Machine Learning-based Prognostic Subgrouping of Glioblastoma: A Multi-center Study
Recommended Citation
Akbari H, Bakas S, Sako C, Fathi Kazerooni A, Villanueva-Meyer J, Garcia JA, Mamourian E, Liu F, Cao Q, Shinohara RT, Baid U, Getka A, Pati S, Singh A, Calabrese E, Chang S, Rudie J, Sotiras A, LaMontagne P, Marcus DS, Milchenko M, Nazeri A, Balana C, Capellades J, Puig J, Badve C, Barnholtz-Sloan JS, Sloan AE, Vadmal V, Waite K, Ak M, Colen RR, Park YW, Ahn SS, Chang JH, Choi YS, Lee SK, Alexander GS, Ali AS, Dicker AP, Flanders AE, Liem S, Lombardo J, Shi W, Shukla G, Griffith B, Poisson LM, Rogers LR, Kotrotsou A, Booth TC, Jain R, Lee M, Mahajan A, Chakravarti A, Palmer JD, DiCostanzo D, Fathallah-Shaykh H, Cepeda S, Santonocito OS, Di Stefano AL, Wiestler B, Melhem ER, Woodworth GF, Tiwari P, Valdes P, Matsumoto Y, Otani Y, Imoto R, Aboian M, Koizumi S, Kurozumi K, Kawakatsu T, Alexander K, Satgunaseelan L, Rulseh AM, Bagley SJ, Bilello M, Binder ZA, Brem S, Desai AS, Lustig RA, Maloney E, Prior T, Amankulor N, Nasrallah MLP, O'Rourke DM, Mohan S, and Davatzikos C. Machine Learning-based Prognostic Subgrouping of Glioblastoma: A Multi-center Study. Neuro Oncol 2024.
Document Type
Article
Publication Date
12-12-2024
Publication Title
Neuro Oncol
Abstract
BACKGROUND: Glioblastoma is the most aggressive adult primary brain cancer, characterized by significant heterogeneity, posing challenges for patient management, treatment planning, and clinical trial stratification.
METHODS: We developed a highly reproducible, personalized prognostication and clinical subgrouping system using machine learning (ML) on routine clinical data, MRI, and molecular measures from 2,838 demographically diverse patients across 22 institutions and 3 continents. Patients were stratified into favorable, intermediate, and poor prognostic subgroups (I, II, III) using Kaplan-Meier analysis (Cox proportional model and hazard ratios [HR]).
RESULTS: The ML model stratified patients into distinct prognostic subgroups with HRs between subgroups I-II and I-III of 1.62 (95%CI: 1.43-1.84, p<0.001) and 3.48 (95%CI: 2.94-4.11, p<0.001), respectively. Analysis of imaging features revealed several tumor properties contributing unique prognostic value, supporting the feasibility of a generalizable prognostic classification system in a diverse cohort.
CONCLUSIONS: Our ML model demonstrates extensive reproducibility and online accessibility, utilizing routine imaging data rather than complex imaging protocols. This platform offers a unique approach for personalized patient management and clinical trial stratification in glioblastoma.
PubMed ID
39665363
ePublication
ePub ahead of print
