Li Xuanzi, Yang Shuai, Peng Yingpeng, You Xueqiang, Peng Shunli, Wang Siyang, Zha Dasong, Zhang Shuyuan, Deng Chuntao
The Cancer Center, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guang dong Province, China.
Department of Radiotherapy of The Cancer Center, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guang dong Province, China.
Cancer Rep (Hoboken). 2025 Aug;8(8):e70303. doi: 10.1002/cnr2.70303.
Pineoblastomas (PBs) are rare central nervous system tumors primarily affecting children and adolescents, with limited data on clinical characteristics and survival outcomes. Prognosis prediction models for this disease are lacking. The purpose of this study was to develop deep learning (DL) models for predicting 3-year survival in patients with pineoblastoma.
Patients with pineoblastomas of all ages were identified from the Surveillance, Epidemiology, and End Results (SEER) database (1975-2019). Deep neural networks (DNN) were trained and tested at a ratio of 7:3 in a 5-fold cross-validated fashion. Multivariate CPH models were constructed for comparison. The primary outcomes were 3-year overall survival (OS) and disease-specific survival (DSS). All the variables were included in the analysis. Receiver operating characteristic (ROC) curve analysis and calibration plots were used to evaluate the model performance.
A total of 145 patients were included in this study. The area under the curve (AUC) for the DNN models was 0.92, 0.91, and 0.749 for OS and 0.76 for DSS. The DNN models exhibited good calibration: the OS model (slope = 0.94, intercept = 0.07) and DSS model (slope = 0.81, intercept = 0.20).
Our DNN models showed a more accurate prediction of survival outcomes in patients with pineoblastoma than the widely used CPH models. These results indicate the potential of DL algorithms to improve outcome prediction in patients with rare tumors.
松果体母细胞瘤（PBs）是一种罕见的中枢神经系统肿瘤，主要影响儿童和青少年，关于其临床特征和生存结果的数据有限。目前缺乏针对该疾病的预后预测模型。本研究的目的是开发深度学习（DL）模型，用于预测松果体母细胞瘤患者的3年生存率。
从监测、流行病学和最终结果（SEER）数据库（1975 - 2019年）中识别出所有年龄段的松果体母细胞瘤患者。深度神经网络（DNN）以7:3的比例进行训练和测试，并采用5折交叉验证的方式。构建多变量CPH模型进行比较。主要结局为3年总生存率（OS）和疾病特异性生存率（DSS）。所有变量均纳入分析。采用受试者工作特征（ROC）曲线分析和校准图来评估模型性能。
本研究共纳入145例患者。DNN模型的OS曲线下面积（AUC）分别为0.92、0.91和0.749，DSS的AUC为0.76。DNN模型表现出良好的校准：OS模型（斜率 = 0.94，截距 = 0.07）和DSS模型（斜率 = 0.81，截距 = 0.20）。
我们的DNN模型在预测松果体母细胞瘤患者的生存结果方面比广泛使用的CPH模型更准确。这些结果表明DL算法在改善罕见肿瘤患者结局预测方面的潜力。
