Prediction of lung metastases in thyroid cancer using machine learning based on SEER database

PURPOSE: Lung metastasis (LM) is one of the most frequent distant metastases of thyroid cancer (TC). This study aimed to develop a machine learning algorithm model to predict lung metastasis of thyroid cancer for providing relative information in clinical decision‐making. METHODS: Data comprising of demographic and clinicopathological characteristics of patients with thyroid cancer were extracted from the National Institutes of Health (NIH)’s Surveillance, Epidemiology, and End Results (SEER) database between 2010 and 2015, which is employed to develop six machine learning algorithm models support vector machine (SVM), logistic regression (LR), eXtreme gradient boosting (XGBoost), decision tree (DT), random forest (RF), and k‐nearest neighbor (KNN). Compared and evaluated models by the following indicators: accuracy, precision, recall rate, F1‐score, the area under the ROC curve (AUC) value and Brier score, and interpreted the association between clinicopathological characteristics and target variables based on the best model. RESULTS: Nine thousand nine hundred and fifty patients were selected, which including 212 patients (2.1%) with lung metastasis, and 9738 patients without lung metastasis (97.9%). Multivariate logistic regression showed that age, T stage, N stage, and histological type were independent factors in TC with LM. Evaluation indicators of the best model‐ RF were as following: accuracy (0.99), recall rate (0.88), precision (0.61), F1‐score (0.72), AUC value (0.99), and the Brier score (0.016). CONCLUSION: RF learning model performed better and can be applied to forecast lung metastasis of thyroid cancer, and offer valuable and significant reference for clinicians' decision‐making in advance.