Developing and validating a multivariable machine learning model for the preoperative prediction of lateral lymph node metastasis of papillary thyroid cancer

Abstract

Background At present, preoperative diagnosis of lateral cervical lymph node metastasis (LLNM) in patients with papillary thyroid carcinoma (PTC) mostly depends on the training and expertise of ultrasound doctors. A machine-learning model for predicting LLNM accurately before PTC surgery may help to determine the scope of surgery and reduce unnecessary surgical trauma. Methods The data of patients with primary PTC who underwent thyroidectomy with lateral cervical lymph node surgery at Beijing Tongren Hospital between July 2009 and June 2021 were retrospectively analyzed. All patients had complete ultrasonic examination, clinical data, and definite pathology diagnosis of lymph nodes. LLNM was confirmed by postoperative pathology. The patients were randomly divided into a training set (155 cases) and a test set (98 cases) at a ratio of 6:4. Eleven parameters, including patient demographics, ultrasound results, and tumor-related conditions, were collected, and a prediction model was established using the support vector machine (SVM) algorithm. Several other machine-learning algorithms were also used to establish models for comparison. The accuracy, precision, recall, F1-score, sensitivity, specificity, Cohen’s kappa value, and area under the receiver operating characteristic curve (AUC) were used to evaluate model performance. Results A total of 87 males and 156 females were included in the study, aged 14–80 years. One hundred and four patients of them had LLNM and 139 did not have LLNM. The pandas Python library was used for the statistical analysis, and the Spearman coefficient was used to analyze the correlation between each parameter and the prediction index. The SVM model performed the best among all the models. Its accuracy, precision, recall, F1-score, sensitivity, specificity, Cohen’s kappa value, and AUC were 90.8%, 91.0%, 90.8%, 90.8%, 87.5%, 94.0%, 81.6%, and 91.0%, respectively. Conclusions This model can enable surgeons to improve the accuracy of ultrasonography in predicting LLNM without additional examination, thus avoiding missing positive lateral cervical lymph nodes and reducing the sequelae caused by unnecessary lateral neck dissection.

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

“…The preoperative ultrasound suspicious findings (size of lymph node more than 5 mm, microcalcification, cystic degeneration, round shape, abnormal boundary, and cortical thickening) in addition to clinical data constitute another model[ 73 ]. Some statistical data of ultrasound signs are shown in Table 4 [ 74 ].…”

Comparison of different machine learning models based on ultrasound-based radiomics to predict central lymph node metastasis of papillary thyroid carcinoma

“…The models were trained using the training set, with optimization achieved through a grid search method incorporating ve-fold cross-validation to minimize prediction errors. Model performance in both the training and validation sets was assessed using standard clinical metrics such as the area under the curve (AUC), sensitivity, speci city, precision, recall, accuracy, and F1-score (19). The performance of models in the validation set was identi ed, and the diagnostic performance of the models was compared to select the best classi er.…”

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

“…Thyroid cancer has become the fastest-growing endocrine malignancy in recent years [1], Among them, papillary thyroid carcinoma (PTC) is the most common histological type, with a 10-year survival rate exceeding 95% [2]. However, the cervical lymph node metastasis (LNM) rate of PTC is as high as 30-80%, especially in the central area [3]. It was reported that patients with central lymph node metastasis (CLNM) might be more likely to have distant metastasis and poor survival than those without CLNM [4].…”