# Phenotypic stratification of Low-grade Glioma using multimodal MRI via outcome-weighted integrative clustering

## TL;DR

This study uses MRI data to identify two subtypes of low-grade glioma, which differ in survival and biological features, helping improve clinical decisions.

## Contribution

A novel outcome-weighted clustering method (survClust) is applied to MRI data for phenotypic stratification of LGG.

## Key findings

- Two LGG subtypes were identified and validated across two cohorts with distinct survival outcomes and biomarker profiles.
- The GA-fKPLS model outperformed other models in predicting IDH and MGMT status with an AUC of 0.809.
- Subtypes showed differences in immune infiltration and pathway activities like JAK-STAT and p53.

## Abstract

Low-grade glioma (LGG) is a diverse group of primary brain tumors, whose molecular heterogeneity hinders classification by traditional pathological methods. Accurate phenotypic subtyping of LGG is essential for capturing tumor characteristics and optimizing clinical management. We intend to identify LGG phenotypic subtypes based on multimodal magnetic resonance imaging (MRI) data, enhancing prognosis evaluation and optimizing treatment strategy.

This was a retrospective multicenter study, and data were drawn from the First Hospital of Shanxi Medical University (FHSXMU) and Shanxi Provincial People’s Hospital (SPPH) (FHSXMU/SPPH cohort, n = 162), and The Cancer Genome Atlas (TCGA)/The Cancer Imaging Archive (TCIA) (TCGA/TCIA cohort, n = 118). In the FHSXMU/SPPH cohort, LGG phenotypic subtypes were identified using the outcome-weighted integrative clustering method (survClust) based on multimodal MRI data (CE-T1 and T2FLAIR). A multivariate Cox proportional hazards model was applied to evaluate survival differences between subtypes. Statistical comparisons between subtypes were performed, and the statistically significant MRI features were utilized to predict clinically relevant biomarkers – isocitrate dehydrogenase (IDH) mutation combined with O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation. Five models were constructed, including fused kernel partial least squares with the genetic algorithm (GA-fKPLS), logistic regression, random forest, support vector machine, and k-nearest neighbor. In the TCGA/TCIA cohort, we validated the identified phenotypic subtypes and further explored their biological characteristics by analyzing pathway activity and immune infiltration levels using mRNA expression data.

Two distinct LGG phenotypic subtypes were identified in the FHSXMU/SPPH cohort, and validated in the TCGA/TCIA cohort. In the FHSXMU/SPPH cohort, significant differences in pathological grade, MGMT promoter status, IDH genotype, survival status, tumor volume, and survival outcome (HR: 2.553, 95%CI: [1.226–5.315]) between the two subtypes (P < 0.05). Compared to other four models, the GA-fKPLS model exhibited superior predictive performance (AUC: 0.809). In the TCGA/TCIA cohort, two LGG phenotypic subtypes showed significant differences in pathway activities (JAK-STAT, TNF-α, p53) and immune cell infiltration (M2 macrophages, T cell regulatory, Monocytes) (Padj < 0.05).

This study identified two LGG phenotypic subtypes and potential biomarkers, offering supplementary information for clinical evaluation and treatment decision-making.

The online version contains supplementary material available at 10.1186/s12883-025-04420-0.