Department of Otorhinolaryngology, Head and Neck Surgery, Beijing Chaoyang Hospital, Capital Medical University, 100020, China.
Department of Oncology, Zibo Central Hospital, 255035, China.
Am J Otolaryngol. 2024 May-Jun;45(3):104209. doi: 10.1016/j.amjoto.2023.104209. Epub 2023 Dec 22.
Currently, there are few practical tools for predicting the prognosis of laryngeal squamous cell carcinoma (LSCC). This study aims to establish a model and a convenient online prediction platform to predict whether LSCC patients will survive 5 years after diagnosis, providing a reference for further evaluation of patient prognosis.
This is a retrospective study based on data collected from two centers. Center 1 included 117 LSCC patients with survival prognosis data, and center 2 included 33 patients, totaling 150 patients. All data were divided into independent training sets (60 %) and testing sets (40 %). Eight machine learning (ML) algorithms were used to establish models with 11 clinical parameters as input features. The accuracy, sensitivity, specificity, and receiver operating characteristic curve (ROC) of the testing set were used to evaluate the models, and the best model was selected. The model was then developed into a website-based 5-year survival status prediction platform for LSCC. In addition, we also used the SHapley Additive exPlanations (SHAP) tool to conduct interpretability analysis on the parameters of the model.
The LSCC 5-year survival status prediction model using the support vector machine (SVM) algorithm achieved the best results, with accuracy, sensitivity, specificity, and area under the ROC curve (AUC) of 85.0 %, 87.5 %, 75.0 %, and 81.2 % respectively. The online platform for predicting the 5-year survival status of LSCC based on this model was successfully established. The SHAP analysis shows that the clinical stage is the most important feature of the model.
This study successfully established a ML model and a practical online prediction platform to predict the survival status of laryngeal cancer patients after 5 years, which may help clinicians to better evaluate the prognosis of LSCC.
目前，预测喉鳞状细胞癌（LSCC）预后的实用工具较少。本研究旨在建立一个模型和一个方便的在线预测平台，以预测 LSCC 患者在诊断后是否能存活 5 年，为进一步评估患者预后提供参考。
这是一项基于两个中心收集的数据的回顾性研究。中心 1 包括 117 例具有生存预后数据的 LSCC 患者，中心 2 包括 33 例患者，共计 150 例患者。所有数据均分为独立的训练集（60%）和测试集（40%）。使用 8 种机器学习（ML）算法，以 11 个临床参数作为输入特征建立模型。使用测试集的准确性、灵敏度、特异性和受试者工作特征曲线（ROC）评估模型，并选择最佳模型。然后，将模型开发成一个基于网站的 LSCC 5 年生存状态预测平台。此外，我们还使用 SHapley Additive exPlanations（SHAP）工具对模型的参数进行可解释性分析。
基于支持向量机（SVM）算法的 LSCC 5 年生存状态预测模型取得了最佳结果，其准确性、灵敏度、特异性和 ROC 曲线下面积（AUC）分别为 85.0%、87.5%、75.0%和 81.2%。基于该模型成功建立了一个用于预测 LSCC 5 年生存状态的在线平台。SHAP 分析表明，临床分期是模型中最重要的特征。
本研究成功建立了一个 ML 模型和一个实用的在线预测平台，以预测 LSCC 患者 5 年后的生存状态，这可能有助于临床医生更好地评估 LSCC 的预后。
