⭐Research highlight: Designer antibiotics by #generativeAI : Researchers developed an AI model that designs novel, synthesizable #antibiotic compounds — several of which showed potent in vitro activity against priority pathogens. Nature Machine Intelligence
nature.com/articles/d4159…

Excited to demonstrate in our work published today at Nature Medicine that we can leverage powerful diffusion models to “augment” our medical imaging datasets in a steerable fashion to oversample underrepresented conditions and attributes.

Google DeepMind Google Research

Our new work in Nature Medicine

Using generative models in path, radiology and derm - we can create synthetic training data to ⬆️ AI fairness & robustness, including underrepresented groups. Work w/ a great team Google DeepMind Google AI Google Health

nature.com/articles/s4159…

By generating synthetic image samples specific to underrepresented groups, diffusion models help medical image classifiers to achieve greater #fairness metrics across a variety of medical disciplines and demographic attributes. Olivia W, Ira Ktena nature.com/articles/s4159…

Our latest editorial is out:

'How to support the transition to AI-powered healthcare'

nature.com/articles/s4159…

⚡ Our March issue is live! Featuring several #biomarker and #immunotherapy studies in #CRC , #PancreaticCancer , #HCC and others, studies on #tuberculosis , #cholera , #postnataldepression , foundation #AI , as well as News, Reviews, Opinion and more...
nature.com/nm/volumes/30/…

In our March editorial, we advocate for prospective testing of AI technologies in terms of clinical outcomes, to support an organic, reliable transition to a more sustainable and equitable healthcare system

nature.com/articles/s4159…

⚡️🔬📣Excited to share our two new Nature Medicine articles, we develop computational pathology foundation models,

1. UNI, a self-supervised computational pathology model trained on 100 million pathology images from 100k+ slides.
2. CONCH, a vision-language model for…

I hope to meet some of you at the various meetings I'll be attending in the following months:
- Advancing Health with AI (Wenzhou, 26-28/4)
- Symposium on AI for Learning Health Systems (Puerto Rico, 7-10/5)
- #EULAR2024 (Vienna, 12-15/6)
- Digital Mental Health & Wellbeing, 19-21 June 2024 (Derry, 19-21/6)

Please do reach out if you are also going!

When #AI support was provided to 140 radiologists, there was marked variability and unpredictability as to its impact on performance
nature.com/articles/s4159… Nature Medicine Pranav Rajpurkar Feiyang (Kathy) Yu

A large-scale study examined the heterogeneous effects of AI assistance on 140 radiologists across 15 chest X-ray diagnostic tasks, finding that conventional experience-based factors fail to reliably predict the impact of AI assistance Pranav Rajpurkar

nature.com/articles/s4159…

Who benefits from AI?

Our new study with 140 radiologists in Nature Medicine challenges prevailing assumptions.

We find years of experience, subspecialty and familiarity with AI tools fail to reliably predict the impact of AI assistance.

nature.com/articles/s4159…

Analyzing clinical records from a cohort of 3,042 donors in the Netherlands Brain Bank, natural language processing models unveil the symptomatology and potential misdiagnoses of a broad range of neurodegenerative disorders

nature.com/articles/s4159…

A modelling study of 35 cholera-endemic countries in Africa showed that introducing #Cholera surveillance could improve the effectiveness and cost-effectiveness of preventative cholera vaccination campaigns.
nature.com/articles/s4159…

Denosumab, a receptor activator of nuclear factor-kB ligand inhibitor, previously developed for osteoporosis, was shown to be effective at inducing structural modification in patients with erosive hand #Osteoarthritis after 24 weeks UGent nature.com/articles/s4159…

Our clinical #NLP work just published in Nature Medicine! We present a framework to adapt & evaluate #LLM s for summarization. Physicians 🩺 prefer #LLM summaries to those of #medical experts❗

Big step to reduce documentation 📚 and focus more on personalized care 🙌

A 🧵

Really excited to see our Q&A on Clinical Trial Disparities with me and Sabine Oertelt-Prigione @[email protected] published in Nature Communications. nature.com/articles/s4146…

Many thanks to Andy Jobbins, PhD for assembling this team and for putting it all together.