Sign in Subscribe
Machine learning

Machine Learning Model Predicts Survival in Metastatic Pancreatic Neuroendocrine Tumors

Strategic Insights

— 1 min read

Research conducted by Zhejiang Provincial People's Hospital has developed a machine learning-based survival prediction model using data from the Surveillance, Epidemiology, and End Results (SEER) database. This model incorporates ten key prognostic factors, including AJCC TNM stage, tumor grade, primary surgery, and age, to provide accurate survival predictions for patients with metastatic pancreatic neuroendocrine tumors (pNETs). The model, which achieved strong predictive performance with an area under the receiver operating characteristic curve (AUROC) of 0.781, 0.747, and 0.741 for 1-, 3-, and 5-year survival, respectively, has been implemented in a web-based application to support clinical decision-making and personalized treatment planning.

Key Takeaways:

  • The study developed a machine learning-based survival prediction model using data from the Surveillance, Epidemiology, and End Results (SEER) database.
  • The model incorporated ten key prognostic factors, including AJCC TNM stage, tumor grade, primary surgery, and age.
  • The XGBoost algorithm was applied to construct the model, which achieved strong predictive performance with an AUROC value of 0.781, 0.747, and 0.741 for 1-, 3-, and 5-year survival, respectively.
  • The model was implemented in a web-based application that delivers real-time, individualized survival estimates to support clinical decision-making and personalized treatment planning.
  • The model addresses a critical gap in prognostic tools for metastatic pNETs.
  • The study was led by Yuchen Zheng and included additional authors from Zhejiang Provincial People's Hospital.

Statistics:

  • 1430 patients were included in the study.
  • The AUROC values for 1-, 3-, and 5-year survival were 0.781, 0.747, and 0.741, respectively.
  • The model was constructed using the XGBoost algorithm.
  • The model was implemented in a web-based application to support clinical decision-making and personalized treatment planning.

Sources:

  • A clinically applicable machine learning model for personalized survival prediction in metastatic pancreatic neuroendocrine tumors. European Journal of Surgical Oncology, 2025;51(9):110222.
  • Elsevier Sci Ltd, 125 London Wall, London, England.
  • Zhejiang Provincial People's Hospital.
  • Yuchen Zheng, General Surgery, Cancer Center, Dept. of Hepatobiliary & Pancreatic Surgery and Minimally Invasive Surgery, Zhejiang Provincial People's Hospital.

Read more