Machine learning for dermatologic lesion classification
Building an image-classification workflow with deidentified ISIC data, patient-level splitting, reproducible preprocessing, and model evaluation designed for clinically honest interpretation.
Working at the intersection of medicine, data, and service—with a focus on translating new technology into better, more human patient care.
Explore selected work ↓I’m a medical student at Kansas City University with interests in dermatology, oncology, and technology-enabled research. My work is grounded in a simple question: how can we use better tools without losing sight of the person in front of us?
From clinical dermatology to machine-learning projects, I’m most energized by work that connects careful analysis with meaningful patient outcomes.
Research and technical projects focused on clinically useful questions, reproducible methods, and clear communication.
Building an image-classification workflow with deidentified ISIC data, patient-level splitting, reproducible preprocessing, and model evaluation designed for clinically honest interpretation.
A multimodal health concept using transfer learning and classical machine learning to explore cancer-image classification and cardiovascular risk.
Computational work in Drosophila genetics, ortholog discovery, and transposable-element analysis.
Medical training with growing focus in dermatology, oncology, research, and student service.
Supported patient intake, documentation, procedures, care coordination, and access to treatment.
Hands-on experience in computational biology and genetics, paired with an undergraduate foundation in technical problem-solving.
Work centered on access, resource navigation, teamwork, and showing up for people when systems feel difficult to navigate.
I’m continuing to build at the edge of clinical medicine and research—especially where oncology, dermatology, and emerging technology overlap.