Development and Validation of Survival Prediction Models for Patients With Pineoblastomas Using Deep Learning: A SEER‐Based Study

ABSTRACT Purpose 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 lear...

Full description

Saved in:
Bibliographic Details
Main Authors: Xuanzi Li, Shuai Yang, Yingpeng Peng, Xueqiang You, Shunli Peng, Siyang Wang, Dasong Zha, Shuyuan Zhang, Chuntao Deng
Format: Article
Language:English
Published: Wiley 2025-08-01
Series:Cancer Reports
Subjects:
Online Access:https://doi.org/10.1002/cnr2.70303
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849222379356553216
author Xuanzi Li
Shuai Yang
Yingpeng Peng
Xueqiang You
Shunli Peng
Siyang Wang
Dasong Zha
Shuyuan Zhang
Chuntao Deng
author_facet Xuanzi Li
Shuai Yang
Yingpeng Peng
Xueqiang You
Shunli Peng
Siyang Wang
Dasong Zha
Shuyuan Zhang
Chuntao Deng
author_sort Xuanzi Li
collection DOAJ
description ABSTRACT Purpose 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. Methods 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. Results 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). Conclusion 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.
format Article
id doaj-art-5b1dbb79d72f4a50b0fcddce5845212c
institution Kabale University
issn 2573-8348
language English
publishDate 2025-08-01
publisher Wiley
record_format Article
series Cancer Reports
spelling doaj-art-5b1dbb79d72f4a50b0fcddce5845212c2025-08-26T06:00:41ZengWileyCancer Reports2573-83482025-08-0188n/an/a10.1002/cnr2.70303Development and Validation of Survival Prediction Models for Patients With Pineoblastomas Using Deep Learning: A SEER‐Based StudyXuanzi Li0Shuai Yang1Yingpeng Peng2Xueqiang You3Shunli Peng4Siyang Wang5Dasong Zha6Shuyuan Zhang7Chuntao Deng8The Cancer Center The Fifth Affiliated Hospital of Sun Yat‐sen University Zhuhai Guang dong Province ChinaDepartment of Radiotherapy of The Cancer Center The Fifth Affiliated Hospital of Sun Yat‐sen University Zhuhai Guang dong Province ChinaThe Cancer Center The Fifth Affiliated Hospital of Sun Yat‐sen University Zhuhai Guang dong Province ChinaSchool of Innovative Engineering Macao University of Science and Technology Macao Macao Special Administrative Region ChinaThe Cancer Center The Fifth Affiliated Hospital of Sun Yat‐sen University Zhuhai Guang dong Province ChinaThe Cancer Center The Fifth Affiliated Hospital of Sun Yat‐sen University Zhuhai Guang dong Province ChinaThe Cancer Center The Fifth Affiliated Hospital of Sun Yat‐sen University Zhuhai Guang dong Province ChinaThe Cancer Center The Fifth Affiliated Hospital of Sun Yat‐sen University Zhuhai Guang dong Province ChinaDepartment of Radiotherapy of The Cancer Center The Fifth Affiliated Hospital of Sun Yat‐sen University Zhuhai Guang dong Province ChinaABSTRACT Purpose 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. Methods 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. Results 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). Conclusion 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.https://doi.org/10.1002/cnr2.70303artificial intelligencedeep learningmachine learningpineoblastomaSEER
spellingShingle Xuanzi Li
Shuai Yang
Yingpeng Peng
Xueqiang You
Shunli Peng
Siyang Wang
Dasong Zha
Shuyuan Zhang
Chuntao Deng
Development and Validation of Survival Prediction Models for Patients With Pineoblastomas Using Deep Learning: A SEER‐Based Study
Cancer Reports
artificial intelligence
deep learning
machine learning
pineoblastoma
SEER
title Development and Validation of Survival Prediction Models for Patients With Pineoblastomas Using Deep Learning: A SEER‐Based Study
title_full Development and Validation of Survival Prediction Models for Patients With Pineoblastomas Using Deep Learning: A SEER‐Based Study
title_fullStr Development and Validation of Survival Prediction Models for Patients With Pineoblastomas Using Deep Learning: A SEER‐Based Study
title_full_unstemmed Development and Validation of Survival Prediction Models for Patients With Pineoblastomas Using Deep Learning: A SEER‐Based Study
title_short Development and Validation of Survival Prediction Models for Patients With Pineoblastomas Using Deep Learning: A SEER‐Based Study
title_sort development and validation of survival prediction models for patients with pineoblastomas using deep learning a seer based study
topic artificial intelligence
deep learning
machine learning
pineoblastoma
SEER
url https://doi.org/10.1002/cnr2.70303
work_keys_str_mv AT xuanzili developmentandvalidationofsurvivalpredictionmodelsforpatientswithpineoblastomasusingdeeplearningaseerbasedstudy
AT shuaiyang developmentandvalidationofsurvivalpredictionmodelsforpatientswithpineoblastomasusingdeeplearningaseerbasedstudy
AT yingpengpeng developmentandvalidationofsurvivalpredictionmodelsforpatientswithpineoblastomasusingdeeplearningaseerbasedstudy
AT xueqiangyou developmentandvalidationofsurvivalpredictionmodelsforpatientswithpineoblastomasusingdeeplearningaseerbasedstudy
AT shunlipeng developmentandvalidationofsurvivalpredictionmodelsforpatientswithpineoblastomasusingdeeplearningaseerbasedstudy
AT siyangwang developmentandvalidationofsurvivalpredictionmodelsforpatientswithpineoblastomasusingdeeplearningaseerbasedstudy
AT dasongzha developmentandvalidationofsurvivalpredictionmodelsforpatientswithpineoblastomasusingdeeplearningaseerbasedstudy
AT shuyuanzhang developmentandvalidationofsurvivalpredictionmodelsforpatientswithpineoblastomasusingdeeplearningaseerbasedstudy
AT chuntaodeng developmentandvalidationofsurvivalpredictionmodelsforpatientswithpineoblastomasusingdeeplearningaseerbasedstudy