Thrilled to share our new Cell paper discussing state-of-the-art in #ML for #cancer detection, treatment and monitoring! authors.elsevier.com/a/1gjhVL7PXmbbo Topics include ML for: -imaging diagnosis -liquid biopsy -which #ML are FDA-approved/deployed -new omic tech + opportunities

We should be very cautious when using detectors to classify if text is written by #AI or human. We find these detectors classify >50% of real text by non-native English speakers as AI-generated. OTOH most #GPT polished essays evade detection arxiv.org/pdf/2304.02819…

My new @MBoCjournal bioRxiv highlight is out! Eric Wu, @atrev_bio, Aaron Mayer, and James Zou Enable Medicine present 7-UP, computationally generating single-cell 40 protein expression markers from 7 multiplexed immunofluorescence markers 🔥 molbiolcell.org/doi/full/10.10…

In "Leveraging #Physiology & #AI to Deliver Advancements in #Healthcare" Zhang et al. explore how past work has shaped the field & defined future challenges - new in Physiological Reviews! ow.ly/o62q50O1ynE Joseph C Wu, MD, PhD James Zou Stanford Medicine Stanford Engineering #MachineLearning

Method alert: Machine learning can help with the challenge of interpreting imaging of 40+ protein biomarkers enabled by CODEX systems. A machine learning framework called 7-UP can classify cell types and predict patient survival outcomes. In PNAS Nexus: ow.ly/U5FJ50OBKKH

(1/) We’re excited to share our NEW machine learning framework called 7-UP, which increases the resolution of low-plex images from 7-plex to 40-plex to enable more complex analysis without needing to generate high-plex images. #bioinformatics #machinelearning #spatialbiology

🧃New PNAS Nexus paper on 7-UP #AI🧃 We develop 7-UP, an AI that can computationally generate 30+ new antibody stains from 7 common biomarkers. It uplevels existing immunofluorescent images into spatial proteomics for richer analysis. academic.oup.com/pnasnexus/arti…

Another bias: If you're a non-native English writer, GPT detectors will frequently classify your writing as #AI-generated cell.com/patterns/fullt… James Zou Weixin Liang Stanford University

Introducing PEPSI🥤, our new method to identify tumor-immune cell interactions from tissue imaging. Incorporating this interaction helps predict how patients respond to cancer therapies. #PSB paper psb.stanford.edu/psb-online/pro… Great job by Eric Wu collaborating w/ Enable Medicine!

Want to compare how different LLMs handle your medical queries—for free? Excited to share MedArena 🏥, the first public medical chatbot arena where clinicians can evaluate and rank the latest medical LLMs! 🏆 If you are a licensed healthcare professional, we welcome you to submit

📢Thrilled to introduce #MedArena medarena.ai 🏥, a platform for clinicians to try frontier #LLMs for free (o3, Gemini, Perplexity + more). Compare and rank medical chatbots and help shape the future of medical AI! 🏆 Current leaderboard👇 Please share #MedTwitter

Introducing MedArena medarena.ai/app/?__theme=l… for clinicians to ask medical questions and compare results of LLM models James Zou Doximity

I encourage every doctor to try out MedArena -- a Turing test of AI models on the tasks that YOU think are important!

Excited to share early updates from MedArena 🏥✨! 1⃣ Current frontrunner: Perplexity 🤖, closely followed by Gemini 2.0 Flash Thinking 🌟—but the competition's just warming up! 🔥 2⃣ Great news: MedArena is global 🌍! Non-US clinicians are welcome—just provide your

Due to popular request, #medarena is now open to global clinicians! medarena.ai/login

Really cool way to evaluate LLMs for medicine in blinded fashion. It really helps build intuition on what works and doesnt. For example, I really like that there is RAG in some models (able to cite literature and references claims), but I've found when I've clicked into some of

Hey #MedTwitter - Want to see how different LLMs handle your medical qs—for free? Check out MedArena 🏥, the first public arena where clinicians can evaluate and rank the latest medical LLMs. Go to medarena.ai to try it out! Eric Wu Kevin Wu James Zou

Zou Lab launches MedArena, a free platform for clinicians to use and compare frontier LLMs MedArena is a free platform for clinicians to use and compare how frontier LLMs work on medical queries. Check it out at: medarena.ai/login

Does RAG solve hallucination? Even w/ RAG, we found that >30% of LLMs' medical statements are not fully supported by (sometimes contradict) the cited refs Nature Communications nature.com/articles/s4146… We present #SourceCheckUp agent to verify faithfulness of LM to source info. Great job