The effectiveness and safety of prophylactic central neck dissection in clinically node-negative papillary thyroid carcinoma patients: A meta-analysis

Interpretable machine learning model based on the systemic inflammation response index and ultrasound features can predict central lymph node metastasis in cN0T1-T2 papillary thyroid carcinoma

Background

It is arguable whether individuals with T1-T2 papillary thyroid cancer (PTC) who have a clinically negative (cN0) diagnosis should undergo prophylactic central lymph node dissection (pCLND) on a routine basis. Many inflammatory indices, including the neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), monocyte-to-lymphocyte ratio (MLR), and systemic immune-inflammatory index (SII), have been reported in PTC. However, the associations between the systemic inflammation response index (SIRI) and the risk of central lymph node metastasis (CLNM) remain unclear.

Methods

Retrospective research involving 1,394 individuals with cN0T1-T2 PTC was carried out, and the included patients were randomly allocated into training (70%) and testing (30%) subgroups. The preoperative inflammatory indices and ultrasound (US) features were used to train the models. To assess the forecasting factors as well as drawing nomograms, the least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression were utilized. Then eight interpretable models based on machine learning (ML) algorithms were constructed, including decision tree (DT), K-nearest neighbor (KNN), support vector machine (SVM), artificial neural network (ANN), random forest (RF), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and categorical boosting (CatBoost). The performance of the models was evaluated by incorporating the area under the precision-recall curve (auPR) and the area under the receiver operating characteristic curve (auROC), as well as other conventional metrics. The interpretability of the optimum model was illustrated via the shapley additive explanations (SHAP) approach.

Results

Younger age, larger tumor size, capsular invasion, location (lower and isthmus), unclear margin, microcalcifications, color Doppler flow imaging (CDFI) blood flow, and higher SIRI (≥0.77) were independent positive predictors of CLNM, whereas female sex and Hashimoto thyroiditis were independent negative predictors, and nomograms were subsequently constructed. Taking into account both the auROC and auPR, the RF algorithm showed the best performance, and superiority to XGBoost, CatBoost and ANN. In addition, the role of key variables was visualized in the SHAP plot.

Conclusions

An interpretable ML model based on the SIRI and US features can be used to predict CLNM in individuals with cN0T1-T2 PTC.

Prevalence of Occult Central Lymph Node Metastasis by Tumor Size in Papillary Thyroid Carcinoma: A Systematic Review and Meta-Analysis

BACKGROUND

While papillary thyroid carcinoma (PTC) is associated with high occult central neck metastasis (CNM) rates, prophylactic central neck dissection (pCND) is controversial. This meta-analysis aims to look at the occult CNM rate according to tumor size.

METHODS

A literature search was conducted in PubMed from inception to April 2023. Inclusion criteria were primary studies that determined occult CNM rates in cN0 PTC by tumor size. Heterogeneity, influential case diagnostics, and proportion data were evaluated with Cochran's Q-test, Baujat plots and Forest plots, respectively.

RESULTS

Fifty-two studies were included in this meta-analysis. The findings demonstrated an occult CNM rate of 30.3% for tumors ≤ 5 mm, 32.7% for tumors ≤ 1 cm, 46.0% for tumors between 1 and 2 cm, 43.1% for tumors between 2 and 4 cm, and 61.2% for tumors > 4 cm. The heterogeneity of each study group was high, though no publication bias was noted. While there was a trend towards increased occult CNM rates with larger tumors, comparisons between different size cutoffs varied in significance.

CONCLUSION

This comprehensive review affirms that occult CNM is high and that an ipsilateral pCND can be justified in all PTC patients for accurate differentiation between Stage I and Stage II disease and its clinical implications.

Role of prophylactic central neck lymph node dissection for papillary thyroid carcinoma in the era of de-escalation

Thyroid cancer is the most common endocrine malignancy. While there has been no appreciable increase in the observed mortality of well-differentiated thyroid cancer, there has been an overall rise in its incidence worldwide over the last few decades. Patients with papillary thyroid carcinoma (PTC) and clinical evidence of central (cN1) and/or lateral lymph node metastases require total thyroidectomy plus central and/or lateral neck dissection as the initial surgical treatment. Nodal status in PTC patients plays a crucial role in the prognostic evaluation of the recurrence risk. The 2015 guidelines of the American Thyroid Association (ATA) have more accurately determined the indications for therapeutic central and lateral lymph node dissection. However, prophylactic central neck lymph node dissection (pCND) in negative lymph node (cN0) PTC patients is controversial, as the 2009 ATA guidelines recommended that CND "should be considered" routinely in patients who underwent total thyroidectomy for PTC. Although the current guidelines show clear indications for therapeutic CND, the role of pCND in cN0 patients with PTC is still debated. In small solitary papillary carcinoma (T1, T2), pCND is not recommended unless there are high-risk prediction factors for recurrence and diffuse nodal spread (extrathyroid extension, mutation in the BRAF gene). pCND can be considered in cN0 disease with advanced primary tumors (T3 or T4) or clinical lateral neck disease (cN1b) or for staging and treatment planning purposes. The role of the preoperative evaluation is fund-amental to minimizing the possible detrimental effect of overtreatment of the types of patients who are associated with low disease-related morbidity and mortality. On the other hand, it determines the choice of appropriate treatment and determines if close monitoring of patients at a higher risk is needed. Thus, pCND is currently recommended for T3 and T4 tumors but not for T1 and T2 tumors without high-risk prediction factors of recurrence.

Clinico-pathological initial outcome of a newly adopted novel surgical technique for nodal metastatic thyroid cancer at a large-volume centre in a high-income developing country

Introduction

Thyroid cancer is the most common tumour in the endocrine system. In the past decade, the incidence of lymph node metastasis has increased, and so has the patient demand for a smaller scar. This research reports the surgical and patho-oncological short-term outcomes of a novel, minimally invasive neck dissection approach for thyroid carcinoma with lymph node metastases at the UAE's leading endocrine surgery centre.

Methods

This study employed a prospectively maintained surgical database to retrospectively analyse relevant parameters such as surgical complications, including bleeding, hypocalcaemia nerve injury and lymphatic fistula, as well as oncological metrics such as the type of tumour and the ratio of lymph node metastasis to the number of harvested lymph nodes in 100 patients that underwent open minimally invasive selective neck dissection.

Results

The study comprised 50 patients with thyroidectomy, with bilateral central compartment neck dissection (BCCND; 50%); 34 with thyroidectomy, BCCND and selective bilateral lateral compartment neck dissection (BLCND; 34%); and 16 patients with selective unilateral central and lateral compartment neck dissection by recurrent nodal disease (ULCND; 16%). The female-to-male gender ratio was 78:22, with median ages of 36 and 42 years, respectively. Histopathology findings revealed that 92% of patients had papillary thyroid cancer (PTC) and 8% had medullary thyroid cancer. The mean total number of lymph nodes removed was 22 in the BLCND group, 17 in the ULCND group and 8 in the BCCND group (p = 0.001). Furthermore, the average lymph node metastasis was significantly higher in the BLCND group (p = 0.002). The percentage of temporary hypoparathyroidism was 29.8% and it persisted for 1.3%. The lateral compartment dissection morbidity was as follows: Four male patients with tall cell infiltrative PTC presented with pre-existing vocal cord paresis, necessitating nerve resection and anastomosis, and two more developed it after surgery (1.1% of the nerve at risk). Lymphatic fistulas occurred in four patients (4%) who were treated conservatively. Two patients were readmitted due to symptomatic neck collection. Horner syndrome was discovered in just one female patient. Male gender, aggressive histology and lateral compartment dissection independently increased surgical morbidity. In a high-volume endocrine centre, the adoption of minimally invasive selective neck dissections to treat nodal metastatic thyroid cancer did not increase specific cervical surgery complications.