IMG-147. State-of-the-Art AI Techniques for Magnetic Resonance Spectroscopy in Differentiating High-Grade from Low-Grade Gliomas: A Diagnostic Test Accuracy Meta-Analysis
Abstract
Magnetic Resonance Spectroscopy (MRS) plays a pivotal role in the non-invasive evaluation of brain tissue by enabling the detection of metabolic biomarkers associated with tumor type and aggressiveness. Metabolic profiling through MRS is particularly valuable for distinguishing between low-grade and high-grade gliomas, thereby improving diagnostic accuracy, informing treatment decisions, and supporting therapy monitoring. This study investigates the use of artificial intelligence (AI)-based approaches applied to MRS data for predicting glioma grade. A comprehensive literature search was conducted in PubMed, EMBASE, and Web of Science from their inception through May 2025 to identify studies utilizing machine learning algorithms with MRS to classify gliomas as low-grade or high-grade, according to WHO criteria. Statistical analyses were performed using R version 4.3.3 with the ‘mada’ package. The quality of the included studies was assessed using the QUADAS-2 tool for diagnostic accuracy studies. Out of 554 studies screened, 5 studies met the inclusion criteria, encompassing a total of 482 participants, with 263 diagnosed as high-grade and 219 as low-grade gliomas. The pooled sensitivity and specificity were found to be 89% (95% CI: 79% - 95%, I² = 42%) and 90% (95% CI: 86% - 94%, I² = 0%), respectively. The positive and negative likelihood ratios were calculated at 7.05 (95% CI: 3.7 - 13.6, I² = 0%) and 0.15 (95% CI: 0.08 - 0.30, I² = 23%), respectively. The analysis yielded…
How strong is the evidence?
Evidence Hub reads this as a meta-analysis, done in people. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid. Reported size: 482 participants or records.
Read the paper
Related studies
- Global, regional, and national burden of hepatitis B, 1990–2019: a systematic analysis for the Global Burden of Disease Study 2019
- A meta‐analysis of anal cancer incidence by risk group: Toward a unified anal cancer risk scale
- Global fertility in 204 countries and territories, 1950–2021, with forecasts to 2100: a comprehensive demographic analysis for the Global Burden of Disease Study 2021
- Exercise interventions in Alzheimer's disease: A systematic review and meta-analysis of randomized controlled trials
- Prognostic Significance of Carbonic Anhydrase IX Expression in Cancer Patients: A Meta-Analysis
- Glucocorticoid Resistance: Is It a Requisite for Increased Cytokine Production in Depression? A Systematic Review and Meta-Analysis
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.