Machine learning model improves survival predictions for pancreatic neuroendocrine tumors

A novel machine learning model has been developed by researchers to predict survival in metastatic pancreatic neuroendocrine tumors (PNETs), a condition traditionally associated with poor prognosis. Utilizing data from 1430 patients, the model employed the extreme gradient boosting (XGBoost) algorithm and integrated ten prognostic factors. It demonstrated strong predictive accuracy, achieving area under the receiver operating characteristic curve (AUROC) values of 0.781, 0.747, and 0.741 for 1-, 3-, and 5-year survival rates, respectively.