Hello! My name is Samaneh Nemati, Sam for short, and I am a cognitive neuroscientisti with a background in biomedical engineering, with 10+ years of experience building data-driven models for biomedical images/signals, neuroimaging, and multimodal clinical research. My work sits at the intersection of biomedical engineering and neuroscience, where I use MRI, EEG, statistical modeling, and machine learning to turn complex brain data into interpretable biomarkers of brain health and behavior.

I came to the brain through math. As an undergraduate in biomedical engineering, I fell in love with imaginary numbers, strange and seemingly abstract objects that kept me up late working through textbooks. They finally made sense in a Signals and Systems class, when I realized they lived inside Fourier transforms, and Fourier transforms could turn the wiggling, chaotic lines of EEG into meaningful rhythms of neural activity. It felt like I found the tool to see the brain in a new way.

Today I am Director of the Data Science Core (HESTIA) at the University of South Carolina and a Research Associate in the Aphasia Lab. In these roles, I build reproducible data pipelines, curate multimodal datasets, and develop computational models for clinical and translational research. I help build the Brain Health Index, a composite biomarker framework that uses multimodal brain images, brain-age modeling, behavioral data, and machine learning to quantify how the brain is aging.

Other threads in my work include structural and functional MRI processing, EEG signal analysis, graph neural networks for brain connectivity, hearing loss and cognitive decline in healthy aging, and prediction of language recovery after stroke. Across these projects, I focus on the full data science workflow: data curation, preprocessing, feature extraction, model development, validation, visualization, and communication of results to both technical and non-technical collaborators.

The through-line across all of it is translating complex brain measurements into usable evidence: computational biomarkers, predictive models, and interpretable findings that can help scientists and clinicians understand what is happening in the brain and what may come next.

I'm passionate about applying this foundation in neural signal processing, clinical trails, and brain-behavior modeling to neurotechnology, BCI, and neurorehabilitation, where rigorous data science can help improve patients lives.