Jonathan Bortinger

Our study of AMIE at @BIDMC_Medicine is out! You can read about what we did in posts from my co-authors (including the Google post below). But I wanted to talk about some background for this study, and what I think are most interesting findings. 🧵⬇️ x.com/GoogleResearch…

Foolproof get rich quick hack: Step 1) Buy $500M in minoxidil Step 2) Sell $500M of minoxidil for $400M Step 3) Get acquired by $HIMS for 3x revenue.

Thanks to @EricTopol for highlighting our latest study, which looks at some of the failure points in the clinical reasoning performance of reasoning models. What does this mean for the future of diagnostic decision support? And can LLMs actually medically reason? A 🧵⬇️

Huge update to our preprint today on the superhuman performance of reasoning models in medical diagnosis! TL;DR – they don't just surpass humans in meaningful benchmarks, but in actual medical care from unstructured clinical data: A 🧵⬇️: x.com/AdamRodmanMD/s…

@BIDMC_Medicine @BIDMC_IM @VankaAnita @BIDMChealth @HMFPBoston @ccsmith269 @BIDMC_Education Congrats!

We're thrilled to announce Dr. Anita Vanka has been appointed Program Director of @BIDMC_IM. Having completed her own training in the program, Dr. Vanka will bring her wealth of medical training knowledge to continue to foster our residents to become future leaders in medicine.

@KevinH_PhD I am so sad to read this. I have followed you online and learned so much from reading your posts and papers. You have moved the field forward!

After 21 years at my dream job, I’m very sad to announce my early retirement from the National Institutes of Health. My life’s work has been to scientifically study how our food environment affects what we eat, and how what we eat affects our physiology. Lately, I’ve focused on unravelling the reasons why diets high in ultra-processed food are linked to epidemic proportions of chronic diseases such as diabetes and obesity. Our research leads the world on this topic. Given recent bipartisan goals to prevent diet-related chronic diseases, and new agency leadership professing to prioritize scientific investigation of ultra-processed foods, I had hoped to expand our research program with ambitious plans to more rapidly and efficiently determine how our food is likely making Americans chronically sick. Unfortunately, recent events have made me question whether NIH continues to be a place where I can freely conduct unbiased science. Specifically, I experienced censorship in the reporting of our research because of agency concerns that it did not appear to fully support preconceived narratives of my agency’s leadership about ultra-processed food addiction. I was hoping this was an aberration. So, weeks ago I wrote to my agency’s leadership expressing my concerns and requested time to discuss these issues, but I never received a response. Without any reassurance there wouldn’t be continued censorship or meddling in our research, I felt compelled to accept early retirement to preserve health insurance for my family. (Resigning later in protest of any future meddling or censorship would result in losing that benefit.) Due to very tight deadlines to make this decision, I don’t yet have plans for my future career. The NIH has been a wonderful place because it allows scientists to take risks, form unique collaborations, and do studies difficult to conduct elsewhere. I’m proud of what we’ve accomplished and I’m fortunate to have had such wonderful colleagues and scientific collaborators. I hope to someday return to government service and lead a research program that will continue to provide gold-standard science to make Americans healthy.

There is a lot of buzz about our new paper in Nature Medicine on the effects of LLMs (GPT-4) on physician management reasoning! I had TONS of fun working on this -- but what it MEANS requires some unpacking. A 🧵⬇️ x.com/EricTopol/stat…

Preprint out today that tests o1-preview's medical reasoning experiments against a baseline of 100s of clinicians. In this case the title says it all: Superhuman performance of a large language model on the reasoning tasks of a physician Link: arxiv.org/abs/2412.10849 A 🧵⬇️

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 🧵⬇️ x.com/EricTopol/stat…

@DrMarkAwad @MSKCancerCenter Congrats!

I'm honored to join the phenomenal thoracic group @MSKCancerCenter as we continue working with the global oncology community to advance care for our patients worldwide with groundbreaking new discoveries and practice-changing therapies. #LCSM mskcc.org/news-releases/…

@halletecco @RelentlesHealth had a great episode on this topic recently…you are right, the “system” is bonkers 💊💵 open.spotify.com/episode/5IyCNu…

What's a typical day in a GP practice in Denmark 🇩🇰 where 98%+ of people have access to primary care? Here's some of what I learned spending the day at a practice in Aarhus last month 🧵 (and yes, the space really is as beautiful as it looks in these photos!)

🚨#FLOW: The most anticipated trial of the year now published in @NEJM with #ERA24 Semaglutide 1.0mg once weekly disease modifying with kidney, CV, & mortality benefits in people w T2D+CKD, cementing itself as a new pillar of care. 🧵 on key thoughts 👇🏾 nejm.org/doi/full/10.10…

@OpeyemiOlabisi8 @Cervantes_Lily1 @DukeKidney @dukemedicine Congrats!

I am grateful for the opportunity to serve as Vice Chief for Research in the Duke Division of Nephrology! I look forward to working with colleagues, community of learners and investigators to build on the existing excellence @DukeKidney @dukemedicine

@zach_london Great 🧵Are there any general principles to adress patients with pre-existing peripheral neuropathies who have an indication to begin one of these anti-cancer drugs? Are some types of neuropathies more susceptible to worsen with exposure?

Neuropathy is the most common reason to stop chemotherapy. Here are a few practical things to know about it. 1/ #tweetorial #neurotwitter

@NateShivelyMD This is an awesome thread! Thanks for posting 🧫Love the quote “bacteria are smart but not that smart”

Summary: PO works, no high quality data to the contrary. Guidelines on when to switch. (Gave caveat for #2 that no need repeat blood cultures for uncomplicated GNR bacteremia). Absolutely fantastic talks! #SHEASpring2024 20/20

Next up is the Dogmas of stewardship! Bookmark this thread folks, some great stuff below. First up is Dr. Jim Lewis. #SHEASpring2024 1/

#idboardreview unimmunized child w/fever, cough, nasal inflammation followed 2 days later by diffuse nonpruritic maculopapular rash on face then chest then arms/legs. Exam: red conjuctiva, cbc, chem normal, chest clear, cxr b/l interstitial infiltrates #idtwitter #idxposts #meded

@MichaelAlbertMD @soonergise “Cardiovascular disease was defined as previous myocardial infarction, previous stroke, or symptomatic peripheral arterial disease.” I wonder how prior auth will limit access for those with sub clinical ASCVD (positive CAC…CCTA, etc) or elevated clinical risk scores

@soonergise SELECT trial inclusion criteria

🚨BREAKING: Novo Nordisk receives the first of its kind FDA approval of Wegovy (Semaglutide) for secondary prevention of cardiovascular disease in people with overweight and obesity. novonordisk.com/news-and-media…

@emollick @AdamRodmanMD

This is a neat result on the ability of AI to answer medical questions. A well-prompted frontier generalist AI (GPT-4) beats highly fine-tuned specialized LLMs (Med-PaLM 2) in its area of specialty. Models are improving fast, though usual testing caveats. arxiv.org/pdf/2311.16452…

@MichaelAlbertMD I’ve learned a lot from following you and @BevTchangMD …do you have any favorite publications or online grand rounds that cover some of the practical issues re; titration or adjustment and optimizing longitudinal success?

FUN FACT: The majority of physicians prescribing GLP1s (TODAY) were never formally trained on how to prescribe them.