CMI Communications

@cmicomms.bsky.social

ESCMID's open-access journal with companion podcast (Communicable) for all things infectious diseases, clinical microbiology, AMR & stewardship #IDSky #MedSky #EpiSky #ClinMicro

🗞️ https://www.cmi-comms.org/

🎙️ https://communicable.transistor.fm

@steventong.bsky.socialReposted by @cmicomms.bsky.social

The next Clarity commentary. On the SNAP trial. Neither I nor @gurujosh.bsky.social had anything to do with this commentary (deliberately).
Conclusions though are in line with my interpretation of the data. i.e., use cefazolin for MSSA bacteremia.
@angelahuttner.bsky.social @cmicomms.bsky.social

@escmid.bsky.socialReposted by @cmicomms.bsky.social

💡 Take your clinical trial from concept to completion. Learn how to design, conduct and report a clinical trial through expert-led sessions and workshops covering every stage of the clinical trial journey.

Register today: https://ow.ly/lStL50Zrgqa

#IDSky CMI Communications CLARITY_Initiative

@cmicomms.bsky.social

📣We rely more & more on #AI for literature review

So how did 6 large language models compare to humans when extracting data from #RCTs for a systematic review?

Not very well: overall #LLM concordance was 0.58-0.75.

#IDSky
@steventong.bsky.social
@seanong.bsky.social
cmi-comms.org/article/S295...

cmi-comms.orgA proof-of-concept performance evaluation of six large language models for semiautomated data extraction in a systematic review on infectious diseases clinical trialsLarge language models (LLMs) are increasingly being used in the systematic review process. Our objective was to explore data extraction performance of six LLMs from a published systematic review of in...