Khaled Saab (@khaledsaab11) 's Twitter Profile
Khaled Saab

@khaledsaab11

Research Scientist @GoogleDeepMind working on Medical AI | Med-Gemini, AMIE | prev: PhD @StanfordAILab

ID: 1108592177972572160

linkhttps://khaledsaab.github.io/ calendar_today21-03-2019 04:52:26

161 Tweet

758 Takipçi

354 Takip Edilen

Adam Rodman (@adamrodmanmd) 's Twitter Profile Photo

We are excited to share our latest results on AMIE, Google AI Google DeepMind conversational medical AI. TL;DR – in a blinded OSCE, AMIE was equivalent or better at not only diagnosis – but also at making management decisions. This is a big deal! 🧵⬇️ x.com/alan_karthi/st…

James Zou (@james_y_zou) 's Twitter Profile Photo

Interesting that Gemini Flash Thinking has emerged as clinicians' preferred model on #MedArena! 🏅 Clinicians around the world can now use and compare frontier #LLMs for free at medarena.ai/login. #medtwitter

Interesting that Gemini Flash Thinking has emerged as clinicians' preferred model on #MedArena! 🏅 

Clinicians around the world can now use and compare frontier #LLMs for free at medarena.ai/login. #medtwitter
Vivek Natarajan (@vivnat) 's Twitter Profile Photo

Great to see our Google DeepMind Google AI AI co-scientist innovations (multi-agent idea generation tournament) ship fast with Google Cloud Agentspace! Incredible shipping momentum at Google! 🚢 Agentspace -cloud.google.com/products/agent… AI co-scientist - research.google/blog/accelerat…

Khaled Saab (@khaledsaab11) 's Twitter Profile Photo

Really enjoyed collaborating with Anita Rau, Serena Yeung-Levy, and the Stanford crew on this! If we want AI to help in the OR, we need to know what today's VLMs can (and can't) do. Great to see Med-Gemini benchmarked alongside others here in this much-needed, rigorous eval for the

Alan Karthikesalingam (@alan_karthi) 's Twitter Profile Photo

✨New study from our team Google DeepMind Google AI - AMIE goes Multimodal✨ Our research conversational diagnostic AI now fluently considers visual photos/tests. In randomized OSCE study AMIE outperformed PCPs in simulated consultations in which patients uploaded photos of skin

Vivek Natarajan (@vivnat) 's Twitter Profile Photo

Out-the-box gemini 2.0 flash in an agentic framework surpasses doctors in multimodal medical conservations. This is a pretty big deal for medicine. Huge congrats to @KhaledSaab11 Ryu Tanno | 丹野 龍太郎 Jan Freyberg + the whole AMIE team Google DeepMind Google AI on this accomplishment!

David Stutz (@davidstutz92) 's Twitter Profile Photo

AMIE with vision! Patients can now share visual content such as skin images or ECG tracings with AMIE. In a multimodal OSCE study, we show that AMIE outperforms PCPs in requesting and interpreting that information -- a thread 🧵: goo.gle/42D0QcB

Ryu Tanno | 丹野 龍太郎 (@ryutarotanno) 's Twitter Profile Photo

Excited to share a big update on AMIE, our research AI doctor from Google DeepMind and Google AI Now, AMIE can “see” and interpret visual medical data within a diagnostic conversation. Yes, AMIE exceeded human doctors (PCPs) in many key metrics like diagnostic accuracy and

Excited to share a big update on AMIE, our research AI doctor from <a href="/GoogleDeepMind/">Google DeepMind</a> and <a href="/GoogleAI/">Google AI</a> 

Now, AMIE can “see” and interpret visual medical data within a diagnostic conversation.

Yes, AMIE exceeded human doctors (PCPs) in many key metrics like diagnostic accuracy and
Adam Rodman (@adamrodmanmd) 's Twitter Profile Photo

Our multimodal AMIE study is out! This is another exciting step for conversational medical AI – many congrats to the AMIE team! A brief 🧵on what this means for both doctors and patients: x.com/GoogleAI/statu…

Vivek Natarajan (@vivnat) 's Twitter Profile Photo

Excited to share new validation results of our Google DeepMind Google AI AI co-scientist! Addressing the challenge of liver fibrosis, a condition affecting millions globally with few treatments options, we've been working with Dr. Gary Peltz Stanford Medicine, exploring how

Mario Nawfal (@marionawfal) 's Twitter Profile Photo

GOOGLE’S AI JUST DIAGNOSED YOUR RASH... BETTER THAN YOUR DOCTOR Google’s new AI, AMIE, just crushed real doctors in a head-to-head diagnostic battle — and it did it with smartphone photos, blurry PDFs, and zero coffee breaks. In a test with 25 actors playing sick patients, AMIE

GOOGLE’S AI JUST DIAGNOSED YOUR RASH... BETTER THAN YOUR DOCTOR

Google’s new AI, AMIE, just crushed real doctors in a head-to-head diagnostic battle — and it did it with smartphone photos, blurry PDFs, and zero coffee breaks.

In a test with 25 actors playing sick patients, AMIE
Khaled Saab (@khaledsaab11) 's Twitter Profile Photo

As we continue to see step changes in base model capabilities, our ability to advance human knowledge and unlock scientific progress accelerates 🔭🧪🩻

David JH Wu, MD (@davidjhwu) 's Twitter Profile Photo

Packed house at #AIMI25 for this star-studded panel featuring Emily Alsentzer (Stanford CS), Karan Singhal (OpenAI), @KhaledSaab11 (DeepMind) and Marinka Zitnik (Harvard Biomedical Informatics) and Ethan Goh 🎯: foundational model roadmap for health AI

Packed house at #AIMI25 for this star-studded panel featuring <a href="/Emily_Alsentzer/">Emily Alsentzer</a> (Stanford CS), <a href="/thekaransinghal/">Karan Singhal</a> (OpenAI), @KhaledSaab11 (DeepMind) and <a href="/marinkazitnik/">Marinka Zitnik</a> (Harvard Biomedical Informatics) and <a href="/drethangoh/">Ethan Goh</a> 

🎯: foundational model roadmap for health AI
Sabri Eyuboglu (@eyuboglusabri) 's Twitter Profile Photo

When we put lots of text (eg a code repo) into LLM context, cost soars b/c of the KV cache’s size. What if we trained a smaller KV cache for our documents offline? Using a test-time training recipe we call self-study, we find that this can reduce cache memory on avg 39x

When we put lots of text (eg a code repo) into LLM context, cost soars b/c of the KV cache’s size.

What if we trained a smaller KV cache for our documents offline? Using a test-time training recipe we call self-study, we find that this can reduce cache memory on avg 39x
Khaled Saab (@khaledsaab11) 's Twitter Profile Photo

Early detection of neurodegenerative disease has been a major challenge, often requiring invasive tests or waiting for clear symptoms. The stellar team Prima Mente are tackling this challenge head on by building epigenetic foundation models that analyze DNA fragments in the