Ranveer Vasdev, MD, MS

Congratulations to the 22nd Annual Joseph Weston Segura MD Resident Essay Contest winners! 🥇1st @RanveerVasdev,🥈2nd @moh_ahmedMD,🥉3rd Matthew Lee MD,🎥1st Place Video @AnessaRafetto. We are proud of the dedication honoring Dr Segura! Special thanks to Dr Michael Blute, emcee!

AI agents perform better when they access tools they love. Introducing @gxl_ai's Paperclip: the command-line interface for scientific literature. gxl.ai/blog/paperclip

That’s a wrap on #EAU26! My first time to this amazing meeting. A few gems I’m going to take back across the pond: 📍 PET modified txt in 1/5 with UTUC 📍 For similar survival curves consider nadir + 0.5 after PCa s/p RT 📍 Accurate online content = fight the men’s heath crisis

First-in-human Nectin4-targeted fluorescence imaging for TURBT #EAU26 @urotoday • Diagnostic accuracy: 96% vs 85.6% with WLC • Tumor margin detection: 91.1% vs 72.2% • Ex vivo biopsy accuracy: 96.3% • Preclinical models doubled complete resection rates Probe demonstrated a favorable safety profile

New in Claude Code: Remote Control. Kick off a task in your terminal and pick it up from your phone while you take a walk or join a meeting. Claude keeps running on your machine, and you can control the session from the Claude app or claude.ai/code

Perspective by S. Parsa (@drshyonparsa) et al.: Designing Clinically Useful AI: A Blueprint for Impact nejm.ai/4qBoHTn #ArtificialIntelligence #AIinMedicine

Google just dropped another banger! the figures in this paper were drawn by the system described in the paper. PaperBanana is an agentic framework that generates publication-ready academic illustrations from methodology descriptions. no manual design, no Figma, just your method section and a caption. here's how it works: five specialized agents collaborate in sequence: > Retriever: finds relevant reference diagrams from a curated set of NeurIPS papers. matches by visual structure, not topic. > Planner: translates your methodology text into a detailed visual description using in-context learning. > Stylist: applies aesthetic guidelines (color palettes, typography, layout) auto-summarized from hundreds of top-tier papers. > Visualizer + Critic loop: generates the image, critiques it against source text, and refines. repeats for 3 rounds. one surprising finding: randomly selected examples work nearly as well as semantically matched ones. what matters is showing the model what good diagrams look like, not finding the topically perfect reference. in blind evaluations, humans preferred PaperBanana outputs nearly 3 out of 4 times. it also extends to statistical plots using code-based generation for numerical precision. link in the next tweet.

WATCH🎥: Sevann Helo, MD, (@Helo_MD) shares insights from a study that examined how an asynchronous video interview influenced applicant evaluation and selection. @MayoUrology urologytimes.com/view/assessing…

Attention Med Students ~ Apply now for the Mayo Clinic Grainger Medical Student Research Fellowship! Apps due Feb 12. #UroSoMe @UroResidency @Uro_Res @Uro_Stream @AmerUrological @UroAcademic @abhinav__khanna

Love this study. RUDOLPH 🦌 evaluates accuracy of the silly verbiage we use when communicating how far to move the patient for positioning Will be using “a full send” for every lithotomy case moving forward @SocSurgErgo @Anaes_Journal

How do you know how far to reposition your patient!? "Around 6 inches"? "a smidge"? Check out RUDOLPH - Rough Units of Distance in Operating theatre Longitudinal Patient Handling #anaesthesia #MedTwitter doi.org/10.1111/anae.7…

Our overview of and guidance for performance measures to evaluate medical AI is finally out! - Stop bashing AUROC - Calibration + clinical utility are key - Plot risk distributions - Classification measures are improper thelancet.com/journals/landi…

Howard Marks on AI: "Since no one can say definitively whether this is a bubble, I'd advise that no one should go all-in without acknowledging that they face the risk of ruin if things go badly. But by the same token, no one should stay all-out & risk missing out on one of the great technological steps forward. A moderate position, applied with selectivity & prudence, seems like the best approach." Source: oaktreecapital.com/docs/default-s…

⚡️ Low-grade NMIBC: favourable prognosis but high recurrence, driving intensive cystoscopic follow-up and costs. Review summarises its FGFR3/RAS/PIK3CA-driven biology, limits of surveillance and the promise of urine biomarkers plus new targeted/immunotherapies. #BladderCancer @NatRevUrol nature.com/articles/s4158…

New Anthropic research: Estimating AI productivity gains from Claude conversations. The Anthropic Economic Index tells us where Claude is used, and for which tasks. But it doesn’t tell us how useful Claude is. How much time does it save?

Releasing a new "Agentic Reviewer" for research papers. I started coding this as a weekend project, and @jyx_su made it much better. I was inspired by a student who had a paper rejected 6 times over 3 years. Their feedback loop -- waiting ~6 months for feedback each time -- was painfully slow. We wanted to see if an agentic workflow can help researchers iterate faster. When we trained the system on ICLR 2025 reviews and measured Spearman correlation (higher is better) on the test set: - Correlation between two human reviewers: 0.41 - Correlation between AI and a human reviewer: 0.42 This suggests agentic reviewing is approaching human-level performance. The agent grounds its feedback by searching arXiv, so it works best in fields like AI where research is freely published there. It’s an experimental tool, but I hope it helps you with your research. Check it out here: paperreview.ai

Iinternet searches and website traffic have increased sharply for an #AI-based clinical resource (OpenEvidence) relative to a traditional platform (UpToDate) since early 2024. ja.ma/4pm8Bfq

For men with prostate cancer treated with radiation therapy, what is the ideal duration of hormone therapy? Intermediate risk: <6 months High risk: ~12 months (For most) The longer the hormones, the less death from prostate cancer, but more death from heart attack, stroke, etc.

A foundation model for time series forecasting