Development and Validation of Survival Prediction Models for Patients With Pineoblastomas Using Deep Learning: A SEER ‐Based Study
Cancer Reports · 2025
DOI: 10.1002/cnr2.70303 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Cancer Reports, 2025. Verfasst von Xuanzi Li und 8 weiteren Autor:innen. Beteiligte Einrichtung: The Cancer Center, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guang dong Province, China. Hauptthemen laut MEDLINE: Deep Learning, Pinealoma, Pineal Gland, Brain Neoplasms. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Basic and Applied Basic Research Foundation of Guangdong province.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- 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.
- School of Innovative Engineering, Macao University of Science and Technology, Macao, Macao Special Administrative Region, China.
ORCID-Profile: Chuntao Deng
Förderung
- Basic and Applied Basic Research Foundation of Guangdong province
Zitieren
APA
Li, X., Yang, S., Peng, Y., You, X., Peng, S., Wang, S., Zha, D., Zhang, S., & Deng, C. (2025). Development and Validation of Survival Prediction Models for Patients With Pineoblastomas Using Deep Learning: A SEER ‐Based Study. Cancer Reports. https://doi.org/10.1002/cnr2.70303
Vancouver
Li X, Yang S, Peng Y, You X, Peng S, Wang S, et al. Development and Validation of Survival Prediction Models for Patients With Pineoblastomas Using Deep Learning: A SEER ‐Based Study. Cancer Reports. 2025. doi:10.1002/cnr2.70303
BibTeX
@article{Li2025,
author = {Li, Xuanzi and Yang, Shuai and Peng, Yingpeng and You, Xueqiang and Peng, Shunli and Wang, Siyang and Zha, Dasong and Zhang, Shuyuan and Deng, Chuntao},
title = {Development and Validation of Survival Prediction Models for Patients With Pineoblastomas Using Deep Learning: A SEER ‐Based Study},
journal = {Cancer Reports},
year = {2025},
doi = {10.1002/cnr2.70303}
}
EUVIMED