Institute for Artificial Intelligence in Medicine

@iaim-nu.bsky.social

The mission of I.AIM is to bridge computational methods with human expertise to advance medical science and improve human health. https://ow.ly/RAFj50UmErR

1/ What started as a “hey, wouldn’t it be cool…” 💡 side project turned into a full study on how to identify immunocompromised patients. Gold standard = research coordinators manually labeling statuses ✅
Everything else tested against that.
🔗 academic.oup.com/jamia/advanc...

Large language models accurately identify immunosuppression in intensive care unit patients

AbstractObjective. Rule-based structured data algorithms and natural language processing (NLP) approaches applied to unstructured clinical notes have limit

academic.oup.com

AI in women’s health has huge potential—helping spot cycle changes, support fertility, & expand access. To truly deliver, apps must be transparent, inclusive, & protect privacy. With smart design + oversight, AI can move from hype to real health impact. ow.ly/XQA350X0UuM

Improving Oversight Of Reproductive Health Apps That Use AI | Health Affairs Forefront

Artificial intelligence governance in reproductive health needs better tools and stronger norms.

ow.ly

Awesome work from @vijeethg.bsky.social - LLMs for the win! Hopefully this is one step towards doing less chart review. #LLMs #GPT @iaim-nu.bsky.social @nufeinbergmed.bsky.social @nuintmed.bsky.social #HBMI #HSIP

Vijeeth Guggilla@vijeethg.bsky.social · 11mo ago

#LLMs outperformed structured data algorithms and natural language processing in identifying various types of immunosuppression in ICU patients. Read more about our approach here: doi.org/10.1093/jami...; ft. @keyboardbiologist.bsky.social @catgaohow.bsky.social