Microsoft: GPT-4 has great potential in health care, and its own "LLaVA-Med" model can accelerate related nursing and research.

CTOnews.com, August 14 (Xinhua)-- large-scale models such as GPT-4 have great potential in the medical field, which can help speed up the medical process and build more accurate pathological models by pooling large-scale patient data to improve the efficiency of medical drug development, Microsoft's research team said a few days ago.

Microsoft claims that GPT-4 is actually even better than medical tools such as Criteria2Query on the market, and although GPT-4 is only trained in "general" Internet data rather than specific medical data, it is still enough to build complex clinical studies according to specified medical standards and play a greater role in processing medical images and other biological data.

▲ Image Source Microsoft CTOnews.com reported earlier that Microsoft is currently developing a LLaVA-Med medical model based on GPT-4 to provide biomedical imaging data to medical professionals. Microsoft claims that its "LLaVA-Med" model can accelerate care and research related to the medical industry.

Microsoft has also launched language models such as BioGPT specifically for medical tasks, but Microsoft is betting on its OpenAI, relying on GPT-4 to develop a dedicated medical model.