Heading to #TLM26 in Denver? UCSF authors are on 78 abstracts: 16 orals, 62 posters and 30 invited and moderator roles across Nov 5–8. Come find the @UCSFLiverCenter team! #AASLD #LiverTwitter

Fangirling over @umichmedicine Hepatology & LTx, home of the world’s best liver docs! Honored to be invited by the great Dr. Anna Lok for the Sheila Sherlock visiting professorship. #GoBlue (❤️ @zingermans) @ebtapper @NikMazumder_MD @pummy92 @RobertFontanaMD @HPB_Txp_Surg

We don't ask whether a model touched their prose. We ask authors to own every word. @JACCJournals parted w/ICMJE & doesn't require disclosure of AI writing help: the rule is unenforceable, biased, & not good for medical communication. My Editor's Page: jacc.org/doi/10.1016/j.jacc.…

Congratulations to Dr. Mamatha Bhat, Co-Chair of CASL's Research Committee, named an inaugural recipient of the 2026 Canada Leads SUMO-UHN Distinguished Physician Investigator Award. #CASL #Hepatology

📑 🤖 #AI-generated draft hepatology e-consults show promise‼️ ⭐️83% provided appropriate case-specific recommendations ⚠️ 10% contained misleading/incorrect ⚠️ 3.4% posed risk of severe harm 🚨Human oversight remains essential🚨 #OpenAccess @egnij journals.lww.com/hepcomm/ful…

Human Dr to patient - You just puked. Let’s find out why. AI - Nothing AI can’t see and reason in real time. Human Dr sees patient collapse. Does CPR. AI - Nothing AI can’t see or do CPR Human Dr sees patient- Discusses patients with other doctor who knows patient and discussed the fact that a parent was beating the shit of the patient. Shows empathy Adapts care regimen AI - Nothing. No doctor knows what will happen to a patient when it steps in their office. They have a real time identification and response skill set that AI can’t and won’t have. SDOH will always matter. I don’t see a world where AI has judgement and can know the outcomes of its decisions without a human in the loop.. I’m obviously not a doctor, but there will be no point where real time observation, communication and context won’t matter. A human can’t consume and remember all the data and information AI can. So AI will always have value. Every single one of us has more variables in our body than can be quantified , let alone identified and defined. Once we can identify them all or ar least enough, AI will be able to personalize responses for specific issues. But that won’t happen in the next 5 or 10 years. It’s a problem similar to dealing with CTE. You can’t figure out what actually happened until the patient is dead. Tell me where I’m wrong

Congratulations to @JenLaiLiverDoc for her @AASLDtweets Impact Award! aasld.org/aasld-impact-award…

What is the incidence of hepatic AVMs in people with hereditary hemorrhagic telangectasia? This study provides a clear answer Congratulate Dr. Cho on his @HepCommJournal paper And also @egnij on this very cool, super powerful LLM-NLP pipeline he built journals.lww.com/hepcomm/ful…

A Brown professor gave his students a take-home midterm exam. After suspecting many cheated using AI, he made the final in-person. The orange dots are the midterm scores and the gray dots are the final scores. Looks like all but 3 cheated on the midterm.

There are too many studies in the medical literature comparing AI models It doesn’t add anything meaningful and these models are often obsolete or replaced by the time of publication

Thanks to all attendees and expert speakers for our final session of DDW on AI in Hepatology! See you all again soon! #DDW2026 @AmerGastroAssn @YaleDigestive

The Young Investigators Forum at #cit26 was an amazing opportunity for the field’s most promising youngsters to share their research while also sharing some entertaining fun facts about themselves along the way!

Every time Friends, if every thing reduces risk by 50% then what you are studying is not a true effect of a therapy but a universal constant of database research

I’m excited to introduce AASLD’s newest Special Interest Group: Clinical Informatics & Digital Health (CIDH SIG)! This new AASLD community is focused on innovation, collaboration, and digital transformation in #hepatology. Learn more and get involved: bit.ly/3OigJk8

Yes! Every resident who comes to my clinic and tells me they are interested in cardiology or critical care hears from me a plea to expand the use of elastography inpatient for heart failure management

⭐ Meet the 2026 Clinical Research Leadership Program #CRLP cohort! These physician-scientists will receive training in clinical research management & convene w/ other #ACGInstitute programs at #LeadershipYOU in June 2026. 🎉Congrats! #ACGfamily #FutureofGI @NeenaSAbrahamMD

📑 Generative AI in hepatology: Transforming multimodal patient-generated data into actionable insights 🤖 #LiverX #ArtificialIntelligence #OpenAccess journals.lww.com/hepcomm/ful…

Thank you @PaulYKwo @Stanford_GI for the invitation to come share our research at @UCSFGIfellows @UCSFTransplant

Happy New Year to everybody ! In my view, these are 6 major unmet needs that must be addressed in 2026 to move hepatology forward globally: