Development and Validation of Clinical-Radiomics Nomogram for Preoperative Prediction of Central Lymph Node Metastasis in Papillary Thyroid Carcinoma.

BACKGROUND: This investigation sought to create and verify a nomogram utilizing ultrasound radiomics and crucial clinical features to preoperatively identify central lymph node metastasis (CLNM) in patients diagnosed with papillary thyroid carcinoma (PTC). METHODS: We enrolled 1069 patients with PTC between January 2022 and January 2023. All patients were randomly divided into a training cohort (n = 748) and a validation cohort (n = 321). We extracted 129 radiomics features from the original gray-scale ultrasound image. Then minimum Redundancy-Maximum Relevance and Least Absolute Shrinkage and Selection Operator regression were used to select the CLNM-related features and calculate the radiomic signature. Incorporating the radiomic signature and clinical risk factors, a clinical-radiomics nomogram was constructed using multivariable logistic regression. The predictive performance of clinical-radiomics nomogram was evaluated by calibration, discrimination, and clinical utility in the training and validation cohorts. RESULTS: The clinical-radiomics nomogram which consisted of five predictors (age, tumor size, margin, lateral lymph node metastasis, and radiomics signature), showed good calibration and discrimination in both the training (AUC 0.960; 95% CI, 0.947-0.972) and the validation (AUC 0.925; 95% CI, 0.895-0.955) cohorts. Discrimination of the clinical-radiomics nomogram showed better discriminative ability than the clinical signature, radiomics signature, and conventional ultrasound model in both the training and validation cohorts. Decision curve analysis showed satisfactory clinical utility of the nomogram. CONCLUSION: The clinical-radiomics nomogram incorporating radiomic signature and key clinical features was efficacious in predicting CLNM in PTC patients.

Construction of a nomogram for central lymph node metastasis in papillary thyroid cancer based on gender grouping.

BACKGROUND: The status of central lymph nodes is crucial for determining the surgical approach to papillary thyroid carcinoma (PTC). Because of the differences between genders in central lymph node metastasis (CLNM), we aimed to construct separate predictive models for CLNM according to gender. METHODS: In our study, a total of 1258 PTC patients who underwent thyroid cancer surgery from September 2021 to March 2023 were analyzed retrospectively. The data were analysed univariately and multivariately using SPSS software grouped according to gender and nomograms of CLNM were plotted using R software. The variables included in this study were sex, Age, body mass index, Diabetes, chronic lymphocytic thyroiditis (CLT), Suspicious central lymph node (SCLN), A/T, Margin, Microcalcification (MC), BRAF, Number, Location, CLNM. RESULTS: The preoperative nomogram in male patients included four clinical variables: CLT, Margin, Number, Size. The preoperative nomogram of female patients included six clinical variables: Age, SCLN, Margin, MC, Number, Size. The calibration curves showed great agreement in both the training group and the validation group. The decision curve analysis showed the feasibility of nomogram in predicting CLNM in both man and woman. CONCLUSION: Based on the successful establishment of nomogram, we can analyze the variability of CLNM between male and female, which may provide clinicians with personalized clinical schemes in the treatment of PTC.

Prediction model of lymph node metastasis posterior to the right recurrent laryngeal nerve.

BACKGROUND: At present, it is still controversial whether lymph nodes posterior to the right recurrent laryngeal nerve (LN-prRLN) in papillary thyroid carcinoma (PTC) patients should be dissected. Failure to dissect metastatic lymph nodes results in continued metastasis from the positive lymph nodes to other regions. Our study aimed to establish a predictive model and predict the probability of metastasis of the lymph nodes posterior to the right recurrent laryngeal nerve (LNM-prRLN) in patients. METHODS: A total of 309 patients underwent surgery for thyroid cancer between May 2019 and September 2022. The risk factors were identified by univariate and multivariate analyses, and statistically significant risk factors identified in the multivariate analysis were included in the nomogram. We used the calibration curve and the receiver operating characteristic (ROC) curve to verify the accuracy of the prediction model. RESULTS: Multivariate analysis showed that irregular tumor margins (OR: 3.549, 95% CI 1.294-9.733, P = 0.014), extrathyroidal extension (OR: 4.507, 95% CI 1.694-11.993, P = 0.003), maximum tumor diameter > 1 cm (OR: 5.729, 95% CI 2.617-12.542, P < 0.001), overweight status (OR: 2.296, 95% CI 1.057-4.987, P = 0.036), high total cholesterol level (OR: 5.238, 95% CI 2.304-11.909, P < 0.001), and multifocality (OR: 11.954, 95% CI 5.233-27.305, P < 0.001) were independent risk factors for LNM-prRLN. The area under the ROC curve was 0.927. The calibration curve showed good agreement between the predicted and observed rates of LNM-prRLN. CONCLUSION: The probability of LNM-prRLN could be predicted by a nomogram based on the statistically significant risk factors identified in the multivariate analysis. This nomogram can guide clinicians when preoperatively evaluating the status of the LN-prRLN with regard to LNM-prRLN in PTC patients. For patients at high risk for LNM-prRLN, the preventive dissection of LN-prRLNs can be considered.

Nomograms for Prediction of High-Volume Lymph Node Metastasis in Papillary Thyroid Carcinoma Patients.

OBJECTIVE: The coexistence rate between chronic lymphocytic thyroiditis (CLT) and papillary thyroid carcinoma (PTC) is quite high. Whether CLT influences metastatic lymph nodes remains uncertain. High-volume lymph node metastasis is recommended as an unfavorable pathological feature. We aimed to investigate risk factors for high-volume central lymph node metastasis (CLNM) and lateral lymph node metastasis (LLNM) in PTC patients. STUDY DESIGN: Retrospective cohort study. SETTING: Changzhou First People's Hospital. METHODS: Clinicopathological characteristics of 1094 PTC patients who underwent surgery in our center from January 2019 to November 2021 were analyzed. RESULTS: The number of metastatic lymph nodes in the central compartment and lateral compartment were lower in the CLT group. We demonstrated that age, BRAF V600E, shape, and the number of foci were risk factors for high-volume CLNM in patients with CLT. For patients without CLT, sex, age, tumor size, number of foci, and margin were risk factors for high-volume CLNM. Tumor size, number of foci, location, and CLNM were all risk factors for high-volume LLNM in patients with or without CLT. Body mass index was only associated with high-volume LLNM in CLT patients. All the above factors were incorporated into nomograms, which showed perfect discriminative ability. CONCLUSION: Separate predictive systems should be used for CLT and non-CLT patients for a more accurate clinical assessment of lymph node status. Our nomograms of predicting high-volume CLNM and LLNM could facilitate risk-stratified management of PTC recurrence and treatment decisions.

Construction of prediction models for determining the risk of lateral lymph node metastasis in patients with thyroid papillary carcinoma based on gender stratification.

BACKGROUND: Lateral lymph node metastasis (LLNM) is associated with poor prognosis in patients with papillary thyroid cancer (PTC). The purpose of this study was to determine the risk factors for LLNM and establish prediction models that could individually assessed the risk of LLNM. METHODS: A total of 619 PTC patients were retrospectively analyzed in our study. Univariate and multivariate analysis were performed for male and female patients, respectively, to assess relationships between clinicopathological features and LLNM. By integrating independent predictors selected by binary logistic regression modeling, preoperative and postoperative nomograms were developed to estimate the risk of LLNM. RESULTS: LLNM was detected in 80 of 216 male patients. Of 403 female patients, 114 had LLNM. The preoperative nomogram of male patients included three clinical variables: the number of foci, tuner size, and echogenic foci. In addition to the above three variables, the postoperative nomogram of male patients included extrathyroidal extension (ETE) detected in surgery, central lymph node metastasis (CLNM) and high-volume CLNM. The preoperative nomogram of female patients included the following variables: age, chronic lymphocytic thyroiditis (CLT), BRAF V600E, the number of foci, tumor size and echogenic foci. Variables such as CLT, BRAF V600E, the number of foci, tumor size, ETE detected in surgery, CLNM, high-volume CLNM and central lymph node ratio were included in the postoperative nomogram. Above Nomograms show good discrimination. CONCLUSIONS: Considering the difference in the incidence rate of LLNM between men and women, a separate prediction system should be established for patients of different genders. These nomograms are helpful in promoting the risk stratification of PTC treatment decision-making and postoperative management.

LASSO-based machine learning models for the prediction of central lymph node metastasis in clinically negative patients with papillary thyroid carcinoma.

Background: The presence of central lymph node metastasis (CLNM) is crucial for surgical decision-making in clinical N0 (cN0) papillary thyroid carcinoma (PTC) patients. We aimed to develop and validate machine learning (ML) algorithms-based models for predicting the risk of CLNM in cN0 patients. Methods: A total of 1099 PTC patients with cN0 central neck from July 2019 to March 2022 at our institution were retrospectively analyzed. All patients were randomly split into the training dataset (70%) and the validation dataset (30%). Eight ML algorithms, including the Logistic Regression, Gradient Boosting Machine, Extreme Gradient Boosting (XGB), Random Forest (RF), Decision Tree, Neural Network, Support Vector Machine and Bayesian Network were used to evaluate the risk of CLNM. The performance of ML models was evaluated by the area under curve (AUC), sensitivity, specificity, and decision curve analysis (DCA). Results: We firstly used the LASSO Logistic regression method to select the most relevant factors for predicting CLNM. The AUC of XGB was slightly higher than RF (0.907 and 0.902, respectively). According to DCA, RF model significantly outperformed XGB model at most threshold points and was therefore used to develop the predictive model. The diagnostic performance of RF algorithm was dependent on the following nine top-rank variables: size, margin, extrathyroidal extension, sex, echogenic foci, shape, number, lateral lymph node metastasis and chronic lymphocytic thyroiditis. Conclusion: By incorporating clinicopathological and sonographic characteristics, we developed ML-based models, suggesting that this non-invasive method can be applied to facilitate individualized prediction of occult CLNM in cN0 central neck PTC patients.

A comparative analysis of eight machine learning models for the prediction of lateral lymph node metastasis in patients with papillary thyroid carcinoma.

Background: Lateral lymph node metastasis (LLNM) is a contributor for poor prognosis in papillary thyroid cancer (PTC). We aimed to develop and validate machine learning (ML) algorithms-based models for predicting the risk of LLNM in these patients. Methods: This is retrospective study comprising 1236 patients who underwent initial thyroid resection at our institution between January 2019 and March 2022. All patients were randomly split into the training dataset (70%) and the validation dataset (30%). Eight ML algorithms, including the Logistic Regression, Gradient Boosting Machine, Extreme Gradient Boosting, Random Forest (RF), Decision Tree, Neural Network, Support Vector Machine and Bayesian Network were used to evaluate the risk of LLNM. The performance of ML models was evaluated by the area under curve (AUC), sensitivity, specificity, and decision curve analysis. Results: Among the eight ML algorithms, RF had the highest AUC (0.975), with sensitivity and specificity of 0.903 and 0.959, respectively. It was therefore used to develop as prediction model. The diagnostic performance of RF algorithm was dependent on the following nine top-rank variables: central lymph node ratio, size, central lymph node metastasis, number of foci, location, body mass index, aspect ratio, sex and extrathyroidal extension. Conclusion: By combining clinical and sonographic characteristics, ML algorithms can achieve acceptable prediction of LLNM, of which the RF model performs best. ML algorithms can help clinicians to identify the risk probability of LLNM in PTC patients.

Influence of Obesity Parameters on Different Regional Patterns of Lymph Node Metastasis in Papillary Thyroid Cancer.

Objective: Obesity increases risk of thyroid cancer. However, the association between obesity and the progression of papillary thyroid cancer (PTC) remains controversial. This retrospective study aimed to explore the relationship between obesity and regional patterns of lymph node metastasis (LNM) in PTC. Methods: We retrospectively reviewed data from 1015 patients with PTC. We calculated obese parameters, such as body mass index (BMI), body fat percentage (BFP), and body surface area (BSA). Logistic regression models were used to assess associations between obese parameters and the rate of lymph node metastasis (LNM), number of LNM, pattern of LNM, and lymph node ratio (LNR). Results: Higher BMI was not associated with different regional patterns of LNM in PTC. In men with PTC, high BFP was an independent predictor of total LNM, central lymph node metastasis (CLNM), total lateral lymph node metastasis (LLNM), multiple lateral lymph node metastasis, and simultaneous metastasis in lateral compartment. In addition, male patients with high BFP had higher central LNR and higher number of CLNM. For women, high BSA was an independent predictor of LLNM and level IV metastasis. Female patients with high BSA had higher number of CLNM. Conclusion: BFP and BSA, possibly influenced by gender, were positively associated with the number and risk of LNM in different regions of PTC patients. However, BMI was not the predictor for aggressiveness of PTC in terms of LNM. Clinical decision-making for regional LNM in PTC patients should consider the factor of obesity.

Nomograms for the prediction of lateral lymph node metastasis in papillary thyroid carcinoma: Stratification by size.

Background: Lateral lymph node metastasis (LLNM) is a risk factor of poor prognosis in papillary thyroid cancer (PTC). We aimed to determine predictive factors and develop the nomograms for LLNM in patients with papillary thyroid microcarcinoma (PTMC) and macro-PTC. Methods: We reviewed the medical records of 1,106 patients who underwent surgery between January 2019 and January 2022. Patients were divided into a PTMC and a macro-PTC group. We developed preoperative and postoperative nomograms for predicting LLNM based on results of multivariate analysis. Internal calibration was performed for these models. Results: The number of metastatic lymph nodes in lateral compartment was higher in macro-PTC patients. LLNM was independently associated with gender, the number of foci, location, shape, and central lymph node metastasis (CLNM) in PTMC patients. For macro-PTC patients, chronic lymphocytic thyroiditis, the number of foci, location, margin, CLNM, and central lymph node ratio were all independent predictors for LLNM. All the above factors were incorporated into nomograms, which showed the perfect discriminative ability. Conclusion: The diameter of the tumor has an impact on the rate of LLNM. Separate predictive systems should be used for PTMC and macro-PTC patients for more accurate clinical assessment of lateral lymph node status. Through these nomograms, we can not only detect high-risk patients with occult LLNM preoperatively, but also form appropriate treatment protocols for postoperative management of PTC patients with different risks.

Nomograms to predict ipsilateral and contralateral central lymph node metastasis in clinically lymph node-negative patients with solitary isthmic classic papillary thyroid carcinoma.

BACKGROUND: Isthmus-originating papillary thyroid carcinoma has unique clinicopathological characteristics. There are no specific guidelines regarding the extent of surgery for isthmic papillary thyroid carcinoma. We aimed to evaluate the characteristics of clinically lymph node-negative patients with solitary isthmic papillary thyroid carcinoma and to determine the best surgical protocol for these patients. METHODS: A total of 904 patients diagnosed with solitary papillary thyroid carcinoma who underwent surgery were retrospectively reviewed. These patients were divided into the isthmic group (246 patients) or lobar group (658 patients). We compared the 2 groups and conducted a multivariate analysis to assess risk factors for ipsilateral and contralateral central lymph node metastasis in isthmic papillary thyroid carcinoma patients. Nomograms for predicting central lymph node metastasis in isthmic papillary thyroid carcinoma patients were developed and internal calibration was performed for these models. RESULTS: Isthmic papillary thyroid carcinoma patients have a significantly higher incidence of extrathyroidal extension and central lymph node metastasis than do lobar papillary thyroid carcinoma patients. For isthmic papillary thyroid carcinoma patients, sex, BRAF V600E mutation, chronic lymphocytic thyroiditis, tumor size, margin, and extrathyroidal extension were independent risk factors of ipsilateral central lymph node metastasis. Body mass index, BRAF V600E mutation, tumor size, location, and extrathyroidal extension were independent risk factors of contralateral central lymph node metastasis. All the above factors were incorporated into nomograms, which showed the perfect discriminative ability. CONCLUSION: Based on the predictive nomograms, we proposed a risk stratification scheme and corresponding individualized surgical treatment based on different nomogram scores. In the debate about prophylactic central neck dissection among clinically lymph node-negative patients with solitary isthmic papillary thyroid carcinoma, our nomograms provide the balance to avoid overtreatment and undertreatment through personal risk assessment.

A Nomogram Based on Clinical and Ultrasound Characteristics to Predict Central Lymph Node Metastasis of Papillary Thyroid Carcinoma.

Background: The status of lymph nodes in the central compartment is crucial to determining the surgical strategies for papillary thyroid carcinoma (PTC). We aimed to develop a nomogram for predicting central lymph node metastasis (CLNM). Methods: A total of 886 PTC patients who underwent total thyroidectomy or lobectomy with central neck dissection (CND) from July 2019 to June 2020 were retrospectively retrieved. Clinical and ultrasound features were collected. Univariate and multivariate analysis were performed to determine risk factors of CLNM. A nomogram for predicting CLNM was developed, internal and external calibration was performed for the established model. Results: Variables (sex, chronic lymphocytic thyroiditis, tumor size, the number of foci, tumor location, margin) significantly associated with CLNM were included in the nomogram. The nomogram showed excellent calibration in the training group and validation group, with area under curves of 0.806 (95% CI, 0.771 to 0.825), and 0.799 (95% CI, 0.778-0.813) respectively. Conclusion: Through this accurate and easy-to-use nomogram, the possibility of CLNM can be objectively quantified preoperatively. Clinicians can use this nomogram to evaluate the status of lymph nodes in PTC patients and consider prophylactic CND for those with high scores.

Papillary Thyroid Microcarcinoma: A Nomogram Based on Clinical and Ultrasound Features to Improve the Prediction of Lymph Node Metastases in the Central Compartment.

Background: Accurate preoperative identification of central lymph node metastasis (CLNM) is essential for surgical protocol establishment for patients with papillary thyroid microcarcinoma (PTMC). We aimed to develop a clinical and ultrasound characteristics-based nomogram for predicting CLNM. Methods: Our study included 399 patients who were pathologically diagnosed with PTMC between January 2011 and June 2018. Clinical and ultrasound features were collected for univariate and multivariate analyses to determine risk factors of CLNM. A nomogram comprising the prognostic model to predict the CLNM was established, and internal validation in the cohort was performed. The Cox regression model was used to determine the risk factors for recurrence-free survival (RFS) and cumulative hazard was calculated to predict prognosis. Results: Three variables of clinical and US features as potential predictors including sex (odd ratio [OR] = 1.888, 95% confidence interval [CI], 1.160-3.075; P =0.011), tumor size (OR = 1.933, 95% CI, 1.250-2.990; P =0.003) and ETE (OR = 6.829, 95% CI, 3.250-14.350; P <0.001) were taken into account. The predictive nomogram was established by involving all the factors above used for preoperative prediction of CLNM in patients with PTMC. The nomogram showed excellent calibration in predicting CLNM, with area under curves (AUC) of 0.684 (95% CI, 0.635 to 0.774). Furthermore, tumor size, multifocality, presence of ETE, vascular invasion, and CLNM were the significant factors related to the RFS. Conclusion: Through this easy-to-use nomogram by combining clinical and US risk factor, the possibility of CLNM can be objectively quantified preoperatively. This prediction model may serve as a useful clinical tool to help clinicians determine an individual's risk of CLNM in PTMC, thus make individualized treatment plans accordingly.

Synchronous papillary thyroid carcinoma and follicular thyroid carcinoma: case report and review of literature.

Collision tumor is a term denoting two histologically distinct tumor types occuring at the same anatomic site, which is a rare clinical entity. In the thyroid gland, collision tumors are rare. Here we report a case of the synchronous occurrence of follicular thyroid carcinoma (FTC) and papillary thyroid carcinoma (PTC). The current case report describes a 40-year-old woman with synchronous FTC and PTC. Pathologists and surgeons should be aware of collision tumors to avoid possible misdiagnosis.

Influence of Tumor Number on Clinicopathologic Features and Outcomes of Patients With Papillary Thyroid Carcinoma.

OBJECTIVES: The purpose of this study was to investigate the significance of tumor number on clinicopathologic factors and outcomes of patients with papillary thyroid carcinoma (PTC). METHODS: We retrospectively analyzed 667 patients with PTC. We compared clinicopathologic features of patients with a different tumor number. Cox proportional hazards model was used to analyze risk factors of recurrence. RESULTS: In papillary thyroid microcarcinoma (PTMC), the increase in the number of tumor foci was related to a higher risk of minimal extrathyroidal extension (ETE) and lymphovascular invasion (P < .05). Patients with PTMC with four or more foci had a significantly higher risk of central lymph node metastasis (CLNM) and lateral lymph node metastasis (LLNM) than patients with solitary tumors (P < .05). Patients with macro-PTC with four or more foci and with three foci had a higher risk of gross ETE and lymphovascular invasion than patients with solitary tumors (P < .05). The increase in the tumor number was related to a higher risk of CLNM in macro-PTC (P < .05). The number of foci was the independent predictor of recurrence in patients with macro-PTC (P < .05). CONCLUSIONS: An increase in the number of tumors was associated with an increased risk of aggressive clinicopathologic features in PTMC and macro-PTC. The number of tumor foci could influence risk of recurrence in macro-PTC.