Notes on digital healthcare policy, research papers and startup building.
The MIMIC-IV dataset is the quiet, unglamorous foundation behind both of my published papers. Both of my papers — the one on whether LLMs can safely explain radiology reports, and the follow-up on whether radiologists can actually catch it when they can’t — used the same underlying data source. I’ve referenced it in passing in…
Today I was at COEX for MEeT 2026 — something a little different from my usual beat. Not a trade show floor, but a conference specifically about the messy, unglamorous process of turning a clinical idea into an actual company. This was its first-ever run. I want to be upfront about why this one hit…
Radiologist oversight of AI errors is the exact question this study set out to quantify. My last post walked through my main study on whether LLMs can safely explain radiology reports to patients — and one of the more uncomfortable findings was the calibration deficit: the models’ most dangerous errors were the ones delivered with…
This one’s personal — it’s my own peer-reviewed research, published this year in Healthcare. I’ve spent most of this blog reviewing other people’s work and other people’s technology. This time I get to walk you through mine. Here’s where it actually started. Ordinary people are already asking AI chatbots questions about their own medical information…
KHF 2026 — the K-Hospital + HealthTech Fair — was held this week at COEX in Seoul, and I made a point of pre-registering and going. I studied digital healthcare myself, and I wanted to see with my own eyes where Korea’s medical health-tech industry actually stands right now, beyond the press releases. One honest…