Urologic oncologist | Kidney cancer | Retzius-sparing prostatectomy | Harvard-trained epidemiologist | Creator, Urology Oral Boards Coach | Fort Worth, TX
Fort Worth, TX
Joined July 2009
- Tweets2.8K
- Following974
- Followers1.1K
- Likes694
Pinned Tweet
Urology Oral boards coach with physician authored frameworks. Wanted to share some highlights. Feedback is appreciated!
- Works within the boundaries of a case and framework, it will and cannot hallucinate!- More than 300 authored cases
- Goes off a deterministic rubric - to adequately test the case on all major miletones.
- Frameworks respecting what to withhold, when to reveal, key decision points, and how the examiner should probe. like the real exam.
- Over 100 OSCE scenarios including visual OSCE
- Medical grade dictation for long answers
- Voice mode (talk to the examiner while driving to work).
- Testing mode will not *accidentally* teach, and
- Open book mode cannot reveal the answer for the next question
Web:
urologyboardscoach.com
iOS:
tinyurl.com/w34syzzw51
Sohrab Arora retweeted
> AI now catches far more errors in clinical trial papers than human peer reviewers: all 15 models tested scored 53% to 96% on planted errors, while untrained human reviewers averaged just 27%.
> The result held on 58 new trials published in 2026, so the models weren’t simply recalling old papers they had seen in training; Claude Opus 5.5 scored highest at 99%.
> Humans miss the errors that most change a trial’s meaning, catching text-table contradictions only 7% of the time, and they take 5 to 8.5 hours per review against AI’s 1.4 to 16.3 minutes.
Lots of debate this week on whether journals should ban AI in peer review.
We actually tested this in our new preprint, and the results were pretty clear to me.
For context, I've reviewed for most of the big journals and evaluated 1,000 human reviews as an editor. I love to read and evaluate science.
TLDR: From now on I won't do any peer review without AI. For clinical trials, I'd even call human-only review dangerous 🧵
Urology oral boards is not a game🎳. Nor is it a test a knowledge 📚.
It is a test of structure, hitting all the checkboxes, and keeping it moving!
Urology Oral Boards Coach at urologyboardscoach.com was built around that structure and framework. Available on web, iOS, and Android.
Web: urologyboardscoach.com
iOS app: apps.apple.com/us/app/urolog…
Android: play.google.com/store/apps/d…
Sohrab Arora retweeted
Original Article: Durvalumab, Tremelimumab, and Enfortumab Vedotin in Muscle-Invasive Bladder Cancer (phase 3 VOLGA trial) nej.md/4z7dQFm
#ESMO26 | @myESMO
ALT A graph showing event-free survival for the durvalumab–enfortumab vedotin (EV) and control groups (intention-to-treat population).
ALT A graph showing event-free survival for the durvalumab–tremelimumab–EV and control groups (intention-to-treat population).
Sohrab Arora retweeted
Massive. New Harvard study finds that AI-written paper reviews now beat the best human peer reviews on every measure the authors tested.
Peer review is slow and often misses errors. Earlier studies concluded AI should only assist human reviewers, not replace them.
They used 134 reviews from rapidPeer, a Harvard service that pays expert reviewers well. Claude Opus 4.8 reviewed the same 1124 papers, and GPT-5.5 plus 3 former journal editors judged the pairs blind.
GPT-5.5 picked the AI review in all 132 decided pairs, and the editors picked it 87% of the time. Only 5.5% of the AI's claims about the paper were wrong, versus 15.9% for the human reviews.
Teams that depend on expert critique can now let AI do the first full review pass, and keep a human for the final decision.
Sohrab Arora retweeted
By avoiding the rectal wall, transperineal biopsy avoids inoculating prostate tissue with rectal flora. PREVENT found fewer infections than transrectal biopsy with culture-directed prophylaxis.
Ref: doi:10.1001/jamaoncol.2024.4000
#ProstateBiopsy #Urology
🤖 Made with AI
Sohrab Arora retweeted
Today @GoogleResearch is launching Deep Review — an agentic system designed to stress-test manuscripts, design docs, and complex proposals before submission or publication. After pilot partnerships analyzing over 15,000 research papers, we’re making Deep Review globally accessible to help researchers, engineers, and professionals bring structured critique to their daily workflows.
Sohrab Arora retweeted
New unpopular opinion:
AI prose is perfectly fine in most contexts. Get over yourselves.
People worried about AI slop in academic medicine should go back and look at papers before AI. 90% of those are human slop.
Focus on science, not the tool. #medtwitter #AcademicTwitter @EricTopol @MicrobiomDigest @CaulfieldTim @fperrywilson @VPrasadMDMPH
What makes an "AI" app more than a wrapper around a chatbot? For our Urology Oral Boards Coach urologyboardscoach.com/: ~500 pages of clinician-authored frameworks, rule-based deterministic case logic, and AI guided by that structure.
Now Also listed on "Clinicians That Code" as a verified builder. @bart
I keep hearing: "We don't need research assistants anymore."
Let's play this out. If research assistants are just researchers-in-training, how exactly do we plan on getting senior scientists 10 years from now?
Would love to hear thoughts from folks who mentor early career researchers.
@AcademicChatter @OpenAcademics @ThePhDPlace @PostdocVoice @CT_Bergstrom @JacquelynGill @InsideHigherEd
Sohrab Arora retweeted
In a place presumably guided by science (or at least common sense), let's call out the crazy:
- surgeons with shaved heads wearing mandatory caps
- people nowhere near the sterile field wearing ridiculously fitted beard condoms
What else?
Sohrab Arora retweeted
Today @TheLancet published our AMIE study with @BIDMC_Medicine, the first prospective study of patient-facing conversational diagnostics in a real clinic.
AMIE is a research system people can chat with before doctors appointments. Testing AMIE outside the lab with real urgent care patients showed how technology can help gather medical histories safely. Clinicians reported that the summaries helped them prepare for visits in 75% of cases and influenced their approach to care in more than half. AMIE’s differential diagnoses also matched the doctors’ final diagnoses 90% of the time giving clinicians more time to focus on patient care.
It’s Google’s first-ever paper in The Lancet’s main journal!
Phase 3 UTOPIA (zusduri) is everything wrong with modern oncology trial design. No control arm, a 3 month surrogate endpoint for low-grade NMIBC, and testing a minor formulation tweak just to fix Zusduri's clunky reconstitution. FDA rubber-stamping at best @UroGenPharma. #BladderCancer
Sohrab Arora retweeted
Pure mathematics may be over as a human-driven endeavour. It may not take long before humanity will be made largely redundant in other scientific disciplines. We are living in interesting times ...
We’re releasing a broad range of new mathematical results produced by an internal frontier model.
We’ve been consulting with the independent Advisory Group on Mathematics and Artificial Intelligence at the Institute for Advanced Study, and we have drawn on their advice and public recommendations to inform how we release these results.
github.com/openai/math
Sohrab Arora retweeted
OpenAI seems to have made a serious breakthrough toward the Riemann hypothesis, and people are still virtue-signaling their “pure human” work with Pangram scores.
Well, this blew up!
Just goes to show that behind every great surgeon is a passionate opinion on suture material. Chromic gut is just the thread that binds us all together, pun intended.
