A Novel Swarm Intelligence-Driven Feature Selection for Interpretable Machine Learning in Multiparametric MRI-Based GBM Overall Survival Analysis
Cancers, vol.18, no.12, 2026 (SCI-Expanded, Scopus)
- Publication Type: Article / Article
- Volume: 18 Issue: 12
- Publication Date: 2026
- Doi Number: 10.3390/cancers18121888
- Journal Name: Cancers
- Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, BIOSIS, Chemical Abstracts Core, CINAHL, EMBASE, Academic Search Ultimate (EBSCO), Natural Science Collection (ProQuest), Biological Science Database (ProQuest), Biomedical Reference Collection: Corporate Edition (EBSCO)
- Keywords: artificial intelligence, brain tumor, GBM, precision oncology, quantitative imaging biomarkers, radiomics, survival analysis
- Yıldız Technical University Affiliated: Yes
Abstract
Background/Objectives: In this study, we develop and validate an interpretable machine learning (ML) model that integrates a hybrid swarm intelligence (SI)-based feature selection method with multiparametric magnetic resonance imaging (MRI)-derived RFs to estimate overall survival (OS) in glioblastoma multiforme (GBM) patients. Methods: A cohort of 276 GBM patients with open-access pre-treatment MRI data was used to perform comprehensive radiomic analysis. In the training (discovery) dataset, we employed five-fold cross-validation combined with bootstrapping to ensure robust methodological validation. Model evaluation covered the concordance index (C-index) with 95% confidence intervals (CIs). Additionally, survival stratification was performed using Kaplan–Meier curves and the log-rank test to separate patients into low- and high-risk groups for OS. The final survival model integrates patient age and ten independent RFs. Results: The model’s performance in the holdout test dataset was evaluated by a C-index of 0.71 (95% CI: 0.63–0.80), exhibiting statistically significant risk stratification (p = 3 × 10−4). Upon external validation, the model achieved a C-index of 0.67, maintaining statistical significance (p = 1 × 10−2). Conclusions: The research combined a traditional regularized Cox regression (Cox-LASSO) model with a new SI-based LASSO-PSO method, yielding significant stratification. To our knowledge, the present study offers one of the first studies to document the use of an interpretable ML model with an SI-based approach for successful risk stratification based on OS.