Google has unveiled a suite of generative AI models, called MedLM, for the healthcare sector that can be used for clinic documentation, pre-clinical drug research, among others.

Being called a family of foundation models, MedLM is built on Med-PaLM 2, Google’s large language model that can answer questions about a broad range of medical topics.

MedLM is said to be “fine-tuned” for the healthcare domain. At present, it has two models that can be accessed by Google Cloud users in the US on the Vertex AI platform.

The MedLM suite has a large and medium model. The larger model facilities complex activities, while the medium model is ideal for scaling across tasks.

Google said it also plans to introduce its Gemini-based models to the MedLM suite in the future.

In a blog post, the technology giant said: “Healthcare organisations are exploring the use of AI for a range of applications, from basic tasks to complex workflows. Through piloting our tools with different organisations, we’ve learned the most effective model for a given task varies depending on the use case. For example, summarising conversations might be best handled by one model, and searching through medications might be better handled by another.” 

Health tech company Augmedix said that it has been trialling Google Cloud’s Med-PaLM 2 and looks to incorporate MedLM into its stack.

The integration of MedLM is significant for Augmedix clients. Among them is HCA Healthcare, who introduced Augmedix documentation products to its four hospitals.

Augmedix founder, director, and chief strategy officer Ian Shakil said: “Generative AI solutions for use in healthcare delivery require a more tailored and precise approach than general purpose LLMs, which is why we value our strategic partnership with Google Cloud.

“Google Cloud has established its leadership as an AI innovator with solutions specifically designed to address the needs of healthcare providers.”