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

Lateral lymph node metastasis in papillary thyroid cancer: Is there a difference between PTC and PTMC?

Papillary thyroid carcinoma (PTC) and papillary thyroid microcarcinoma (PTMC) are generally characterized as less invasive forms of thyroid cancer with favorable prognosis. However, once lateral cervical lymph node metastasis takes place, the prognosis may be significantly impacted. The purpose of this study was to evaluate whether there is a difference in the pattern of lateral lymph node metastasis between PTC and PTMC. A retrospective analysis was performed for PTC and PTMC patients that underwent central area dissection and unilateral lateral neck lymph node dissection (II-V area) between January 2020 and December 2021. Compared with PTMC group, the PTC group exhibited higher incidence of capsule invasion, extrathyroid invasion and lymphatic vessel invasion. Both the number and rate of central lymph nodes metastasis were elevated in the PTC group. While the number of lateral cervical lymph node metastasis was higher, the metastasis rate did not demonstrate significant difference. No significant differences were identified in the lymph node metastasis patterns between the 2 groups. The determination of the extent of lateral neck lymph node dissection solely based on the tumor size may be unreliable, as PTC and PTMC showed no difference in the number and pattern of lateral neck metastasis. Additional clinical data are warranted to reinforce this conclusion. For patients categorized as unilateral, bilateral, or contralateral cervical lymph node metastasis (including level I, II, III, IV, or V) or retropharyngeal lymph node metastasis who require unilateral lateral neck dissection, the size of the primary tumor may not need to be a central consideration when assessing and deciding the extent of lateral neck dissection.

Predicting central cervical lymph node metastasis in papillary thyroid microcarcinoma using deep learning

Background

The aim of this study is to design a deep learning (DL) model to preoperatively predict the occurrence of central lymph node metastasis (CLNM) in patients with papillary thyroid microcarcinoma (PTMC).

Methods

This research collected preoperative ultrasound (US) images and clinical factors of 611 PTMC patients. The clinical factors were analyzed using multivariate regression. Then, a DL model based on US images and clinical factors was developed to preoperatively predict CLNM. The model's efficacy was evaluated using the receiver operating characteristic (ROC) curve, along with accuracy, sensitivity, specificity, and the F1 score.

Results

The multivariate analysis indicated an independent correlation factors including age ≥55 (OR = 0.309, p < 0.001), tumor diameter (OR = 2.551, p = 0.010), macrocalcifications (OR = 1.832, p = 0.002), and capsular invasion (OR = 1.977, p = 0.005). The suggested DL model utilized US images achieved an average area under the curve (AUC) of 0.65, slightly outperforming the model that employed traditional clinical factors (AUC = 0.64). Nevertheless, the model that incorporated both of them did not enhance prediction accuracy (AUC = 0.63).

Conclusions

The suggested approach offers a reference for the treatment and supervision of PTMC. Among three models used in this study, the deep model relied generally more on image modalities than the data modality of clinic records when making the predictions.

Integrating US-guided FNAB, BRAFV600E mutation, and clinicopathologic characteristics to predict cervical central lymph-node metastasis in preoperative patients with cN0 papillary thyroid carcinoma

BACKGROUND

The prevalence of cervical central lymph-node metastasis (CLNM) is high in patients with papillary thyroid carcinoma (PTC). There is considerable controversy surrounding the benefits of prophylactic central lymph-node dissection (pCLND) in patients with clinically negative central compartment lymph nodes (cN0). Therefore, it is crucial to accurately predict the likelihood of cervical CLNM before surgery to make informed surgical decisions.

METHODS

Date from 214 PTC patients (cN0) who underwent partial or total thyroidectomy and pCLND at the Guizhou Provincial People's Hospital were collected and retrospectively analyzed. They were divided into two groups in accordance with cervical CLNM or not. Their information, including clinical characteristics, ultrasound (US) features, pathological results of fine-needle aspirations biopsy (FNAB), and other characteristics of the groups, was analyzed and compared using univariate and multivariate logistic regression analyses.

RESULTS

A total of 214 patients were eligible in this study. Among them, 43.5% (93/214) of PTC patients had cervical CLNM, and 56.5% (121/214) did not. The two groups were compared using a univariate analyses, and there were no significant differences between the two groups in aspect ratio, boundary, morphology, component, and BRAFV600E (P > 0.05), and there were significant differences between gender, age, maximum tumor size, tumor location, capsule contact, microcalcifications, color Doppler flow imaging (CDFI), and Hashimoto's thyroiditis (HT) (P < 0.05). A multivariate logistic regression analysis was performed to further clarify the correlation of these indices. However, only age (OR = 2.455, P = 0.009), maximum tumor size (OR = 2.586, P = 0.010), capsule contact (OR = 3.208, P = 0.001), and CDFI (OR = 2.225, P = 0.022) were independent predictors of cervical CLNM. Combining these four factors, the area under the receiver-operating characteristic (ROC) curve for the joint diagnosis is 0.8160 (95% 0.7596-0.8725). Univariate analysis indicated that capsule contact (P = 0.001) was a possible predictive factor of BRAFV600E mutation.

CONCLUSIONS

In conclusion, four independent predictors of cervical CLNM, including age < 45 years, tumor size > 1.0 cm, capsule contact, and rich blood flow, were screened out. Therefore, a comprehensive assessment of these risk factors should be conducted when designing individualized treatment regimens for PTC patients.

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.

Prediction of Cervical Lymph Node Metastasis in Clinically Node-Negative T1 and T2 Papillary Thyroid Carcinoma Using Supervised Machine Learning Approach

Papillary thyroid carcinoma (PTC) is generally considered an indolent cancer. However, patients with cervical lymph node metastasis (LNM) have a higher risk of local recurrence. This study evaluated and compared four machine learning (ML)-based classifiers to predict the presence of cervical LNM in clinically node-negative (cN0) T1 and T2 PTC patients. The algorithm was developed using clinicopathological data from 288 patients who underwent total thyroidectomy and prophylactic central neck dissection, with sentinel lymph node biopsy performed to identify lateral LNM. The final ML classifier was selected based on the highest specificity and the lowest degree of overfitting while maintaining a sensitivity of 95%. Among the models evaluated, the k-Nearest Neighbor (k-NN) classifier was found to be the best fit, with an area under the receiver operating characteristic curve of 0.72, and sensitivity, specificity, positive and negative predictive values, F1 and F2 scores of 98%, 27%, 56%, 93%, 72%, and 85%, respectively. A web application based on a sensitivity-optimized kNN classifier was also created to predict the potential of cervical LNM, allowing users to explore and potentially build upon the model. These findings suggest that ML can improve the prediction of LNM in cN0 T1 and T2 PTC patients, thereby aiding in individual treatment planning.