Published work, one book, and the research questions I keep coming back to.
I am less interested in publication volume than in whether the work points at something operationally real. The throughline here is the same as everywhere else on the site: better tools, tighter evaluation, and less tolerance for polished nonsense.
Published work has mostly come out of practical clinical problems rather than a separate academic track.
American Journal of Emergency Medicine · 2021
Technical publication related to lens-clearing laryngoscopy. PMID: 33632548.
This came out of a practical device problem, not an abstract research interest. It sits closer to deployment than theory, which is usually where I am most interested anyway.
The same bias applies here. I would rather make something compact and usable than something that looks impressive on a shelf.
Independently published · 2020
Pocket reference guide for emergency medicine ultrasound.
I like compact tools that are actually useful on shift. This was built in that spirit: practical, quick, and meant to be used rather than admired.
Most of my current work is on a narrow set of problems: how to evaluate clinical AI honestly, how to preserve physician oversight, and how to build support systems that stay useful when the workflow gets messy.
Current Stanford MCiM work focused on evaluation, physician oversight, and practical deployment of clinical decision support systems.
Stanford practicum work using clinical conversation data for structured differential support and workup recommendations.