iiinova — where your digital self keeps evolving

Gary Weissman

@gweissman.bsky.social

181 followers 300 following 0 posts

ICU Doc, Assistant Professor of Medicine and Informatics, Palliative and Advanced Illness Research (PAIR) Center, UPenn. Clinical informatics, AI, ML, clinical decision support, health policy.

Posts Replies Media

Reposted by Gary Weissman

Richard Riley (R²) @richarddriley.bsky.social · 07/05/2026

⭐ Now published: trilogy of articles proposing how to calculate the sample size for building a prediction model that targets precise & fair predictions at individual level. part 1: binary outcomes - pubmed.ncbi.nlm.nih.gov/40624575/ part 2: time-to-event outcomes - pubmed.ncbi.nlm.nih.gov/41402895/

lnkd.in

This link will take you to a page that’s not on LinkedIn

1166

Reposted by Gary Weissman

Emily Moin @emilymoin.com · 12/02/2026

Online ahead of print! Is big data finally coming for the ventilator? Is it even worth the effort? academic.oup.com/annalsats/ad...

academic.oup.com

Waveform data capture substantial variation in tidal volume and other respiratory parameters

AbstractRationale. Patients receiving invasive mechanical ventilation (IMV) require accurate assessments of ventilator parameters. Documentation of these p

491

Reposted by Gary Weissman

UCSF CODEX @ucsfcodex.bsky.social · 28/08/2025

🎥 Event recording now available! Thank you to Andrew Gonzalez and @gweissman.bsky.social for joining us and sharing about their impactful projects. Learn more and watch now: codex.ucsf.edu/events/codex... @ajsharmamd.bsky.social @benrosnermdphd.bsky.social

codex.ucsf.edu

031

Reposted by Gary Weissman

PennLDI @pennldi.bsky.social · 16/07/2025

Sepsis prediction models are a promising tool, but very few have been successfully employed in clinical settings. A new study suggests a key reason: clinicians’ definitions of sepsis often differ from the “Sepsis-3” criteria used to train models Read more: pubmed.ncbi.nlm.nih.gov/40417569/

pubmed.ncbi.nlm.nih.gov

Sepsis Prediction Models are Trained on Labels that Diverge from Clinician-Recommended Treatment Times - PubMed

Many sepsis prediction models use the Sepsis-3 definition or its variants as a training label. However, among the few sepsis models ever deployed in practice, there is scant evidence that they offer c...

141