Predicting survival in glioblastoma with multimodal neuroimaging and machine learning.
Patrick H LuckettMichael OlufawoBidhan LamichhaneKi Yun ParkDonna DierkerGabriel Trevino VerasteguiPeter YangAlbert H KimMilan G ChhedaAbraham Z SnyderJoshua S ShimonyEric C LeuthardtPublished in: Journal of neuro-oncology (2023)
We demonstrate that machine learning can accurately classify survival in GBM patients based on multimodal neuroimaging before any surgical or medical intervention. These results were achieved without information regarding presentation symptoms, treatments, postsurgical outcomes, or tumor genomic information. Our results suggest GBMs have a global effect on the brain's structural and functional organization, which is predictive of survival.
Keyphrases
- machine learning
- end stage renal disease
- free survival
- randomized controlled trial
- ejection fraction
- chronic kidney disease
- artificial intelligence
- healthcare
- pain management
- big data
- prognostic factors
- peritoneal dialysis
- type diabetes
- health information
- dna methylation
- white matter
- patient reported outcomes
- copy number
- adipose tissue
- multiple sclerosis
- chronic pain
- brain injury
- genome wide
- cerebral ischemia