• Sakhr Alshwayyat, Haya Kamal, Tala Abdulsalam Alshwayyat, Mustafa Alshwayyat, Mesk Alkhatib, and Ayah Erjan.
• King Hussein Cancer Center, Amman, Jordan; Princess Basma Teaching Hospital, Irbid, Jordan; Applied Science Research Center, Applied Science Private University, Amman, Jordan.
• World Neurosurg. 2024 Dec 31; 194: 123545123545.

ObjectiveIntracranial solitary fibrous tumor is a rare central nervous system tumor that lacks a reliable prognostic clinical model. Uncertainty persists regarding the treatment outcomes of surgery and adjuvant radiotherapy (ART). To address this, we investigated the efficacy of ART and applied machine learning (ML) to develop accurate prognostic models.MethodsThe Surveillance, Epidemiology, and End Results database was used for this study's analysis. To identify the prognostic variables, we conducted Cox regression analysis and constructed prognostic models using 5 ML algorithms to predict 5-year survival. A validation method incorporating the area under the curve of the receiver operating characteristic curve was used to validate the accuracy and reliability of the models. We investigated the role of ART and surgery using Kaplan-Meier survival analysis, competing risk analysis, and Bias Reduction through Analysis of Competing Events method.ResultsThe study population comprised 747 patients. Among them are 316 patients with "surgery" and 431 patients with "surgery + ART." The therapeutic groups showed significant differences in overall survival. Multivariate Cox regression analysis revealed that older age and surgery alone were poor prognostic factors. The most significant prognostic factors were the local tumor excision, followed by lobectomy and age.ConclusionsAlthough ART did not lead to a substantial decrease in cancer-specific deaths, it did improve overall survival. This underscores the broader health benefits of ART, including effective management of comorbid conditions. Caution is advised when interpreting these survival benefits because of potential confounding factors in patient health and treatment management. Our web tool and ML models aid in clinical decision-making.Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved.

6 keywords...

hide…