Analysis of Risk Factors for Lymph Node Metastases in Elderly Patients with Papillary Thyroid Micro-Carcinoma

Optimal surgical population for cervical lymph node dissection in PTC

Objective

There is still controversy about whether cervical lymph node dissection should be performed in surgical treatment of PTC. Based on the data of thyroid cancer patients from Liaocheng People's Hospital from 2015 to 2018, this study focused on appropriate indications for cervical lymph node dissection surgery.

Methods

The clinical and pathological data of patients with initial treatment of PTC in thyroid surgery department from 2015 to 2018 were collected. In all cases, 1001 patients underwent total thyroidectomy + central lymph node dissection, and 1107 patients underwent total thyroidectomy + central + cervical lymph node dissection.

Results

The average metastasis rate of all cases was 57.23%, and even the metastasis rate of PTMC was as high as 48.97%. The total metastasis rate of central and lateral cervical lymph nodes was 74.44%, and the cervical lymph nodes were present in 49.32% of the metastatic cases. In 55.56% of the cases, the tumor diameter was more than 1 cm, and the metastasis rate of cervical lateral area was 56%. With the increase of tumor diameter, the cervical metastasis rate increased from 22.54% to 73.33%.

Conclusion

The metastasis rate of PTC is more than 50%, and nearly half of them have cervical metastasis, especially in patients with high risk factors. We observed that PTC 1 cm or greater has significant rates of metastasis.

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

BACKGROUND

The 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.

METHODS

A 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.

RESULTS

Multivariate 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.

CONCLUSION

CLNM 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.

A novel tool for predicting the risk of central lymph node metastasis in patients with papillary thyroid microcarcinoma: a retrospective cohort study

Introduction

Central lymph node status in papillary thyroid microcarcinoma (PTMC) plays an important role in treatment decision-making clinically, however, it is not easy to predict central lymph node metastasis (CLNM). The present work focused on finding the more rational alternative for evaluating central lymph node status while identifying influencing factors to construct a model to predict CLNM incidence.

Methods

In this study, we retrospectively analyzed the typical sonographic and clinicopathologic features of 546 PTMC patients who underwent surgery, among which, the data of 382 patients were recruited in the training cohort and that of 164 patients in the validation cohort. Based on the outcome of the training cohort, significant influencing factors were further identified through univariate analysis and were considered as independent variables in multivariable logistic regression analysis and incorporated in and presented with a nomogram.

Results

In total, six independent predictors, including the age, sex, tumor size, multifocality, capsular invasion, Hashimotos thyroiditis were entered into the nomogram. Both internal validation and external validation revealed the favorable discrimination of our as-constructed nomogram. Calibration curves exhibited high consistency. As suggested by decision-curve analyses, the as-constructed nomogram might be applied in clinic. Besides, the model also distinguished patients according to risk stratification.

Conclusions

The novel nomogram containing remarkable influencing factors for CLNM cases was established in the present work. The nomogram can assist clinicians in clinical decision-making.

Application of Machine Learning Algorithms to Predict Central Lymph Node Metastasis in T1-T2, Non-invasive, and Clinically Node Negative Papillary Thyroid Carcinoma

Purpose: While there are no clear indications of whether central lymph node dissection is necessary in patients with T1-T2, non-invasive, clinically uninvolved central neck lymph nodes papillary thyroid carcinoma (PTC), this study seeks to develop and validate models for predicting the risk of central lymph node metastasis (CLNM) in these patients based on machine learning algorithms.

Methods: This is a retrospective study comprising 1,271 patients with T1-T2 stage, non-invasive, and clinically node negative (cN0) PTC who underwent surgery at the Department of Endocrine and Breast Surgery of The First Affiliated Hospital of Chongqing Medical University from February 1, 2016, to December 31, 2018. We applied six machine learning (ML) algorithms, including Logistic Regression (LR), Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGBoost), Random Forest (RF), Decision Tree (DT), and Neural Network (NNET), coupled with preoperative clinical characteristics and intraoperative information to develop prediction models for CLNM. Among all the samples, 70% were randomly selected to train the models while the remaining 30% were used for validation. Indices like the area under the receiver operating characteristic (AUROC), sensitivity, specificity, and accuracy were calculated to test the models' performance.

Results: The results showed that ~51.3% (652 out of 1,271) of the patients had pN1 disease. In multivariate logistic regression analyses, gender, tumor size and location, multifocality, age, and Delphian lymph node status were all independent predictors of CLNM. In predicting CLNM, six ML algorithms posted AUROC of 0.70–0.75, with the extreme gradient boosting (XGBoost) model standing out, registering 0.75. Thus, we employed the best-performing ML algorithm model and uploaded the results to a self-made online risk calculator to estimate an individual's probability of CLNM (https://jin63.shinyapps.io/ML_CLNM/).

Conclusions: With the incorporation of preoperative and intraoperative risk factors, ML algorithms can achieve acceptable prediction of CLNM with Xgboost model performing the best. Our online risk calculator based on ML algorithm may help determine the optimal extent of initial surgical treatment for patients with T1-T2 stage, non-invasive, and clinically node negative PTC.