Research & AI
My graduate direction sits at the intersection of computer science, artificial intelligence, biostatistics, data quality, accessibility, and public health.
Research direction
I am interested in systems that are technically useful, transparent about uncertainty, attentive to data quality, and designed around the people affected by their outputs. My media and communication background adds a practical emphasis on accessibility and translating technical findings clearly.
Selected research threads
Revised a PHED 1304 research project into a reproducible descriptive analysis of CDC/NCHS surveillance estimates across total, age, and race/Hispanic-origin groupings.
Research value: demonstrates target-leakage detection, time-window awareness, suppression handling, transparent AI assistance, and responsible interpretation.
Read case studyDeveloped an operational Python desktop workflow that combines reviewed intake records, structured IPTC/XMP metadata, vision-assisted accessibility drafts, and controlled-vocabulary review in institutional media post-production.
Research value: demonstrates a human-in-the-loop design in which AI assists, deterministic automation handles repeatable work, humans retain authority, outputs remain auditable, and institutional data stays protected.
Read case studyProfessional experience with cross-system reconciliation, exception handling, and quality controls reinforces an interest in reliable AI and data operations.
Research value: automated checks are useful only when their assumptions, failure states, and escalation paths are understood.
View experienceBuilt a Python and ArcGIS workflow that transforms incomplete nonprofit partner records into mapping-ready spatial data.
Research value: connects data engineering and spatial analysis with future questions about service access and geographic disparities.
Read case studyTechnical preparation
