Institute of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan; Department of Radiation Oncology, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan.
Department of Radiation Oncology, Chang Gung Memorial Hospital, Chang Gung University, Linkou, Taiwan.
Radiother Oncol. 2023 Dec;189:109911. doi: 10.1016/j.radonc.2023.109911. Epub 2023 Sep 12.
Radiation-induced hypothyroidism (RIHT) is a common but underestimated late effect in head and neck cancers. However, no consensus exists regarding risk prediction or dose constraints in RIHT. We aimed to develop a machine learning model for the accurate risk prediction of RIHT based on clinical and dose-volume features and to evaluate its performance internally and externally.
We retrospectively searched two institutions for patients aged >20 years treated with definitive radiotherapy for nasopharyngeal or oropharyngeal cancer, and extracted their clinical information and dose-volume features. One was designated the developmental cohort, the other as the external validation cohort. We compared the performances of machine learning models with those of published normal tissue complication probability (NTCP) models.
The developmental and external validation cohorts consisted of 378 and 49 patients, respectively. The estimated cumulative incidence rates of grade ≥1 hypothyroidism were 53.5% and 61.3% in the developmental and external validation cohorts, respectively. Machine learning models outperformed traditional NTCP models by having lower Brier scores at every time point and a lower integrated Brier score, while demonstrating a comparable calibration index and mean area under the curve. Even simplified machine learning models using only thyroid features performed better than did traditional NTCP algorithms. The machine learning models showed consistent performance between folds. The performance in a previously unseen external validation cohort was comparable to that of the cross-validation.
Our model outperformed traditional NTCP models, with additional capabilities of predicting the RIHT risk at individual time points. A simplified model using only thyroid dose-volume features still outperforms traditional NTCP models and can be incorporated into future treatment planning systems for biological optimization.
放射性甲状腺功能减退症（RIHT）是头颈部癌症中一种常见但被低估的晚期效应。然而，关于 RIHT 的风险预测或剂量限制尚无共识。我们旨在开发一种基于临床和剂量-体积特征的机器学习模型，用于 RIHT 的准确风险预测，并在内部和外部评估其性能。
我们回顾性地在两家机构中搜索了年龄>20 岁的接受根治性放疗的鼻咽癌或口咽癌患者，并提取了他们的临床信息和剂量-体积特征。其中一个被指定为发展队列，另一个为外部验证队列。我们比较了机器学习模型与已发表的正常组织并发症概率（NTCP）模型的性能。
发展队列和外部验证队列分别包含 378 例和 49 例患者。发育队列和外部验证队列的≥1 级甲状腺功能减退症累积发生率分别为 53.5%和 61.3%。机器学习模型通过在每个时间点具有更低的 Brier 分数和更低的综合 Brier 分数，优于传统的 NTCP 模型，同时表现出可比的校准指数和平均曲线下面积。即使使用仅甲状腺特征的简化机器学习模型也比传统的 NTCP 算法表现更好。机器学习模型在折叠之间表现出一致的性能。在以前未见过的外部验证队列中的性能与交叉验证相当。
我们的模型优于传统的 NTCP 模型，具有在各个时间点预测 RIHT 风险的额外能力。仅使用甲状腺剂量-体积特征的简化模型仍然优于传统的 NTCP 模型，可以纳入未来的治疗计划系统以进行生物学优化。
