Interpretable machine learning model for prediction of overall survival in laryngeal cancer

Abstract

Background: The mortality rates of laryngeal squamous cell carcinoma cancer (LSCC) have not significantly decreased in the last decades.

Objectives: We primarily aimed to compare the predictive performance of DeepTables with the state-of-the-art machine learning (ML) algorithms (Voting ensemble, Stack ensemble, and XGBoost) to stratify patients with LSCC into chance of overall survival (OS). In addition, we complemented the developed model by providing interpretability using both global and local model-agnostic techniques.

Methods: A total of 2792 patients in the Surveillance, Epidemiology, and End Results (SEER) database diagnosed with LSCC were reviewed. The global model-agnostic interpretability was examined using SHapley Additive exPlanations (SHAP) technique. Likewise, individual interpretation of the prediction was made using Local Interpretable Model Agnostic Explanations (LIME).

Results: The state-of-the-art ML ensemble algorithms outperformed DeepTables. Specifically, the examined ensemble algorithms showed comparable weighted area under receiving curve of 76.9, 76.8, and 76.1 with an accuracy of 71.2%, 70.2%, and 71.8%, respectively. The global methods of interpretability (SHAP) demonstrated that the age of the patient at diagnosis, N-stage, T-stage, tumor grade, and marital status are among the prominent parameters.

Conclusions: A ML model for OS prediction may serve as an ancillary tool for treatment planning of LSCC patients.

Chinese Abstract

背景

喉鳞状细胞癌(LSCC)的死亡率在近几十年中并未显著下降。

目标

我们的主要目的是将 DeepTables与最先进的机器学习 (ML) 算法(Voting ensemble、Stack ensemble 和 XGBoost)进行其预测性能比较, 以便将 LSCC 患者按照总生存率 (OS) 机会进行分级。 此外, 我们还使用整体和局部模型不可知技术, 通过提供可解释性来改进已开发的模型。

方法

检查了监测、流行病学和最终结果 (SEER) 数据库中共 2792 名诊断为 LSCC 的患者。 使用SHapley Additive exPlanations (SHAP) 技术检查了整体模型-不可知可解释性。 同样, 对预测的单个解释是通过使用局部可解释模型不可知解释(LIME)来进行的。

结果

最先进的 ML 集成算法的性能优于 DeepTables。 具体来说, 所检查的集成算法显示, 接收曲线下的可比加权面积为 76.9、76.8、和 76.1, 准确率分别为 71.2%、70.2% 和 71.8%。 整体可解释性方法(SHAP) 显示, 患者诊断时的年龄、N 期、T 期、肿瘤等级和婚姻状况状态都是突出的参数。

结论

用于 OS 预测的 ML 模型可以作为制定喉鳞状细胞癌患者的治疗计划的辅助工具。

Keywords:

• Machine learning
• deep learning
• DeepTables
• laryngeal cancer
• laryngeal squamous cell carcinoma
• XGBoost
• voting ensemble
• stacked ensemble
• sEER
• overall survival

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

The Sigrid Jusélius Foundation. State funding for the Helsinki University Hospital. Finska Läkaresällskapet.