Thanks Ivana J. and @jonc101x for the fantastic talks on machine learning and LLMs in medicine! Lots of great discussion but more importantly some wild magic 🪄🪄🪄 (@jonc101x is a magician if you can believe it)

Our new study in JAMA Internal Medicine looking at the reasoning abilities of GPT-4 compared with human physicians just came out.

Big picture: AI displays (much) better reasoning than humans, makes diagnoses similarly, but hallucinates considerably more.

A 🧵to put in context ⬇️

An LLM outperformed human clinicians in the ability to process medical data and display clinical reasoning, raising hopes that LLMs might be able to serve as “copilots” in clinical workflows. ja.ma/4cxVJgV

Super excited to share our passion project comparing human and LLM reasoning.

An important finding: GPT generally wrote MORE, didn’t cut corners like humans thus scores could be ⬆️

Adam Rodman Raja-Elie Abdulnour Steph Cabral Byron Crowe Philip Wilson

jamanetwork.com/journals/jamai…

We know LLMs can ace multiple-choice exams. Taking us deeper, an important new study led by Steph Cabral and Adam Rodman conducts a nuanced evaluation of the clinical reasoning abilities of GPT-4 wrt physicians. Guess who wins?

Need more of these!
jamanetwork.com/journals/jamai…

It is remarkable how routine it has become for careful studies to show that GPT-4 (not trained specifically for medicine) outperforms most doctors in key aspects of diagnosis.

That doesn't mean that GPT-4 is reliable in all circumstances, but it still seems like a big deal.

How good is #AI at clinical reasoning? An early, simulated assessment
jamanetwork.com/journals/jamai…
“An LLM was better than physicians in processing
medical data and clinical reasoning using recognizable frameworks as measured by R-IDEA”

On pulm consults with Harvard Pulmonary & Critical Care Fellowship BIDMC IM Residency, and consulted on a case of platypnea that is still escaping us. In the spirit of a Staci Saunders intern report today on effective med-ed, here's my general approach to the condition and attempt at an infographic!
#MedTwitter

🖥️We wrapped up our first Academic Half Day on AI in Medicine! Thanks to all our speakers!

We learned more about tools like #GPT -4 and Open Evidence, especially in research and clinical application. We also discussed ethical & future policy implications. #Bioethics #AI #MedEd

SURGE (our unsupervised method to discover context-specific eQTLs without requiring pre-specification of the contexts of interest) is now out in Genome Biology! genomebiology.biomedcentral.com/articles/10.11…

We are absolutely delighted to welcome this amazing class of new fellows to the MGH/BIDMC Pulmonary and Critical Care Medicine Fellowship in July 2024!
MGH Division of Pulmonary & Critical Care Medicine
BIDMC Pulmonary, Critical Care, and Sleep Medicine

I’m excited to share our latest preprint on fine-mapping causal tissues and genes at disease associated loci using our new method, TGFM medrxiv.org/content/10.110…

We are VERY excited to be kicking off this year's Harvard Medical School Combined Grand Rounds series with A Turing Test for Clinical Reasoning: Large Language Models and the Future of Diagnosis!

(link here: healthcare.partners.org/streaming/Live…)

Medical educators have a crucial role in shaping the inevitable integration of AI into the healthcare.

Adam Rodman and I wrote about it in NEJM ⬇️

nejm.org/doi/full/10.10…