Alshwayyat Sakhr, Qasem Hanan M, Khasawneh Lina, Alshwayyat Mustafa, Alkhatib Mesk, Alshwayyat Tala Abdulsalam, Salieti Hamza Al, Odat Ramez M
Research Associate, King Hussein Cancer Center, Amman, Jordan; Internship, Princess Basma Teaching Hospital, Irbid, Jordan; Research Fellow, Applied Science Research Center, Applied Science Private University, Amman, Jordan.
Faculty of Dentistry, Jordan University of Science and Technology, Irbid, Jordan.
J Stomatol Oral Maxillofac Surg. 2025 Jun;126(3S):102209. doi: 10.1016/j.jormas.2024.102209. Epub 2024 Dec 25.
Oral cancer, particularly mucoepidermoid carcinoma (MEC), presents diagnostic challenges due to its histological diversity and rarity. This study aimed to develop machine learning (ML) models to predict survival outcomes for MEC patients and pioneer a clinically accessible prognostic tool.
Using the SEER database (2000-2020), we constructed predictive models with five ML algorithms: Random Forest Classifier (RFC), Gradient Boosting Classifier (GBC), Logistic Regression (LR), K-Nearest Neighbors (KNN), and Multilayer Perceptron (MLP). Predictive variables were identified via Cox regression, and Kaplan-Meier analysis assessed survival trends. Model performance was validated through the area under the curve (AUC) of receiver operating characteristic (ROC) curves.
This study included 1314 patients diagnosed with MEC of the oral cavity. The RFC demonstrated the highest predictive accuracy (AUC = 0.55), followed by the GBC and RFC (AUC = 0.53). The most affected primary site was the hard palate, followed by the retromolar and cheek mucosa. Survival rates varied with the treatment modality, with the highest rates observed in patients undergoing surgery alone. ML models have identified age, sex, and metastasis as significant prognostic factors influencing survival outcomes, underscoring the complexity and heterogeneity of MEC.
This study highlights ML's potential to enhance survival predictions and personalize treatment for MEC patients. We developed the first web-based prognostic tool, providing a novel, accessible solution for improving clinical decision-making in MEC.
口腔癌，尤其是黏液表皮样癌（MEC），因其组织学多样性和罕见性而面临诊断挑战。本研究旨在开发机器学习（ML）模型以预测MEC患者的生存结局，并开创一种临床可用的预后工具。
利用监测、流行病学和最终结果（SEER）数据库（2000 - 2020年），我们使用五种ML算法构建了预测模型：随机森林分类器（RFC）、梯度提升分类器（GBC）、逻辑回归（LR）、K近邻算法（KNN）和多层感知器（MLP）。通过Cox回归确定预测变量，并采用Kaplan - Meier分析评估生存趋势。通过受试者操作特征（ROC）曲线的曲线下面积（AUC）验证模型性能。
本研究纳入了1314例被诊断为口腔MEC的患者。RFC显示出最高的预测准确性（AUC = 0.55），其次是GBC和RFC（AUC = 0.53）。受影响最严重的原发部位是硬腭，其次是磨牙后区和颊黏膜。生存率因治疗方式而异，单纯接受手术的患者生存率最高。ML模型已确定年龄、性别和转移是影响生存结局的重要预后因素，这凸显了MEC的复杂性和异质性。
本研究强调了ML在增强MEC患者生存预测和个性化治疗方面的潜力。我们开发了首个基于网络的预后工具，为改善MEC的临床决策提供了一种新颖、易用的解决方案。
