ARCeH Externship via Extern
I'm a biology student harnessing data and AI to improve healthcare outcomes and decision-making. Let's connect!
From AI-powered document processing to healthcare data exploration, my portfolio showcases projects that highlight my skills in analytics and technology.
.jpg)
Pfizer · Apr 2026 · ✅ Verified by Extern
Prototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.
.jpeg)
TruBridge · Aug 2026 · ✅ Verified by Extern
A TruBridge externship focused on applying data analytics and AI to public healthcare datasets, with an emphasis on infection tracking, outcomes, and trend analysis.
I'm a biology student harnessing data and AI to improve healthcare outcomes and decision-making. Let's connect!
I'm a senior at the University of Memphis pursuing a Bachelor's Degree in Biology. With hands-on experience in data analytics and AI applications in healthcare, I'm eager to enhance my resume and build a competitive edge for my career.
Externships
Data Analytics, Health Outcomes Externship with ARCeH
In progress
Skills
✅ Verified by Extern
Prototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.
The work built and evaluated an end-to-end document intelligence prototype for pharmaceutical supplier files. It combined text and image extraction, layout-aware OCR comparisons, Python-based parsing, and retrieval-augmented generation experiments. Deliverables included extraction scripts, OCR evaluations, a Gradio chat demo, and retrieval accuracy reports.
I delivered a complete local document intelligence pipeline: text and image preprocessing, field extraction from multi-page SDFs, an OCR engine comparison favoring PaddleOCR, optimized RAG configurations, blob-splitting and classification, and a Gradio RAG chatbot with supporting documentation and Colab tests.
✅ Verified by Extern
A TruBridge externship focused on applying data analytics and AI to public healthcare datasets, with an emphasis on infection tracking, outcomes, and trend analysis.
The work investigated links between socioeconomic status and cancer outcomes by surveying public-health repositories and selecting the CDC U.S. Cancer Statistics Public Use Database alongside county-level Social Vulnerability Index data. The project downloaded and preprocessed those datasets and used Python in Google Colab to clean, visualize, and explore county-level SVI indicators, producing
I selected and documented the CDC U.S. Cancer Statistics Public Use Database and county-level SVI sources, downloaded and preprocessed those datasets, and produced EDA visuals—histograms, box plots, and a correlation heatmap—that showed positive correlations among poverty, unemployment, and related measures.
✅ Verified by Extern · ⏱️ In progress
Here’s what the data says: put a pin in Bangkok. Draw a five-hour flight radius around it. You just circled half the world's population. And half of those people are kids under five, an age where survival itself isn't guaranteed. Five isn't an arbitrary number: it's the line researchers use as a proxy for a country's overall health, because almost every preventable childhood death, driven by a bad water source, poor air quality, or an infection nobody caught in time, happens before it. Clear five, and the odds of reaching adulthood jump astronomically. Don't, and the cause almost always traces back to poverty, healthcare access, environmental risk, or nutrition, something that could have been mapped, measured, and prevented in time. That's the gap this externship exists to close: turning scattered, messy public data into a specific, defensible answer about what's actually driving that risk in a given place, and pass it to the people at ARCeH who want to know about it.
The externship used public health and environmental data to measure drivers of under-five mortality across regions in and around Southeast Asia. The work surveyed data sources, defined suitable analytical approaches, and produced an analysis plan mapping variables to outcomes. The project produced a documented framework for correlational analysis and data limitations.
I located and prepared county-level exposure and health records, applied a six-point fitness checklist to candidate datasets, and produced a documented county-year merge (5-digit FIPS plus Year) ready for correlational analysis.
The project began with a county‑level research question and required finding compatible exposure and health data. I located CDC pediatric asthma ER rates and EPA annual PM2.5 county summaries, applied a six‑point fitness checklist, and confirmed a clean county‑year merge (5‑digit FIPS + Year) with…
I summarized both Path B files, documented that one row equals a county-year, recorded 3,142 rows and 12 columns in the primary file, identified 5-digit FIPS and calendar year as join keys, and specified preprocessing (filter Tennessee, handle suppressed low counts, aggregate PM2.5 to county-year)…
