Development of machine learning models to predict lymph node metastases in major salivary gland cancers

Abstract

Introduction: Indications for elective treatment of the neck in patients with major salivary gland cancers are still debated. Our purpose was to develop a machine learning (ML) model able to generate a pre-dictive algorithm to identify lymph node metastases (LNM) in patients with major salivary gland cancer (SGC).Methods: A Retrospective study was performed with data obtained from the Surveillance, Epidemiology, and End Results (SEER) program. Patients diagnosed with a major SGC between 1988 and 2019 were included. Two 2-class supervised ML decision models (random forest, RF; extreme gradient boosting, XGB) were used to predict the presence of LNM, implementing thirteen demographics and clinical variables collected from the SEER database. A permutation feature importance (PFI) score was computed using the testing dataset to identify the most important variables used in model prediction.Results: A total of 10 350 patients (males: 52%; mean age: 59.9 +/- 17.2 years) were included in the study. The RF and the XGB prediction models showed an overall accuracy of 0.68. Both models showed a high specificity (RF: 0.90; XGB: 0.83) and low sensitivity (RF: 0.27; XGB: 0.38) in identifying LNM. According, a high negative predictive value (RF: 0.70; XGB: 0.72) and a low positive predictive value (RF: 0.58; XGB: 0.56) were measured. T classification and tumor size were the most important features in the con-struction of the prediction algorithms.Conclusions: Classification performance of the ML algorithms showed high specificity and negative predictive value that allow to preoperatively identify patients with a lower risk of LNM.Lay summary: Based on data from the Surveillance, Epidemiology, and End Results (SEER) program, our study showed that machine learning algorithms owns a high specificity and negative predictive value, allowing to preoperatively identify patients with a lower risk of lymph node metastasis. Level of evidence: 3.