# Dose–Response Relationship Between BRAF V600E Abundance and Cervical Lymph Node Metastasis in Papillary Thyroid Cancer

## TL;DR

This study shows that the amount of BRAF V600E mutation in thyroid cancer, not just its presence, better predicts lymph node spread and helps guide surgery decisions.

## Contribution

The paper introduces a quantitative model using BRAF V600E abundance and ultrasound features to predict cervical lymph node metastasis in thyroid cancer.

## Key findings

- BRAF abundance above 20.7% sharply increases lymph node metastasis risk in papillary thyroid cancer.
- An XGBoost model integrating BRAF abundance and ultrasound features achieved strong predictive performance (AUC 0.752).
- Higher BRAF abundance correlates with clinical features like tumor size and microcalcifications.

## Abstract

Cervical lymph node status is critical when planning surgery for papillary thyroid carcinoma, yet most tools treat the BRAF V600E mutation as a simple yes/no finding. We asked whether the amount of BRAF (reported as a percentage in fine-needle aspiration samples) provides more useful, patient-specific information. In a single-center cohort, we measured BRAF abundance preoperatively and linked it with surgical pathology, using flexible models that allow for a relationship where risk increases as abundance rises rather than a fixed cut-off. We found a steep rise in nodal risk at around 20.7% BRAF abundance, followed by a near-plateau, and built an easy-to-understand risk tool that combines BRAF with routine ultrasound features and demographics. This approach may help clinicians discuss options before surgery, focus attention on higher-risk patients, and avoid unnecessary procedures in lower-risk cases. Prospective, multi-center validation is still needed.

Objectives: Papillary thyroid carcinoma (PTC) frequently presents with cervical lymph node metastasis (CLNM), yet preoperative tools often encode BRAF V600E as a binary variable, potentially overlooking information contained in mutation abundance. We sought to quantify the dose–response relationship between BRAF V600E abundance and CLNM and to develop an interpretable model for preoperative risk stratification. Methods: We performed a single-center retrospective study of consecutive PTC patients who underwent preoperative BRAF V600E testing and surgery from 2019 to 2023. Patients were randomly split 70/30 into training and test sets. Candidate predictors included clinical and ultrasound features and BRAF V600E abundance. We used multivariable logistic regression and restricted cubic splines (RCS) to assess nonlinearity and compared six machine-learning algorithms (LR, KNN, SVM, XGB, LightGBM, and NN). Model performance was evaluated by F1, AUC, calibration, and decision-curve analyses; SHAP aided interpretation. Ethics approval: SYSKY-2024-169-01. Results: The cohort included 667 patients; CLNM occurred in 391 (58.6%). CLNM cases had higher BRAF abundance (median 23% vs. 17%) and characteristic clinical/sonographic differences. RCS revealed a nonlinear association between abundance and CLNM, with a steep risk rise of up to ~20.7% followed by a plateau. Among six algorithms, XGBoost showed the best validation performance (AUC 0.752; F1 0.73). SHAP indicated that maximum tumor diameter, BRAF abundance, age, and microcalcifications contributed most to predictions. Conclusions: Modeling BRAF V600E as a quantitative abundance—rather than a binary status—improves preoperative CLNM risk assessment in PTC. An interpretable XGBoost model integrating abundance with routine features demonstrates acceptable discrimination and potential clinical utility for individualized surgical planning and counseling.