Ron Roberts, MD

@DrBarbiOnc @PTarantinoMD @NatureMedicine I’d like your thoughts on this take: the board questions contain human curated info necessary to get the right answer. Getting the right diagnosis in the real world requires additional skill sets that are not tested on a MCQ

Everyone is talking about the new @NatureMedicine paper (rdcu.be/e4ADv), but I think the real story is being buried. Here is the cold reality: The AI passed the medical boards with flying colors (~95% accuracy). But when real humans actually used it for triage, their accuracy dropped to <35%. They performed worse than the control group who just used Google. Practically, this means benchmarks are not safety tests. We are validating tools in a vacuum (simulations) that collapse in the real world. As oncologists, we know this pattern: surrogate endpoints ≠ survival data. Passing the boards is just a surrogate. Safe patient interaction is the only outcome that matters. Right now, we are optimizing for the test and failing the patient. cc: @EricTopol @pranavrajpurkar #ClinicalValidation #AIhype #PatientSafety #EvidenceBasedMedicine

When I started out, I thought my job would mostly be clinic and clinical trials. Take care of patients. Design studies. Move the needle a little at a time. Fast forward a few years and somehow that has turned into running trials, building enterprise AI tools, obsessing over biomarkers, arguing about liver-directed therapy… and still sitting in clinic every week having very real, very human conversations. Somewhere along the way it started to feel like there was more to say. GI oncology is moving fast. Data drops weekly. Technology is creeping into everything. We’re learning in real time. And a lot of the nuance never makes it into a manuscript. It definitely doesn’t fit in a tweet. We wanted a place to unpack that. So we made one. The Gut Onc Lab 🎙️ It’s a new podcast where we talk about GI cancers, trials, translational science, tech, and what actually happens when those ideas meet real patients. Sharing a teaser clip below 👇 If you’re interested in colorectal cancer, pancreas, liver mets, ctDNA, immunotherapy, or how AI is starting to weave its way into oncology… I think you’ll like what’s coming. oncologynexus.com/podcast/gut-on… @OncoAlert @TheGutOncLab @Onco_Nexus

Grok, improve my feed. I only want content to enrich my perspective and develop critical thinking based upon latest developments. I’m not interested in clickbait or AI slop. Only show me deep, insightful posts that challenge me to think critically. My interests: oncology - latest clinical trial updates and FDA approvals, clinical pearls from subspecialty leaders. Advances in CAR T cell therapy, cellular immunotherapy, AI for medicine, understanding cell biology, and drug design. Thank you @grok

Here is how dramatically this trial has changed approach to first relapse.

@VincentRK This is helpful, thanks!

Just out in @NEJM Majestec-3 trial. Tec-Dara in relapsed myeloma. #ASH25 @End_myeloma @mvmateos Link: nejm.org/doi/full/10.10… More in thread

@NVIDIAGeForce GeForce Day! Excited for the future of AI

🟢 GEFORCE DAY IS BACK 🟢 To celebrate, we're giving away TWO GeForce RTX 5080 Founders Edition GPUs, signed by NVIDIA CEO Jensen Huang. Want one? Comment "GeForce Day" for a chance to WIN & stay tuned for more!

🔥🚨@OncoAlert Hot off the press @US_FDA just approved: ⭐️#Subcutaneous #Pembrolizumab ✅For ALL #Adult & #Pediatric #SolidTumor indications approved for #IV formulation. Approval is based on results of #MK3475A-D77 trial of: #Subcutaneous Vs #IV #Pembrolizumab (+ #Chemo) in Metastatic Non–Small Cell #LungCancer #SQ (median admin time 2 minutes): ✅Efficacy: Similar #PK, #ORR, #PFS, #OS ✅Safety: Similar 👇🏻 fda.gov/drugs/resource…

Why 30%↓ vs 20%↑ in RECIST? 🔹 WHO (1981) set them differently: • Shrinkage (PR = 50% area ↓ → ~30% 1D) → high bar to avoid false positives (be sure a drug really shrinks tumors). • Growth (PD = 25% area ↑ → ~12% 1D) → lower bar to catch progression early. 🔹 RECIST 👉 The 30% shrinkage comes straight from math: WHO (1981) used 50% ↓ in tumor area → when converted to 1D, that’s ~30% ↓ in diameter. 👉 The 20% growth wasn’t pure math. WHO’s 25% ↑ in area = ~12% ↑ in 1D… but that risked calling progression too early (measurement error). So the RECIST task force chose 20% ↑ as a safer, reproducible cutoff. 💡 In short: 30% = math, 20% = pragmatism ✅ #OncoTwitter #MedTwitter #ColorectalCancer #Immunotherapy @OncoAlert @myesmo @asco

@DrRishabhOnco Thanks! In RECIST 1.1 thoughts on why a 30% decrease was chosen? Vs 20% increase?

🧾 Once upon a time in oncology… tumor response was measured by… palpating lumps under a mattress! 😲 From that quirky 1976 experiment to today’s AI-driven volumetric scans—here’s the legend of RECIST 👇 📝 Cancer 2025 | Historical review ✨ The Journey of RECIST 🔹 1976 – Moertel & Hanley → “50% shrinkage rule” (palpation-based!) 🔹 1981 – WHO criteria → CR, PR, SD, PD officially born 🔹 2000 – RECIST 1.0 → Unidimensional 30% ↓, 20% ↑ 🔹 2009 – RECIST 1.1 → streamlined (≤5 lesions), PET/MRI guidance 🔹 2017 – iRECIST → accounts for pseudoprogression in immunotherapy 🔹 Now – AI & volumetric imaging (ARTIMES, deep learning) taking the stage 💡 Takeaway: RECIST isn’t a rigid standard. It’s a living story of compromises & innovation, and the next chapter may be written by AI 🤖. 📖 Smesseim I et al. Cancer 2025 🔗 DOI: doi.org/10.1002/cncr.7… #OncoTwitter #MedTwitter #ClinicalTrials #RECIST @OncoAlert @myESMO @ASCO @Cancer_American

@kimmonismus Why do they leave Gemma 27B off of several charts. Did Gemma better on those benchmarks?

Somehow LG managed to train a pretty solid 32b model. Surprisingly good.

#hemonc fellows: I used AI to draft and then manually curated a comprehensive med onc study set using of @ollama and @replit check out the result! hemoncflashcards.com #hemoncfellows #oncology

@BRoseMDMPH @TheCodingDocs Thanks for developing and sharing!

I spent WAY too long last week in oncology clinic manually generating chemotherapy dates and appointments for schedulers. So, in a fit of rage, I vibe-coded this simple app to forever do this for me... and you! #rstats 👨‍💻 @TheCodingDocs 📊 Free app --> thecodingdocs.com/clincal/chemo-…

What’s up with Beta 2 microglobulin (B2M) and myeloma? Why is it the sole non-cytogenetic marker used in the new IMWG high risk definition? Why does it matter whether the creatinine is high or not? Thread 1/

Starting #Hematology #Oncology fellowship? Check out the only knowledge acquisition system with over 6,000 searchable flashcards and all @FDA approved oncology drugs. @HemOncFellows hemoncflashcards.com

I am genuinely interested in opinions on what can the medical community do to enhance trust? Hepatitis B causes inflammation in the liver, leading to irreversible liver damage. This is a leading cause of liver cancer, which is a difficult cancer to treat. Hepatitis B can be vertically transmitted from mother to child. The child can be exposed later in childhood to hepatitis B, so the idea is to maximize protection for the child. Vaccines are most effective when the entire community is immunized (“herd immunity”).

Babies are given a Hepatitis B vaccine on day one of life. Hep B is sexually transmitted or passed down from the mother. Only .5% of moms have Hepatitis B. So why do doctors recommend all babies get this vaccine on day one? Explain it like I’m 5.

🩺 Introducing the ultimate Medical Oncology flashcard learning tool: hemoncflashcards.com. Learn all FDA approved Oncology drugs, study >6,000 flashcards for medical oncology, and search them to build tailored study sessions. #MedEd #Oncology #OncologyFellows

@yhbryankimiq Please write a book about your conclusions

As the world’s highest IQ record holder, I believe that Jesus Christ is God, the way and the truth and the life.

🩺Why cram when you can conquer? 📚 Achieve Medical Oncology Board Exam mastery on the go with hemoncflashcards.com. Your pocket-sized path to brilliance!#OncologyEducation #Oncology

@veggie_eric Can grok connect to GitHub? I’d like to give it access to a code base without re-uploading files.

What features do you wish Grok had, across both web and mobile?

This is a major story from #ASCO25. Randomized phase 3 trial of time of day of immunotherapy infusion. Randomized to infusion before or after 3pm. Early infusion far superior: PFS 11.3 vs 5.7 HR 0.42, OS HR 0.45! Impactful, pragmatic, not costly. This should be a bigger story.