Department of Pharmacy, The First Affiliated Hospital of Ningbo University, Ningbo, Zhejiang, China.
Department of Evaluation and Inspection, Center of Drug Evaluation and Inspection and Adverse Drug Reaction Monitoring of Ningxia Hui Autonomous Region, Yinchuan City, Ningxia Hui Autonomous Region, China.
Cancer Sci. 2024 Nov;115(11):3767-3775. doi: 10.1111/cas.16352. Epub 2024 Sep 23.
Hypothyroidism is a known adverse event associated with the use of immune checkpoint inhibitors (ICIs) in cancer treatment. This study aimed to develop an interpretable machine learning (ML) model for individualized prediction of hypothyroidism in patients treated with ICIs. The retrospective cohort of patients treated with ICIs was from the First Affiliated Hospital of Ningbo University. ML methods applied include logistic regression (LR), random forest classifier (RFC), support vector machine (SVM), and extreme gradient boosting (XGBoost). The area under the receiver-operating characteristic curve (AUC) was the main evaluation metric used. Furthermore, the Shapley additive explanation (SHAP) was utilized to interpret the outcomes of the prediction model. A total of 458 patients were included in the study, with 59 patients (12.88%) observed to have developed hypothyroidism. Among the models utilized, XGBoost exhibited the highest predictive capability (AUC = 0.833). The Delong test and calibration curve indicated that XGBoost significantly outperformed the other models in prediction. The SHAP method revealed that thyroid-stimulating hormone (TSH) was the most influential predictor variable. The developed interpretable ML model holds potential for predicting the likelihood of hypothyroidism following ICI treatment in patients. ML technology offers new possibilities for predicting ICI-induced hypothyroidism, potentially providing more precise support for personalized treatment and risk management.
甲状腺功能减退症是癌症治疗中使用免疫检查点抑制剂（ICI）的已知不良事件。本研究旨在开发一种可解释的机器学习（ML）模型，用于个体化预测接受 ICI 治疗的患者发生甲状腺功能减退症的可能性。接受 ICI 治疗的患者回顾性队列来自宁波大学第一附属医院。应用的 ML 方法包括逻辑回归（LR）、随机森林分类器（RFC）、支持向量机（SVM）和极端梯度提升（XGBoost）。受试者工作特征曲线下的面积（AUC）是主要评价指标。此外，还利用 Shapley 加法解释（SHAP）来解释预测模型的结果。共有 458 例患者纳入研究，其中 59 例（12.88%）患者发生甲状腺功能减退症。在所使用的模型中，XGBoost 表现出最高的预测能力（AUC=0.833）。Delong 检验和校准曲线表明，XGBoost 在预测方面明显优于其他模型。SHAP 方法表明，促甲状腺激素（TSH）是最具影响力的预测变量。所开发的可解释 ML 模型有望预测患者接受 ICI 治疗后发生甲状腺功能减退症的可能性。ML 技术为预测 ICI 诱导的甲状腺功能减退症提供了新的可能性，可能为个性化治疗和风险管理提供更精确的支持。
