Prediction Model of Pathologic Central Lymph Node Negativity in cN0 Papillary Thyroid Carcinoma

Shu, Xiujie; Tang, Lingfeng; Hu, Daixing; Wang, Yuanyuan; Yü, Ping; Yang, Zhixin; Deng, Congrui; Wang, Denghui; Su, Xinliang

doi:10.3389/fonc.2021.727984

Cited by 6 publications

(5 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We noticed that currently, many investigators are developing CLNM risk strati cation prediction tools incorporating many risk factors to help evaluate the need for CLND. Yet among these, few studies have focused on the likelihood of CLNM in the mono-focal, encapsulated group of PTC, underestimating the risk of CLNM in this group of patients whom have traditionally been considered as low cervical lymph node involvement risk group among all PTC patients [13][14][15]. Our study innovatively reviewed data from 1014 mono-focal and encapsulated PTC patients to better assist clinicians in making decisions about whether to perform CLND, and the frequency of postoperative follow-up.…”

Section: Discussionmentioning

confidence: 99%

“…Relatively, the CLNM rates for mono-focal PTC patients without gross ETE by preoperative US were generally low, and these patients are the main candidates for active surveillance (AS) [13]. However, relevant research data showed that even for those without ETE or multifocality, the incidence rate of CLNM was still up to about 30% [13][14][15]. To the best of our knowledge, although several studies have been conducted on the prediction of CLNM for PTC patients, none of them have focused on mono-focal patients with preoperatively-con rmed encapsulated tumor, who have long been thought as low CLNM risk subgroup.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Risk Stratification for Central Lymph Node Metastasis in Mono-focal Papillary Thyroid Carcinoma Patients with Encapsulated Tumor as Confirmed by Preoperative Ultrasound: a Multi-center Analysis

Heng

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

Purposes: Mono-focal papillary thyroid carcinoma (PTC) patients with encapsulated tumor have traditionally been considered as low central lymph node metastasis (CLNM) risk subgroup. The aim of the research was to quantitatively predict the probability of CLNM for mono-focal PTC patients with encapsulated tumor as confirmed by preoperative ultrasound based on pre- and post-operative indexes respectively to guide the selection of prophylactic central lymph node dissection (CLND) and follow-up strategies. Methods A total of 1014 mono-focal PTC patients with encapsulated tumor as confirmed by preoperative ultrasound from three medical centers were retrospectively analyzed, with 534 patients served as Training group and 480 patients as Validation group. Results Multivariate analyses showed that age < 55 years old, male, clinical maximum tumor diameter (cMTD) > 0.5cm, pathological maximum tumor diameter (pMTD) > 0.5cm, and the presence of microscopic thyroid capsular invasion (mTCI) were independent CLNM risk factors. These were used to construct two nomograms that can effectively predict the central neck involvement in mono-focal PTC patients with encapsulated tumor. The first nomogram (pre-model) provides quantitative assessment on the necessity of prophylactic CLND, while the second nomogram (post-model) informs postoperative follow-up strategies. Conclusions Meticulous and comprehensive stratification flow charts that quantitatively evaluate the risk of central lymph node metastasis both pre- and post-operatively were constructed for mono-focal PTC patients with encapsulated tumor as confirmed by preoperative ultrasound, which may benefit both clinical decision-making of prophylactic CLND and postoperative follow-up strategies for the management of neck regions.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Risk Stratification for Central Lymph Node Metastasis in Mono-focal Papillary Thyroid Carcinoma Patients with Encapsulated Tumor as Confirmed by Preoperative Ultrasound: a Multi-center Analysis

Heng

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The dissection of the central compartment was considered level VI and included the prelaryngeal, pretracheal, and paratracheal lymph nodes. The lateral lymph nodes involve levels II, III, IV, and V. The surgical procedure has been described in our previous studies [14,15]. The central lymph nodes were examined by intraoperative frozen section evaluation conducted by two senior pathologists.…”

Section: Surgical Approachmentioning

confidence: 99%

Explainable machine learning model for predicting paratracheal lymph node metastasis in cN0 papillary thyroid cancer

Chun,

Wang,

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Prophylactic dissection of the paratracheal lymph nodes in clinical lymph node-negative (cN0) papillary thyroid carcinoma (PTC) remains controversial, as it is difficult to accurately assess the status of the paratracheal lymph nodes preoperatively. This study aimed to construct and validate an interpretable predictive model for paratracheal lymph node metastasis (PLNM) in cN0 PTC using machine learning (ML) methods. We retrospectively selected 3,212 PTC patients treated at the First Affiliated Hospital of Chongqing Medical University from 2016 to 2020. They were randomly divided into the training and test datasets with a 7:3 ratio. The 533 PTC patients treated at the Guangyuan Central Hospital from 2019 to 2022 were used as an external test set. Nine ML models, including XGBoost, were developed. The predictive performance was evaluated using ROC curves, decision curve analysis (DCA), calibration curves, and precision-recall curves. SHapley Additive exPlanations (SHAP) were used to interpret the top 10 predictive features, and a web-based calculator was created. The XGBoost model achieved AUC values of 0.935, 0.857, and 0.775 in the training, validation, and test sets, respectively, significantly outperforming the traditional nomogram model with AUCs of 0.85, 0.844, and 0.769, respectively. SHAP-based visualizations identified the top ten predictive features: prelaryngeal and pretracheal LNMR, tumor size, pretracheal LNMR, prelaryngeal and pretracheal LNM, age, tumor border, pretracheal LNM, pretracheal NLNM, side of position, calcification. These features were used to develop a web-based calculator. ML is a reliable tool for predicting PLNM in cN0 PTC patients. The SHAP method provides valuable insights into the XGBoost model, and the resultant web-based calculator is a clinically useful tool to assist in the surgical planning for paratracheal lymph node dissection.

show abstract

“…The 2022 National Comprehensive Cancer Network (NCCN) advises against utilizing prophylactic CLND to treat T1 and T2 cN0 PTC ( 5 ). Nevertheless, the sensitivity of preoperative detection, such as ultrasound, is low for assessing the central lymph node (CLN) state ( 6 ); thus, the high probability of occult CLNM cannot be ignored even in cN0 PTMCs ( 7 ).…”

Section: Introductionmentioning

confidence: 99%

A clinical and molecular pathology prediction model for central lymph node metastasis in cN0 papillary thyroid microcarcinoma

Wang

Zhang

et al. 2023

Front. Endocrinol.

View full text Add to dashboard Cite

BackgroundThe frequency of thyroid cancer has rapidly increased in recent years globally. Thus, more papillary thyroid microcarcinoma (PTMC) patients are being diagnosed, including clinical lymph node-negative (cN0) patients. Our study attempted to develop a prediction model for assessing the probability of central lymph node metastasis (CLNM) in cN0 PTMC patients.MethodsA total of 595 patients from the Affiliated Hospital of Qingdao University (training cohort: 456 patients) and the Affiliated Hospital of Jining Medical University (verification cohort: 139 patients) who underwent thyroid surgery between January 2020 and May 2022 were enrolled in this study. Their clinical and molecular pathology data were analyzed with multivariate logistic regression to identify independent factors, and then we established a prediction model to assess the risk of CLNM in cN0 PTMC patients.ResultsMultivariate logistic regression analysis revealed that sex, Hashimoto’s thyroiditis (HT), tumor size, extrathyroidal extension, TERT promoter mutations and NRAS mutation were independent factors of CLNM. The prediction model demonstrated good discrimination ability (C-index: 0.757 and 0.753 in the derivation and validation cohorts, respectively). The calibration curve of the model was near the optimum diagonal line, and decision curve analysis (DCA) showed a noticeably better benefit.ConclusionCLNM in cN0 PTMC patients is associated with male sex, tumor size, extrathyroidal extension, HT, TERT promoter mutations and NRAS mutation. The prediction model exhibits good discrimination, calibration and clinical usefulness. This model will help to assess CLNM risk and make clinical decisions in cN0 PTMC patients.

show abstract

Prediction Model of Pathologic Central Lymph Node Negativity in cN0 Papillary Thyroid Carcinoma

Cited by 6 publications

References 50 publications

Risk Stratification for Central Lymph Node Metastasis in Mono-focal Papillary Thyroid Carcinoma Patients with Encapsulated Tumor as Confirmed by Preoperative Ultrasound: a Multi-center Analysis

Risk Stratification for Central Lymph Node Metastasis in Mono-focal Papillary Thyroid Carcinoma Patients with Encapsulated Tumor as Confirmed by Preoperative Ultrasound: a Multi-center Analysis

Explainable machine learning model for predicting paratracheal lymph node metastasis in cN0 papillary thyroid cancer

A clinical and molecular pathology prediction model for central lymph node metastasis in cN0 papillary thyroid microcarcinoma

Contact Info

Product

Resources

About