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.