biostudies-literatureAkbari HBLRD VANational Cancer InstituteNCI NIH HHSNational Institutes of HealthNIH HHS1102-1115https://www.ebi.ac.uk/biostudies/studies/S-EPMC12083074biostudies-literatureUnknown27(4)<h4>Background</h4>Glioblastoma (GBM) is the most aggressive adult primary brain cancer, characterized by significant heterogeneity, posing challenges for patient management, treatment planning, and clinical trial stratification.<h4>Methods</h4>We developed a highly reproducible, personalized prognostication, and clinical subgrouping system using machine learning (ML) on routine clinical data, magnetic resonance imaging (MRI), and molecular measures from 2838 demographically diverse patients across 22 institutions and 3 continents. Patients were stratified into favorable, intermediate, and poor prognostic subgroups (I, II, and III) using Kaplan-Meier analysis (Cox proportional model and hazard ratios [HR]).<h4>Results</h4>The ML model stratified patients into distinct prognostic subgroups Neuro-oncologyMachine learning-based prognostic subgrouping of glioblastoma: A multicenter study.PMC12083074R01CA269948I01 BX005842U24CA189523U24 CA189523R01 CA269948R01 CA264017R01 CA277728U01CA242871U01 CA242871Park YWSatgunaseelan LAkbari HVadmal VFathallah-Shaykh HShi WDi Stefano ALLaMontagne PMarcus DSDesai ASDavatzikos CMahajan ABagley SJMohan SAli ASNazeri AKotrotsou AVillanueva-Meyer JJain RBakas SBilello MTiwari PPrior TShinohara RTNasrallah MPReSPOND consortiumBarnholtz-Sloan JSRulseh AMRogers LRSotiras AChang JHSloan AEBalana CMelhem EROtani YGriffith BValdes PChoi YSDicker APKurozumi KRudie JMaloney EGarcia JACepeda SLee MBaid UPuig JWoodworth GFAlexander GSAlexander KAhn SSWaite KAboian MSako CBrem SLiem SKoizumi SShukla GImoto RLee SKChakravarti APalmer JDBooth TCGetka ALombardo JAk MBinder ZAPati SSingh AMatsumoto YChang SPoisson LMBadve CCapellades JMilchenko MDiCostanzo DMamourian ECalabrese ESantonocito OSLustig RAAmankulor NColen RRFlanders AEO'Rourke DMWiestler BKawakatsu TLiu FFathi Kazerooni ACao QfalseMachine learning-based prognostic subgrouping of glioblastoma: A multicenter study.<h4>Background</h4>Glioblastoma (GBM) is the most aggressive adult primary brain cancer, characterized by significant heterogeneity, posing challenges for patient management, treatment planning, and clinical trial stratification.<h4>Methods</h4>We developed a highly reproducible, personalized prognostication, and clinical subgrouping system using machine learning (ML) on routine clinical data, magnetic resonance imaging (MRI), and molecular measures from 2838 demographically diverse patients across 22 institutions and 3 continents. Patients were stratified into favorable, intermediate, and poor prognostic subgroups (I, II, and III) using Kaplan-Meier analysis (Cox proportional model and hazard ratios [HR]).<h4>Results</h4>The ML model stratified patients into distinct prognostic subgroups 2025-01-01T00:00:00Z2025 May2026-06-10T05:17:54.618Z2026-06-10T03:07:29.411ZS-EPMC120830743966536310.1093/neuonc/noae260