Raja-Elie Abdulnour
@BageLeMage
Followers
568
Following
405
Statuses
377
Editor-in-chief @JWatch - Clinical development and AI innovation @NEJM - DxEx Scholar 23-24 @theNAMedicine - Views are my own.
Boston
Joined March 2010
AAMC just released its Principles for the Responsible Use of Artificial Intelligence in and for Medical Education Feedback is required! @AAMCtoday #MedTwitter
0
1
3
My JW clinical spotlight on LLM and clinical reasoning. @AdamRodmanMD
Large Language Artificial Intelligence Models and Clinical Reasoning: The Frontier in 2024 Popular AI models like GPT demonstrate expert-like reasoning performance but also substantial human-like cognitive biases. #AI @BageLeMage
0
1
3
RT @AdamRodmanMD: Preprint out today that tests o1-preview's medical reasoning experiments against a baseline of 100s of clinicians. In th…
0
225
0
@AdamRodmanMD Two questions: Did the clinician ChatGPT accounts include a custom GPT? maybe one with the same instructions as your 0-shot GPT arm. Did the control arm have access to other LLMs like OpenEvidence?
0
0
0
Fascinating. "Access alone to LLMs will not improve overall physician diagnostic reasoning in practice." Thanks for the Diagnsotic Performance assessment rubric! @AdamRodmanMD @andrewparsonsMD @andrewolsonmd
Our first RCT on using an LLM on diagnostic reasoning is out! And the results are 🔥🌶️... adding ChatGPT did NOT improve diagnostic accuracy or reasoning, and the AI alone outperformed ALL the humans. What does this mean? A 🧵⬇️
0
0
5
Great column @PaulSaxMD - thanks for the link to the first report of AIDS patients in the US. A piece of history.
Gathering with a bunch of fellow ID geeks (that is, people like me) last week inspired this deeper look at the PCP vs PJP controversy for Pneumocystis jirovecii pneumonia. It’s only Part 1, so a real cliffhanger. Enjoy.
0
0
3
RT @JWatch: For long-term oxygen therapy, is 24 hours a day better than 15? Not according to a randomized trial of supplemental oxygen for…
0
20
0
RT @JWatch: Artificial Intelligence vs. ID Residents and Specialists: Who Tested Best? @BageLeMage #AI #IDTwitter h…
0
1
0
NIV for preoxygenation in the ICU: "In a randomized trial, preoxygenation with NIV significantly and safely lowered the incidence of hypoxemia in critically ill adults." What does that mean for ICU docs? @NEJM @JWatch @PulmPEEPs
0
0
0
RT @JWatch: Dr. Raja-Elie Abdulnour (@BageLeMage), the new Editor-in-Chief of @JWatch, shares some thoughts on his first 2 weeks in this ro…
0
4
0
Mechanical ventilation impact on functional status: "At hospital discharge, the 30-second sit-to-stand test scores showed that ICU survivors in this trial were functionally consistent with 90-year-olds." Biking in bed 1km per day, sometimes on sedation, did not help. @PulmPEEPs
Just published: “Early In-Bed Cycle Ergometry in Mechanically Ventilated Patients” by Michelle E. Kho, PT, PhD (@khome), et al.: @ogradyhk @machealthsci #CCR24
1
0
3
Great tool for visual comparative analyses of different LLM competencies. Quality vs. throughput is particularly helpful. It is all math, with as far as I know, no human in the loop. Therefore I cannot use it to decide whether to fully trust an LLM or not.
0
0
5
Time to change my screensaver.
The best place to relax is near water. After just 2 minutes of viewing water outdoors, blood pressure and heart rate drop. It's more calming to look at a lake, pool, or stream than trees or grass. Beaches are popular for a reason. Wider bodies of water bring more tranquility.
0
0
2