Neil Voore
Elsevier
Journal Submission
9th Grade
Age at Publication
Medical AI
Research Domain
The Research
Neil tackled a critical problem in medical AI: the reliability of nail abnormality detection models. His paper, "Rethinking Evaluation in Nail Abnormality Detection: Dataset Leakage, External Generalization Failure, and ROI-Based Bias Mitigation," examines how standard evaluation protocols can inflate reported accuracy by failing to account for dataset-specific biases.
Key Findings
Standard random data splits allow leakage between training and test sets, leading to inflated performance metrics
Models achieving near-perfect accuracy under random splits show marked decline when evaluated across different data sources
Region-of-interest (ROI) based training that focuses on the nail plate improves external F1-score and reduces background bias
Evaluation design has a larger effect on reported performance than the choice of model architecture
Student Testimonial
"The best part of YRI Fellowship was the positive attitude of the mentors, as they guided me to finish my research paper. The YRI Fellowship fosters a positive and inclusive environment where participants feel respected and supported. I was encouraged to share ideas and collaborate, which helps build strong connections and teamwork skills. Mentors are approachable and provide guidance that boosts confidence and growth. Overall, the program creates a space where individuals can learn, improve, and succeed together."
-- Neil Voore, 9th Grade
Ready to Start Your Research Journey?
Join the YRI Fellowship and work with expert mentors to conduct original research, get published, and build a profile that stands out.
Apply Now