Related Experiment Video
Updated: Oct 19, 2025
Transoral Robotic Total Thyroidectomy and Bilateral Central Regional Lymph Node Dissection for Papillary Thyroid Carcinoma
Published on: September 15, 2023
Web-Based Ultrasonic Nomogram Predicts Preoperative Central Lymph Node Metastasis of cN0 Papillary Thyroid
Chunwang Huang1,2, Shuzhen Cong1,2, Shiyao Shang1
1Department of Ultrasound, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China.
Background:
Many clinicians are facing the dilemma about whether they should apply the active surveillance (AS) strategy for managing Clinically Node-negative (cN0) PTMC patients in daily clinical practice. This research plans to construct a dynamic nomogram based on network, connected with ultrasound characteristics and clinical data, to predict the risk of central lymph node metastasis (CLNM) in cN0 PTMC patients before surgery.
Methods:
A retrospective analysis of 659 patients with cN0 PTMC who had underwent thyroid surgery and central compartment neck dissection. Patients were randomly (2:1) divided into the development cohort (439 patients) and validation cohort (220 patients). The group least absolute shrinkage and selection operator (Group Lasso) regression method was used to select the ultrasonic features for CLNM prediction in the development cohort. These features and clinical data were screened by the multivariable regression analysis, and the CLNM prediction model and web-based calculator were established. Receiver operating characteristic, calibration curve, Clinical impact curve and decision curve analysis (DCA) were used to weigh the performance of the prediction model in the validation set.
Results:
Multivariable regression analysis showed that age, tumor size, multifocality, the number of contact surface, and real-time elastography were risk factors that could predict CLNM. The area under the curve of the prediction model in the development and validation sets were 0.78 and 0.77, respectively, with good discrimination and calibration. A web-based dynamic calculator was built. DCA proved that the prediction model had excellent net benefits and clinical practicability.
Conclusions:
The web-based dynamic nomogram incorporating US and clinical features was able to forecast the risk of preoperative CLNM in cN0 PTMC patients, and has good predictive performance. As a new observational indicator, NCS can provide additional predictive information.
More Related Videos
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
03:55Computer-Aided Three-Dimensional Visualization in the Treatment of Locally Advanced Thyroid Cancer
Published on: June 9, 2023