Google Announces Med-Gemini AI Models for Healthcare Use

Google has introduced Med-Gemini, a family of multimodal models built upon Gemini specifically designed for the healthcare industry. While the models are still unavailable for public or beta testing, the tech giant has published a detailed pre-print version in its research paper available on arXiv.

A notable feature of the AI model is its long-context ability, which enables better processing of health records and research papers. Further, all of the AI models are multimodal and can provide text, image, and video outputs.

Jeff Dean, Chief Scientist at Google DeepMind and Google Research, shared his excitement on X (formerly known as Twitter) saying, “I'm very excited about the possibilities of these models to help clinicians deliver better care, as well as to help patients better understand their medical conditions. AI for healthcare is going to be one of the most impactful application domains for AI, in my opinion.”

Google claims that Med-Gemini AI models have outperformed OpenAI's GPT-4 models in the GeneTuring dataset on text-based reasoning tasks.

Med-Gemini AI models are built on top of Gemini 1.0 and Gemini 1.5 LLM. There are four versions: : Med-Gemini-S 1.0, Med-Gemini-M 1.0, Med-Gemini-L 1.0, and Med-Gemini-M 1.5. 

Reportedly, Med-Gemini-L 1.0 has outperformed its predecessor Med-PaLM 2 by 4.5 percent by scoring 91.1 percent accuracy on MedQA (USMLE).

Web search integration has made the models “more factually accurate, reliable, and nuanced,"  which reflects in the results for complex clinical reasoning tasks, says Google. Moreover, the AI model is fine-tuned for improved performance during long-context processing.

According to Google, higher-quality long text processing would enable the chatbot to provide accurate and pinpoint answers to imperfect queries or during massive medical record processing.

The tech giant is focused on improving the model further before bringing it into the public domain.