Hello Everyone,
Welcome back.
We got to talk about Med Gemini.
So why is this important?
Advent of Med-Gemini
▪ Med-Gemini is Google’s new family of multimodal models for medicine unlocking new possibilities for health
▪ Med-Gemini, a family of Gemini based models for medicine, demonstrating a new SOTA on MedQA, multimodal and long-context abilities, among others
Google’s Med-Gemini Model Achieves 91.1% Accuracy in Medical Diagnostics
Alan Karthikesalingam MD PhD is a big part of this launch.
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.
More accurate multimodal conversations about medical images🩻, surgical videos📽️, genomics🧬, ultra-long health records📚, ECGs🫀 & more with state-of-art performance across multiple benchmarks
I actually want Google, Microsoft and Amazon to do well in AI with healthcare, so this is not a rebuttal for sure. The benefits would be high if LLMs get better in healthcare settings.
Med-Gemini sets a 🆕 state-of-the-art of 91.1% in MedQA-USMLE + outperforms GPT-4 models by an average relative margin of 44.5% on 7 multimodal benchmarks including NEJM Image Challenges.
Keep reading with a 7-day free trial
Subscribe to Artificial Intelligence Survey 🤖🏦🧭 to keep reading this post and get 7 days of free access to the full post archives.