AI for Health @ Google | Staff Research Scientist
Toronto
Joined March 2012
- Tweets137
- Following229
- Followers510
- Likes357
Pinned Tweet
Our teams @Google + @BIDMC_Medicine publish world's first prospective study of a patient-facing conversational diagnostic intelligence @TheLancet - Go #AMIE team!!! blog.google/innovation-and-a…
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!
Mike Schaekermann retweeted
Amazing to see research move from the lab to real-world clinical utility - congrats to the team on this milestone & @TheLancet paper!
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!
New perspective from our #AMIE team at @Google in @NatureMedicine: Prospective evidence for conversational medical AI is hard, but non-negotiable 🔗 nature.com/articles/s41591-0… + rdcu.be/Pgr1WwyjF9Ca
@AdamRodmanMD @AmiParekh10 @drethangoh @cameronphchen @apalepu13 @ymatias +more!
Trust in medical AI hasn't been earned yet.
But it potentially can be with randomized trials conducted in real world medicine
@NatureMedicine @HardyShakerman @cameronphchen
nature.com/articles/s41591-0…
Mike Schaekermann retweeted
@Google's clinical conversational agent continues to improve: Integrating visual (eg, sees patient wrapped in a blanket; observes parts of a physical exam) & audio (hears a cough) into a video consult. V impressive.
Paper: arxiv.org/pdf/2608.09861
Video: youtube.com/watch?v=ISlPOC0q…
Mike Schaekermann retweeted
First time this has been assessed:
Can AI do a video consult with a patient better than a primary care physician?
A new medical AI study demonstrates the diagnostic accuracy advantage of using video (AMIE) over pure text for patient telehealth consultations. A randomized trial of 100 clinical cases, 30 physicians (PCPs), w/ patient actors. 3 arms: AI with video, PCPs with video, text only; main results in Figure (preprint)
arxiv.org/abs/2608.09861v1
Mike Schaekermann retweeted
1/ Medical students don't become doctors by memorizing facts and passing exams. They do by residency, years of practice across thousands of patient encounters.
We wanted to see if we could train models the same way.
Introducing ResidencyRL 🧵
Mike Schaekermann retweeted
Doctors don't become doctors from textbooks. They become doctors through residency, requiring years of practice across thousands of patient encounters.
Can AI learn the same way?
Introducing ResidencyRL 🧵
AMIE showed AI can match PCPs in clinical reasoning: eg xitter.cf/GoogleForHealth/status…
ResidencyRL takes the next step: a model with broad medical knowledge becomes a more competent clinician through RL in simulation. As simulations grow richer, so will the competencies they develop.
Mike Schaekermann retweeted
Medical training begins in textbooks, but clinical competence is forged through practice. We introduce ResidencyRL: a multi-turn online RL method to train health agents in simulation, and demonstrate significant gains on top of frontier systems. arxiv.org/abs/2608.07418
ALT Paper visual abstract
A wonderful consensus piece across a broad group of academia, regulatory and industry leaders, driven by @drethangoh ! Now in @NatureMedicine
What is medical AI superintelligence? How will we know if/when it exists? Our essay @NatureMedicine, led by @drethangoh
nature.com/articles/s41591-0…
Mike Schaekermann retweeted
In Nature Medicine, a new perspective from researchers at @Stanford, @Google, and leading experts across major AI labs and academic institutions, explores the need for a rigorous, task-based framework to define and measure medical AI: goo.gle/3REZ4VJ
Mike Schaekermann retweeted
Prevention is a key part of bioresilience and we believe SynthID for biology can be a big part of this - read more about our + @IsomorphicLabs's approach here: deepmind.google/blog/our-app…
Mike Schaekermann retweeted
New @Nature publication from @GoogleResearch & @GoogleDeepMind: In this study, we advance AMIE, our research medical AI, from one-off diagnostic conversations toward treating & managing disease over time, using clinical guidelines & drug formularies. More: goo.gle/4oA0EEb
Mike Schaekermann retweeted
New research published in @Nature with @GoogleDeepMind shows how AMIE utilizes long-context capabilities of Gemini models to ground its clinical reasoning in authoritative medical knowledge.
In a multi-visit study with patient actors, AMIE demonstrated physician-level capabilities in longitudinal management reasoning, while scoring significantly higher in plan preciseness and guideline alignment.
See the full story from @GoogleForHealth below 🧵↓
New @Nature publication from @GoogleResearch & @GoogleDeepMind: In this study, we advance AMIE, our research medical AI, from one-off diagnostic conversations toward treating & managing disease over time, using clinical guidelines & drug formularies. More: goo.gle/4oA0EEb
New @Nature pub from our team @Google on AMIE our conversational medical AI evolving from diagnostic dialogue to managing disease over time w/ drug formularies & clinical guidelines nature.com/articles/s41586-0…
Lead authors @valentinlievin @apalepu13
@GoogleResearch @GoogleDeepMind
Thrilled to share that our paper on AMIE—our conversational medical AI—is now published in @Nature. We wanted to tackle one of the most challenging areas in clinical AI: management reasoning over multiple patient visits.
nature.com/articles/s41586-0…
Mike Schaekermann retweeted
Our paper “Towards Conversational AI for Disease Management” is out in @Nature! We ran a blinded study comparing our multi-agent AMIE system to 21 primary care physicians to test longitudinal patient care management.
🔗 nature.com/articles/s41586-0…
@GoogleDeepMind @GoogleResearch
Mike Schaekermann retweeted
At Google I/O 2026, we shared major breakthroughs. From accelerating scientific discovery with Gemini for Science to transforming everyday experiences with Google Search, we’re catalyzing a new era of innovation. Read the blog to learn more: goo.gle/4dR4tQu
Mike Schaekermann retweeted
The Iso team has cooked something incredible: our new technical report unveils the latest results from our drug design engine, the IsoDDE, progressing far beyond AlphaFold 3. This breaks new ground compared to AF and other similar methods by a significant degree across all key benchmarks. 1/7
Mike Schaekermann retweeted
🚨 Just published in @NatureMedicine: Research from @GoogleResearch, @GoogleDeepMind & @StanfordMed on large language models in complex cardiology care.
Mike Schaekermann retweeted
Improving complex cardiology care with a large language model: a randomized trial (not real world) shows support with AI led to substantial improvement in accuracy and less time
nature.com/articles/s41591-0…
Mike Schaekermann retweeted
Excited to share our latest research published today in @NatureMedicine, demonstrating how Large Language Models (LLMs) can help bridge the critical shortage of subspecialist medical expertise. nature.com/articles/s41591-0…
