A connectivity-based biomarker for academic success
Project description
The search for an objective measure of learning abilities is an ongoing challenge in cognitive neuroscience. Previous studies have demonstrated that functional connectivity patterns, derived from functional magnetic resonance imaging (fMRI) scans, are predictive of general intelligence as well as specific cognitive traits. However, these examinations were mainly performed under laboratory-constrained settings. In this project, we aim to predict real-life academic performance of undergraduate students from pre-existing functional connectivity patterns. In a preliminary work, we utilized machine-learning (ML) models to predict university admission test scores from task-free functional connectivity. Our results show that real-life cognitive scores can be predicted from brain connectivity and that different connectivity networks support the prediction of different aspects of cognitive performance (e.g., verbal vs. mathematical abilities). Thus, connectivity patterns may point to individual tendencies to succeed in specific academic fields and serve as a non-invasive biomarker for academic performance.
About me
I am a PhD student at the Sagol School of Neuroscience, Tel Aviv University, under the supervision of Dr. Ido Tavor. I received my BSc in biology and psychology, with an emphasis on neuroscience, from Tel Aviv University in 2021. I’m interested in the neural basis of the inter-individual variability in cognitive abilities and learning capabilities. As part of my PhD research, we aim to predict real-life academic performance of undergraduate students from pre-existing brain connectivity patterns, derived from fMRI scans.