{"entity":{"id":"med-gemini","kind":"technology","name":"Med-Gemini and MedLM (Google)","aka":[],"tldr":"Google's medical versions of its Gemini models, able to reason over text, images, and long records.","summary":"Med-Gemini is Google's family of medical models built on the Gemini large multimodal transformer, fine-tuned on medical data and given web search integration so it can reason over text, images and long records. The 2024 arXiv paper reported state-of-the-art results on medical exam and multimodal benchmarks, while MedLM is the commercial line offered to health systems. The intended users are developers and health systems building assistants for documentation, question answering and image interpretation. The evidence is benchmark-heavy and deployment evidence is thin; oncology-specific evaluations remain limited, so its value in tumour boards or treatment planning is not established. For a newcomer: Med-Gemini is Google's medical version of its general AI, strong on exams but not yet proven in cancer care.","status":"emerging","asOf":"2026-09-08","links":[{"label":"Med-Gemini (arXiv 2024)","url":"https://arxiv.org/abs/2404.18416"}],"tags":["foundation-model","llm"],"related":[],"cancers":[],"sections":["ai-computation"],"technologies":["ai-trial-matching"],"targets":[],"drugs":[],"companies":["google-deepmind"],"institutions":[],"pathways":[],"terms":[],"trials":[],"people":[],"bottlenecks":[],"keyPapers":[],"journals":[],"dependsOn":[],"notes":[],"principle":"Med-Gemini is a large multimodal transformer fine-tuned on medical data, with web search integration.","strengths":["Multimodal breadth"],"limitations":["Benchmark-heavy evidence; deployment evidence thin"],"since":2024},"route":"/technologies/med-gemini/","neighbours":{"section":[{"id":"ai-computation","kind":"section","name":"AI & Computation","route":"/fronts/ai-computation/"}],"technology":[{"id":"ai-trial-matching","kind":"technology","name":"AI trial matching & clinical decision support","route":"/technologies/ai-trial-matching/"}],"company":[{"id":"google-deepmind","kind":"company","name":"Google DeepMind (and Google Research)","route":"/companies/google-deepmind/"}],"roadmap":[{"id":"ai-oncology-roadmap","kind":"roadmap","name":"AI in oncology roadmap: pattern readers → foundation models → agents in the workflow","route":"/roadmaps/ai-oncology-roadmap/"},{"id":"ai-oncology-clinic","kind":"roadmap","name":"AI in the oncology clinic: from narrow cleared tools to multimodal decision support","route":"/roadmaps/ai-oncology-clinic/"}]}}