Open to opportunities

Aidan Colvin

@aidancolvin

Message

Aspiring machine learning engineer applying biomedical informatics to improve healthcare decisions.

Zimbabwe

Message

What I'm looking for

I’m looking to apply biomedical ML and data engineering to real healthcare problems—building reliable pipelines, deploying NLP models, and measuring impact with strong metrics—while collaborating with teams that value reproducible research and thoughtful model evaluation.

I’m a biomedical and health informatics graduate student building machine learning solutions that turn messy clinical data into actionable insights. As a Research Assistant with the NC Dept. of Health and Human Services, I analyzed gambling addiction trends in helpline datasets and built custom cleaning logic to improve reporting accuracy for state health policy.

In my lab and practicum work, I’ve combined strict research methodology with practical engineering—running IRB-guided survey research (N=79) and shipping pipelines for leadership-ready outputs. My projects range from engineering regex ETL pipelines and automated NLP keyword extraction to training supervised models that achieved strong performance (e.g., ROC AUC 0.9538), as well as deploying a containerized DistilBERT model via FastAPI for clinical entity extraction.

Experience

Work history, roles, and key accomplishments

Research Data Engineer

UNC Health

Aug 2025 - Dec 2025 (4 months)

Engineered regex-based ETL pipelines to categorize and analyze MD-reported clinical friction points. Produced real-time summary statistics for leadership using automated NLP keyword extraction.

ETL Regex Data Engineering Real Time Analytics Data Aggregation Python

Research Data Engineer

UNC Health GROSS Program

Aug 2025 - Dec 2025 (4 months)

Engineered regex-based ETL pipelines to categorize and analyze MD-reported clinical friction points. Produced real-time summary statistics for leadership using automated NLP keyword extraction.

ETL Regex Real Time Analytics Data Engineering

Research Assistant

NC Dept. of Health and Human Services

May 2020 - Dec 2022 (2 years 7 months)

Analyzed gambling addiction trends in helpline datasets to support state health policy. Normalized raw datasets with custom cleaning logic to improve reporting accuracy.

Trend Analysis Data Analysis Data Cleaning Data Normalization Helpline Data Processing

Research Assistant

North Carolina Department of Health and Human Services

May 2020 - Dec 2022 (2 years 7 months)

Analyzed gambling addiction trends in helpline datasets to inform state health policy. Normalized raw datasets with custom cleaning logic to improve reporting accuracy.

Data Analysis Trend Analysis Data Cleaning Data Normalization Python SQL SPSS Data Mining Policy Research

Honors Thesis Researcher

University Of North Carolina at Chapel Hill

May 2021 - May 2022 (1 year)

Conducted an IRB-approved clinical survey (N=79) following formal study protocols and defense requirements. Managed data collection and statistical analysis to evaluate behavioral health trends in the NC population.

Data Collection Statistical Analysis SPSS Data Management

Honors Thesis Researcher

UNC Chapel Hill Anxiety Lab

May 2021 - May 2022 (1 year)

Conducted an IRB-approved clinical survey (N=79) to evaluate behavioral health trends in the North Carolina population. Managed data collection and statistical analysis through formal thesis defense.

Data Collection Statistical Analysis Data Management

Education

Degrees, certifications, and relevant coursework

University of North Carolina at Chapel Hill

Master of Professional Studies, Biomedical and Health Informatics

Pursuing an M.P.S. in Biomedical and Health Informatics at UNC Chapel Hill, expected to complete in May 2027. Coursework includes Data Mining, Machine Learning, and Programming for Information Science.

University of North Carolina at Chapel Hill

M.P.S., Biomedical and Health Informatics

Pursuing an M.P.S. in Biomedical and Health Informatics at UNC Chapel Hill, expected to complete May 2027. Relevant coursework includes Data Mining, Machine Learning, and Programming for Information Science.