Erin Rose

I build tools that turn public health data into numbers people can use. I founded CareCost Estimate, which turns the huge price files hospitals and insurers must publish into prices you can look up. Verified Supplement Data does the same for supplements: it reads the labels, testing lists and studies most people never see, and turns them into numbers you can check.

What I am, and what I am not

I am not a doctor, dietitian or pharmacist, and nothing on this site is medical advice. I am a data engineer. So the site is built so you do not have to take my word for anything:

• Clinical claims link to their source, usually a PubMed ID.
• Product data comes from the NIH Dietary Supplement Label Database and the product’s own label.
• Who is low in a nutrient comes from CDC NHANES blood test data.
• The math, such as cost per studied dose, is shown on the page.
• When we get something wrong, it goes on the public corrections log.

How pages are made, including how we use software and AI tools: who writes and checks our pages.

Work you can check

The dataset behind this site is published openly, under my name:

• Figshare (DOI): 10.6084/m9.figshare.32917331, the Verified Supplement Evidence dataset, CC BY 4.0
• Hugging Face (DOI): 10.57967/hf/9356, a mirror of the dataset
• Kaggle: verified-supplement-evidence-database
• GitHub: erinheit451/verified-supplement-evidence, open CSV files, CC BY 4.0

I also publish supplement-advisor-mcp, an open-source tool that lets AI assistants look up this data.

Why I built this

Supplement labels are hard to compare. The front of a bottle often shows the weight of a compound, not the amount your body gets. Prices for the same dose can differ by 10 times. And the research sits in journals most people never read. All of the data needed to sort this out is free and public. It just needs to be put together.

Questions, or found a mistake? Email hello@verifiedsupplementdata.com. Fixes are logged publicly.