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 issues. However, this is a regulatory issue that can be easily overcome once adequate anonymization systems are put in place and the regulator is aware of the enormous advances in medical science that can emerge from massive processing of real patient data.
We are at an extremely important moment in the history of medicine: the leap from palliative medicine that can only operate on the basis of visible symptoms, to a genuinely preventive medicine in which patients need not be aware that they have a problem: it is simply necessary for the algorithm to detect some kind of anomaly and assess it as something that deserves further, more detailed examination, so that they can be called by their doctor, who before seeing them can receive full information about the situation that has triggered the alert, and request the relevant tests.
Wearables, in reality, should never have been intended to be interpreted by the user (image in Spanish), who generally lacks the appropriate knowledge and experience. Both these devices and other diagnostic tests intended to be carried out on a daily basis are actually intended to feed algorithmic systems capable of maintaining active monitoring and initial diagnosis in anomaly detection mode. Systems based on generative algorithms providefeedback and care, but the real issue, making it possible to reduce patient suffering and the cost of medical care, relates to other types of algorithms focused on prediction. Moreover, they will give rise to a whole new generation of research in medical science, with much larger volumes of data.
It is not a question of cost, but ambition: the managers of national health systems are not yet aware of the enormous potential of LLMs, and how they could put a country at the forefront of medical research. Whoever is capable of approaching it ambitiously enough will reap huge rewards, and it is hard to imagine that it will be countries like the United States, where a simple diagnostic test used to corroborate the data of a device is still unaffordable for most families. More ambition can be expected in systems that are universal but subject to numerous sustainability problems such as those in the United Kingdom, Spain, Germany or, eventually, small social “laboratories” such as Singapore.
The time to change the scale of care and research in medical science is now. The question is who is prepared to take the lead.
(En español, aquí)
—
This post was previously published on MEDIUM.COM.
***
You may also like these posts on The Good Men Project:
 Escape the Act Like a Man Box |
 What We Talk About When We Talk About Men |
 Why I Don’t Want to Talk About Race |
 The First Myth of the Patriarchy: The Acorn on the Pillow |
Join The Good Men Project as a Premium Member today.
All Premium Members get to view The Good Men Project with NO ADS.
A $50 annual membership gives you an all access pass. You can be a part of every call, group, class and community.
A $25 annual membership gives you access to one class, one Social Interest group and our online communities.
A $12 annual membership gives you access to our Friday calls with the publisher, our online community.
Register New Account
Log in if you wish to renew an existing subscription.
Username
First Name
Last Name
Password
Password Again
Choose your subscription level
- Yearly – $50.00 – 1 Year
- Monthly – $6.99 – 1 Month
Credit / Debit Card PayPal Choose Your Payment Method
Auto Renew
Subscribe to The Good Men Project Daily Newsletter By completing this registration form, you are also agreeing to our Terms of Service which can be found here.
Need more info? A complete list of benefits is here.
—
Photo credit: iStock.com
The post Algorithms Can Revolutionize Healthcare, but Who Will Seize the Initiative? appeared first on The Good Men Project.
