid cancer is the most common endocrine malignancy, with an increasing incidence rate, particularly among adolescents. Follicular thyroid carcinoma (FTC), though less common than papillary thyroid carcinoma (PTC), presents greater diagnostic challenges, especially when differentiating from follicular adenoma (FA). Current diagnostic methods lack specificity, underscoring the need for a simple, cost-effective predictive model for FTC.This study aimed to develop a predictive scoring system based on routine blood biomarkers to distinguish between FTC and FA, facilitating early diagnosis and treatment.
Methods:
A retrospective, single-center case-control study was conducted on patients diagnosed with FTC and FA at Renmin Hospital of Wuhan University from 2016 to 2022. Patients' demographic, clinicopathological characteristics, and preoperative blood biomarker data were analyzed. Statistical tests, including chi-square, t-tests, and Mann-Whitney U-tests, were used to compare biomarkers. Significant variables were included in univariate and multivariate logistic regression analyses, leading to the development of a scoring system. The model's performance was assessed using receiver operating characteristic (ROC) curves.
Results:
The study included 23 patients with FA and 26 patients with FTC. Seven blood biomarkers showed significant differences between the groups: ALB, DBIL, TBIL, LYM#, MCHC, RDW-SD, and WBC. Multivariate logistic regression identified ALB and WBC as key predictors, forming a scoring model (Score = 0.54 × ALB - 1.10 × WBC). The model exhibited strong predictive performance (AUC = 0.839), with sensitivity and specificity of 0.808 and 0.826, respectively.
Conclusion:
The study developed a novel predictive model using routine blood biomarkers, offering a non-invasive, cost-effective tool for differentiating between FTC and FA. The model has significant clinical potential, providing a feasible alternative to conventional diagnostic techniques. Further multicenter studies and mechanistic investigations are warranted to validate and refine the model, enhancing its utility in clinical practice.
