0 reply
0 recast
0 reaction
Healthcare is increasingly embracing AI to improve workflow management, patient communication, and diagnostic and treatment support. It’s critical that these AI-based systems are not only high-performing, but also efficient and privacy-preserving. It’s with these considerations in mind that Google built and recently released Health AI Developer Foundations (HAI-DEF). HAI-DEF is a collection of lightweight open models designed to offer developers robust starting points for their own health research and application development. Because HAI-DEF models are open, developers retain full control over privacy, infrastructure and modifications to the models. In May of this year, Google expanded the HAI-DEF collection with MedGemma, a collection of generative models based on Gemma 3 that are designed to accelerate healthcare and lifesciences AI development.
Today, Google announced two new models in this collection. The first is MedGemma 27B Multimodal, which complements the previously-released 4B Multimodal and 27B text-only models by adding support for complex multimodal and longitudinal electronic health record interpretation. The second new model is MedSigLIP, a lightweight image and text encoder for classification, search, and related tasks. MedSigLIP is based on the same image encoder that powers the 4B and 27B MedGemma models.
https://research.google/blog/medgemma-our-most-capable-open-models-for-health-ai-development/ 1 reply
0 recast
2 reactions
