Predicting phenotypes of elderly from resting state fMRI.
Barbara Verovnik1, Stefan Hajduk2, Marc Van Hulle2
1University of Ljubljana.
Research Square
|August 23, 2023
Summary
Machine learning accurately classified healthy elderly individuals using brain functional connectivity. This approach identifies predictive brain networks and can be applied to various phenotypes for understanding brain aging.
Area of Science:
- Neuroimaging
- Neuroscience
- Machine Learning
Background:
- Machine learning is increasingly used in neuroimaging for predicting phenotypes and clinical outcomes.
- Functional connectome metrics can serve as biomarkers for healthy individuals and patients.
- Resting-state functional magnetic resonance imaging (rs-fMRI) is a key tool in brain studies.
Conclusions:
- Functional connectivity patterns from rs-fMRI can effectively classify phenotypes in healthy elderly.
- The identified predictive networks offer insights into brain aging mechanisms.
- The proposed classification pipeline is adaptable for broader applications in understanding brain health and disease.
