Google is making strides in the field of medical AI with its latest chatbot, Med-PaLM 2. The tech giant is currently conducting tests of the AI chatbot at renowned medical institutions like the Mayo Clinic in the United States. Med-PaLM 2 is built upon Google's PaLM 2 large language model (LLM), which powers its ChatGPT rival, Bard.
Unlike the base model, Med-PaLM 2 has been specifically trained on medical licensing exam questions and answers, as well as a curated set of demonstrations by medical experts. This specialized training equips the chatbot with the ability to answer health-related queries and perform labor-intensive tasks such as document summarization and research data organization.
Med-PaLM 2 can help answer questions and summarize insights from a variety of dense medical texts. We’re working to add more capabilities to Med-PaLM 2, so that it can synthesize information from medical imaging like mammograms or help radiologists interpret results. #GoogleIO
— Google (@Google) May 10, 2023
During Google's recent I/O event, the company released a paper detailing the features and capabilities of Med-PaLM 2. The chatbot demonstrated impressive attributes, including alignment with medical consensus, reasoning ability, and the generation of answers preferred by respondents over physician-generated responses.
However, like other AI chat models, Med-PaLM 2 also exhibited some accuracy issues.
While Google acknowledges that Med-PaLM 2 is still in its early stages, the company believes the updated model could be of tremendous value, particularly in regions with limited access to doctors.
