Department of radiation oncology, Fudan University Shanghai Cancer Center, Shanghai, China.
Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, China.
Radiat Oncol. 2019 Mar 12;14(1):42. doi: 10.1186/s13014-019-1250-z.
To develop and validate a quantitative complication model of temporal lobe necrosis (TLN). To analyze the effect of clinical and dosimetric factors on TLN.
In this study the prediction model was developed in a training cohort that consisted of 256 nasopharyngeal carcinoma (NPC) patients from January 2009 to December 2009. Dosimetric and clinical factors were extracted for model building. Dosimetric factors including the maximum dose, minimum dose, mean dose, dose covering specific volume and dose of percentage volume. Clinical factors include age, gender, T/N-stage, overall stage, diabetes and hypertension. LASSO (least absolute shrinkage and selection operator) regression model was used for feature selection, and prediction model building. A testing cohort containing 493 consecutive patients from January 2010 to December 2010 was used for model validation. The performance of the prediction model was assessed with respect to its calibration, discrimination.
The prediction model, which consisted of two dosimetric features (D0.5cc and D10), is significantly associated with LN status (P < .001 for both training and testing cohorts). None of clinical factors show direct prediction value. The model shows good discrimination, with a C-index of 0.685 (95% CI: 0.6048-0.765) on testing set, and a consistent trend in calibration on testing set.
This study presents a prediction model can be conveniently used to facilitate the individualized prediction of TLN in patients with NPC. Clinical factors have no direct impact on TLN.
开发和验证颞叶坏死（TLN）的定量并发症模型。分析临床和剂量学因素对 TLN 的影响。
本研究中的预测模型是在一个由 2009 年 1 月至 2009 年 12 月的 256 例鼻咽癌（NPC）患者组成的训练队列中开发的。提取了剂量学和临床因素以建立模型。剂量学因素包括最大剂量、最小剂量、平均剂量、特定体积覆盖率和百分比体积剂量。临床因素包括年龄、性别、T/N 期、总期、糖尿病和高血压。LASSO（最小绝对收缩和选择算子）回归模型用于特征选择和预测模型构建。一个包含 2010 年 1 月至 2010 年 12 月连续 493 例患者的测试队列用于模型验证。使用校准和判别来评估预测模型的性能。
由两个剂量学特征（D0.5cc 和 D10）组成的预测模型与 LN 状态显著相关（训练和测试队列均 P < 0.001）。临床因素均无直接预测价值。该模型显示出良好的判别能力，在测试集上的 C 指数为 0.685（95%CI：0.6048-0.765），测试集上的校准趋势一致。
本研究提出了一种预测模型，可以方便地用于预测 NPC 患者 TLN 的个体化。临床因素对 TLN 没有直接影响。
