Great collaboration @BIDMC_Medicine @GoogleDeepMind @GoogleResearch led by @PeterBrodeurMD Jacob Koshy @apalepu13 @AdamRodmanMD @alan_karthi @HardyShakerman @vivnat Marc Cohen and more
English
Wei-Hung Weng
18 posts
Wei-Hung Weng
@ckbjimmy
Research Scientist @GoogleDeepMind, AI for science, MD/PhD, ex @MIT_CSAIL @HarvardDBMI
เข้าร่วม Nisan 2024
16 กำลังติดตาม124 ผู้ติดตาม
AMIE in a real-world primary care clinic! In a prospective study, AMIE achieved 0 safety stops required; DDx included the final diagnosis in 90% of cases; blinded quality was on par with human PCPs, and High patient & doctor satisfaction. [Preprint] lnkd.in/gCwr3rV5
English
Nice work w/ @Moorfields @UCLeye @GoogleDeepMind @GoogleAI Mertcan Sevgi @FaresAntaki @pearsekeane @alan_karthi @vivnat @taotu831 @apalepu13 @yongcheng16 @HardyShakerman @_khaledsaab @RyutaroTanno @valentinlievin @SaraM66905 and more.
English
AMIE can serve as a complimentary tool for ophthalmology. It not only matches specialist performance, but also augments ophthalmologist clinical reasoning, leading to improved accuracy, consensus and planning. [Preprint] lnkd.in/g9HuMWqY
English
Great work @GoogleDeepMind @GoogleResearch w/ @elahevedadi @davidstutz92 @dgtbarrett @alan_karthi @imnatalie_grace @vivnat Ellery Wulczyn @AdamRodmanMD @zhazhir @Romes13 @HardyShakerman @timstro @RyutaroTanno @yasharmaa @AvinatanH48021 Katherine Chou @ymatias @pushmeet et al.
Polski
AMIE now can utilize an asynchronous oversight paradigm, managed by a team of specialized AI agents, guardrailed-AMIE (g-AMIE), to ensuree responsible and scalable human clinician oversight for medical AI. [Preprint] lnkd.in/geHFCqY7
English
Powered by the natively multimodal Gemini and domain-specific inference-time algorithm (without further post-training!), AMIE can now see and interpret visual medical data within a diagnostic conversation [Preprint] lnkd.in/gZJf5Jex
[Blog] lnkd.in/gvk3QwtB
English
Grateful to team @GoogleAI @GoogleDeepMind with @HardyShakerman @valentinlievin @apalepu13 @alan_karthi @AdamRodmanMD @taotu831 @vivnat @KhaledSaab11 @RyutaroTanno @davidstutz92 @yongcheng16 Kavita Kulkarni @SaraM66905 @joelle_barral @dr2w @AvinatanH48021 @ymatias James Manyika
Indonesia
AMIE now gains enhanced management reasoning for disease management over time and longitudinal patient care using the Gemini-based dual-agentic system, with the integration of clinical knowledge! [Preprint] lnkd.in/gqAyVBXV [Blog] lnkd.in/gScdDj3D
Anil Palepu@apalepu13
[1/N] I’m excited to share new work on Project AMIE (Articulate Medical Intelligence Explorer), our conversational medical AI! We put our system through a multi-visit OSCE to assess its management reasoning capabilities. Blog: research.google/blog/from-diag… Paper: gstatic.com/amie/towards_c…
English
Wei-Hung Weng รีทวีตแล้ว
Hypothesis generation and testing is a critical capability for AGI imo. Super excited about our AI co-scientist and other AI for Science work which are important steps towards that. We're on the cusp of an incredible new golden age of AI accelerated scientific discovery.
GIF
English
Great work led by @jrpenades @CostaT_Lab, with our team @GoogleAI @GoogleDeepMind @googlecloud @alan_karthi @vivnat @Mysiak Annalisa Pawlosky Alexander Daryin @taotu831 @apalepu13 Artiom Myaskovsky
English
Pioneer researchers @jrpenades @CostaT_Lab (@imperialcollege) described how our AI co-scientist correctly recapitulated their unpublished, experimentally confirmed mechanism of bacterial gene transfer! Details biorxiv.org/content/10.110… shorturl.at/kRJqE
Alan Karthikesalingam@alan_karthi
The reception to our @GoogleDeepMind @GoogleAI @googlecloud AI co-scientist has been amazing! We are working hard to expand access to the tool for more scientists. 🧫🧬A co-timed pre-print led by pioneer collaborators @imperialcollege, @jrpenades & @CostaT_Lab, describes how the AI co-scientist recapitulated their mechanistic breakthrough in bacterial gene transfer, which was not previously published biorxiv.org/content/10.110… More from José in his interview by @BBCNews, which gives a sense of our wonder in working together: bbc.com/news/articles/… With our super team @vivnat @Mysiak @ckbjimmy @taotu831 @apalepu13 and Annalisa Pawlosky
English
Great work with a team across @GoogleAI @GoogleDeepMind @googlecloud, @Mysiak @vivnat @alan_karthi Alexander Daryin Annalisa Pawlosky @taotu831 @ynhnx @_e_d_v_ @OpsBug @apalepu13 @KhaledSaab11 @RyutaroTanno @AvinatanH48021 @pushmeet @ymatias and more.
English
Delighted to introduce our collaborative, multi-agentic AI co-scientist to accelerate scientific discovery with scientists. Check out blog post goo.gle/417wJrA and preprint lnkd.in/eGZcTXXv for signing up trusted tester program and more details!
GIF
Vivek Natarajan@vivnat
Accelerating scientific discoveries and helping cure diseases might be the most profound purpose of AI. Thrilled to introduce our @GoogleAI @GoogleDeepMind @googlecloud AI co-scientist system, which I believe is an important milestone towards this. Blog - research.google/blog/accelerat… Paper - storage.googleapis.com/coscientist_pa…
English
Pleased to announce the release of the open-source, fully re-labeled MedQA benchmark, to facilitate more accurate model performance estimation. GitHub repository: github.com/Google-Health/… Check David's post for more details!
David Stutz@davidstutz92
Part of our Med-Gemini work was a full relabelling of MedQA, revealing that at least 7.4% of examples are unfit for evaluation. Today, we open sourced these annotations alongside our evaluation script as a new standard evaluation on MedQA. A thread 🧵: github.com/Google-Health/…
English
Excited to share the work using conformal abstention to abstain LLM hallucinations! arxiv.org/abs/2405.01563
David Stutz@davidstutz92
Happy to share our latest work using conformal abstention to improve factuality of LLMs by avoiding hallucinations: arxiv.org/abs/2405.01563 A short thread 🧵:
English
Excited to share Med-Gemini! arxiv.org/abs/2404.18416 Except for remarkable SoTA performance on MedQA and various medical language/image/video tasks, one super exciting potential to highlight is to unlock novel applications via the long-context capability and multimodal dialogue!
GIF
GIF
Alan Karthikesalingam@alan_karthi
Delighted to share ✨Med-Gemini✨ - our new family of multimodal models for medicine unlocking new possibilities for health - arxiv.org/pdf/2404.18416 More accurate multimodal conversations about medical images🩻, surgical videos📽️, genomics🧬, ultra-long health records📚, ECGs🫀 & more with state-of-art performance across multiple benchmarks More accurate, up-to-date answers to medical questions with advanced reasoning and intelligent use of web-search Long-context abilities. Summaries or referral letters from long health records, analyses of dozens of long research PDFs & more (1/6)
English