深度学习模型预测鼻咽癌放疗后甲状腺功能减退
该回顾性研究纳入2015年1月至2020年10月间535例鼻咽癌患者,采用Cox回归、LASSO-Cox分析和Spearman相关检验筛选预测因素,并构建两种深度学习与两种机器学习模型,与传统Cox及NTCP模型通过C-index、Brier评分和决策曲线分析进行比较。研究观察到放射性甲状腺功能减退(RIHT)发生率为41.7%,中位发生时间15个月;DeepSurv模型预测性能优于传统模型(C-index:DeepSurv 0.75,传统模型≤0.63)。
要点
- 535例鼻咽癌患者中RIHT发生率为41.7%,中位发生时间15个月。
- AJCC N分期、甲状腺体积及特定剂量-体积参数被识别为潜在预测因素。
- DeepSurv模型C-index为0.75,优于传统模型(≤0.63)。
核心结论
- DeepSurv在鼻咽癌患者RIHT预测中表现出优于传统模型的预测性能。
- 基于深度学习的预测具有较高准确性,可能有助于个体化患者管理并具有降低RIHT风险的潜力。
- 作者认为将此类模型纳入临床实践可能对RIHT管理有益。
研究设计与样本
- 回顾性研究,纳入2015年1月至2020年10月间535例鼻咽癌患者。
- 采用Cox回归、LASSO-Cox分析和Spearman相关检验识别显著预测因素。
- 训练、调优并比较两种深度学习算法与两种机器学习算法,并与传统Cox及NTCP模型通过C-index、Brier评分和决策曲线分析进行比较。
主要发现
- 研究观察到RIHT发生率为41.7%,中位发生时间为15个月。
- AJCC N分期、甲状腺体积和特定剂量-体积参数被识别为潜在预测因素。
- DeepSurv模型C-index为0.75,传统模型C-index≤0.63。
- 其他模型在治疗后早期时间间隔具有竞争力,深度学习模型随时间推移表现出更优性能。
- 校准和决策曲线分析证实了DeepSurv增强的预测能力;特征重要性分析显示甲状腺V30和V50是最显著的预测因素。
关键数值与推荐
- DeepSurv模型C-index为0.75,传统模型C-index≤0.63。
- RIHT发生率为41.7%,中位发生时间为15个月。
- 特征重要性分析显示甲状腺V30和V50为最显著的预测因素。
临床怎么用
- 原文结论认为将此类模型纳入临床实践可能对RIHT管理有益,并可能有助于个体化患者管理。
- 原文未据此给出具体推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Radiation-induced hypothyroidism (RIHT) is a common complication in nasopharyngeal carcinoma patients. Predicting its onset is crucial for effective management and early intervention. This study aims to develop a model based on deep learning survival analysis to predict RIHT in nasopharyngeal carcinoma patients. METHODS: This retrospective study included 535 nasopharyngeal carcinoma patients between January 2015 and October 2020. Cox regression, LASSO-Cox analyses and Spearman correlation test were employed to identify significant predictors. Two deep learning and two machine learning algorithms were trained, tuned, and compared against traditional Cox and NTCP models by C-index, Brier score, and decision curve analysis. RESULTS: The study observed a 41.7 % incidence of RIHT, with a median time to onset of 15 months. AJCC N stage, thyroid volume and specific dose-volume parameters were identified as potential predictors. DeepSurv model outperformed traditional ones (C-index: DeepSurv 0.75, traditional models ≤ 0.63). While other models were competitive at early post-treatment intervals, deep learning models demonstrated superior performance over time. Calibration and decision curve analysis corroborated the enhanced predictive capability of DeepSurv. Feature importance analysis highlighted thyroid V30 and V50 as the most significant predictors. CONCLUSIONS: DeepSurv demonstrated superior predictive performance for RIHT in nasopharyngeal carcinoma patients compared to traditional models. Deep learning-based predictions offer high accuracy, which may enable personalized patient management and have great potentials in mitigating the risk of RIHT. These findings suggested that incorporating such model into clinical practice could be beneficial for the management of RITH.
引用
- Mao Y, Ding M, Zong D, et al. Predicting radiation-induced hypothyroidism in nasopharyngeal carcinoma patients using a deep learning model. Clin Transl Radiat Oncol. 2025. PMID: 40144227. doi:10.1016/j.ctro.2025.100946
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。