Build the connectome
Converted signals from 200 brain regions into 19,900 unique pairwise connectivity features.
← Back to portfolio
Regeneron ISEF Finalist · Computational Biology
Machine Learning Approaches to Brain Connectivity in Autism
Using resting-state fMRI and interpretable machine learning, I investigated subtle autism-related patterns in functional brain connectivity, and the research-site effects that challenge real-world generalization.
Influential connections were distributed across brain networks rather than concentrated in one “autism region.”
Why I did this
The question began with someone close to me.
This project began with my younger brother, Mason. During my sophomore year, he experienced a profound regression, yet his clinical MRI showed no structural abnormality.
I began wondering what differences might exist not in the appearance of the brain, but in how its regions communicate. Resting-state fMRI offered a way to explore that question through functional connectivity, the synchronization of activity between brain regions while a person is at rest.
What I did
From brain signals to a rigorous multisite machine-learning test
I built a complete analysis pipeline using public, de-identified ABIDE neuroimaging data.
Explore the data
Used PCA and UMAP to examine whether patterns reflected diagnosis or research site.
Test generalization
Trained logistic-regression models and tested each one on an entirely unseen hospital or scanner site.
Challenge the result
Used permutation testing, confidence intervals, site-balanced analysis, and model interpretation to evaluate reliability.
What I found
The signal was real, but the limitations mattered just as much.
Subtle and distributed
Autism-related connectivity differences appeared across many brain-network interactions rather than in one isolated brain region.
Site effects were powerful
Scanner and research-site differences were substantially stronger than diagnosis effects, making strict multisite validation essential.
Above chance, not diagnostic
The model performed significantly above chance on unseen sites, but its accuracy was not sufficient for standalone clinical diagnosis.
Biologically meaningful network patterns
The most informative and reproducible connections were centered on interactions between limbic, attention, control, sensory-motor, and default-mode networks. These patterns are consistent with commonly reported autism-related differences in emotion regulation, sensory processing, and attentional shifting.
What I learned
A model’s accuracy is not enough. I learned to ask what information the model might be exploiting, whether the evaluation reflects the real setting, and how uncertainty should shape the claims I make.
Awards and recognition
Recognized at regional, state, and international levels
International
ISEF
Regeneron International Science and Engineering Fair
- ISEF Finalist
State
GSEF
Georgia Science & Engineering Fair
- Regeneron ISEF Award - Top 4
- Top Ten Grand Award
- Best in Category - Computational Biology & Bioinformatics
- First Honor Award
Special Award
Citadel Securities Innovation Prize
Recognized for Exceptional Data Analysis TechniquesRegional
Regional
Cobb-Paulding Regional Science Fair
- First Place Winner
Explore the project
Interested in the complete research?
The official ISEF page contains the full project presentation and results. The GitHub repository contains the analysis code, reproducibility materials, figures, and technical documentation.
Official Project Page
Regeneron ISEF
View complete project details ↗Source Code and Documentation
GitHub Repository
Explore the analysis pipeline ↗Machine LearningAutismResting-State fMRIFunctional ConnectivityComputational NeuroscienceMultisite GeneralizationInterpretable AI