Algorithms can revolutionize healthcare, but who will seize the initiative?
Google is testing Med-PaLM 2, a chatbot trained on a set of medical expert demonstrations, and that can hold a conversation about healthcare-related issues.
The company began testing the system with patients at the Mayo Clinic in April: the algorithm can generate answers to medical questions and perform automated tasks such as summarizing documents or organizing large amounts of health data obtained from a variety of sources.
These types of algorithms form the basis of the future preventive medicine systems that will characterize health care in developed countries: patients constantly generating large amounts of data on their health parameters thanks to wearables and simple everyday devices, which feed them to algorithms capable of generating the equivalent of a digital twin, a picture of their state of health that could be used for assessing the need for more intensive tests or examinations.
In principle, Med-PaLM 2 is a Large Language Model (LLM) specifically trained with health data to answer questions ranging from diagnostics to queries about symptoms. The decision to use canonical data formulated in medical qualification exam questions is simply a matter of caution: training it with real data from medical records raises numerous confidentiality and privacy…
