New AI technology can detect early signs of more than 1,000 diseases, long before symptoms appear, according to a new study.
The computer algorithm, called MILTON, analyzes patient test results typically collected by GPs to detect trends in the data and predict with high confidence a disease diagnosis several years later.
The pharmaceutical giant AstraZeneca, which developed the artificial intelligence tool, said it would accelerate the development of more effective and targeted treatments.
But it also makes the data freely available to other researchers, who could develop diagnostic tests that enable early preventive treatment to stop diseases in their tracks.
Keep up to date with all the latest news from the UK and around the world by following Sky News
Slave Petrovski, who led the research, told Sky News: “For many of these diseases, at the point when they manifest clinically and the individual goes to the doctor due to illness or observation visible which is very distant from the time when the disease develops. began.
“There may have been a whole cascade of events that happened in the blood before it became symptomatic.
“We can detect signatures in an individual that are highly predictive of the development of diseases such as Alzheimer’s disease, chronic obstructive pulmonary disease (COPD), kidney disease and many others.”
AstraZeneca used data from 500,000 people who were part of the UK Biobank, a large repository of health information.
MILTON analyzed data from 67 routine clinical biomarkers, including detailed results of blood and urine tests, blood pressure and respiratory performance checks, as well as weight, age and gender.
The study also examined data from 50,000 Biobank volunteers on 3,000 proteins found in blood plasma that play critical roles in many bodily functions, including the immune and hormonal systems.
The results of blood pressure checks were included in various data used by AstraZeneca. File photo: iStock
“Exceptional” performance for 121 diseases
The AI tool was able to detect subtle patterns in the data that would have been invisible to the human eye and link them to illnesses that patients were diagnosed with up to a decade or more later.
Its predictive performance was rated “outstanding” for 121 diseases and “highly predictive” for 1,091 others, according to the study published in the journal Nature Genetics.
Even if routine biomarkers collected by GPs were predictive, the addition of analysis of 3,000 proteins – which is not expected to significantly increase the cost of blood tests – significantly increased MILTON’s power to report patients at risk.
Dr. Petrovski said this discovery opens the possibility of intervening much earlier in the disease process.
“It is always possible to combine lifestyle with (pharmaceutical) interventions to achieve the best health benefits,” he said.
“Often when we look at diseases, they are at later stages and therefore are difficult to reverse.
“The goal would be to intervene earlier and manage the disease to ensure it does not progress.”
AstraZeneca emphasizes that MILTON is currently a research tool and that additional work needs to be done before it can be used clinically by doctors.
Read more on Sky News:
Apple launches new phone and AI in major event
A robot dentist performs the first automated procedure
“The impact will be on improving our knowledge of diseases”
Professor Tim Frayling, professor of human genetics at the University of Exeter, was also cautious.
He said: “We need to be careful when we claim we can ‘predict disease’ when we really mean ‘we can give you a slightly better idea of your chances of developing disease, but there are still many factors unknown”.
“This approach will likely have more impact on improving our knowledge of how diseases develop rather than who exactly will develop them.”
Expert worries about ethical use of tool
Professor Dusko Ilic, of Stem Cell Sciences, King’s College London (KCL), said MILTON’s predictive power was “remarkable”, opening up the possibility of earlier intervention, more personalized treatments and healthcare costs lower.
But he warned: “I have some concerns about its ethical use.
“The powerful predictive capabilities of this tool could, if left unregulated, be misused by health insurance companies or employers to evaluate individuals without their knowledge or consent. This could lead to discrimination and a violation of privacy.
“Strict guidelines and oversight will be essential to ensure MILTON’s benefits are realized in an ethical and responsible manner.”
