AstraZeneca has developed artificial intelligence research tool ‘MILTON’, which it says is capable of predicting diseases years before a diagnosis.
According to the pharmaceutical giant, MILTON can leverage data from nearly 500,000 people to identify if someone has a higher risk of contracting a disease.
It believes this tool will speed up the process of discovering new drug targets and biomarkers, leading to the development of more effective treatments.
Heading the research, Slavé Petrovski, Vice President, Centre for Genomics Research at AstraZeneca, commented on the significance of the AI tool: “MILTON is a significant advance on the predictive tools currently used.
“Our research demonstrates MILTON’s capabilities and how it is able to identify disease risk cases in large biobank datasets, which in the future, could enable us to detect illnesses earlier and at more treatable stages.
“Improving our ability to detect illnesses earlier and at more treatable stages is critical for early interventions in clinical care.”
The name MILTON stands for ‘MachIne Learning with phenoType associatiONs’. It was built from 67 routine clinical biomarkers and it includes data from 3,000 plasma protein measurements for a smaller group of 50,000 participants.
It reportedly analysed 3,200 diseases with a ‘high’ predictability level for 1,091 diseases and ‘exceptional’ performance for 121 diseases.
The findings have yielded possible new biomarker signatures that can be used to predict diseases years before an official diagnosis has been made.
AstraZeneca claims that MILTON’s capabilities will improve drug target discovery in genetic studies of large populations.
Traditionally, case-control studies, self-reported data, and hospital billing codes may not complete their classifications of participants into cases or controls. MILTON, however, can highlight cases where individuals have been incorrectly classified as controls.
With AI-augmented reclassifications, the statistical power for genetic discovery is significantly increased, making the process of uncovering genes associated with disease more accurate.
Professor Tim Frayling, Professor of Human Genetics at the University of Exeter, told Sky News that it is important to accurately clarify its achievement:
“We need to take care when claiming we can ‘predict disease’ when we really mean ‘we can give you a slightly better idea of your chances of developing a disease but there are still many unknown factors’.
“This approach will likely have more impact on improving our knowledge of how diseases develop rather than who exactly will develop them.”
The predictive capabilities of MILTON can be used in any biobank, whatever the genomic ancestry.
The Cambridge-based pharmaceutical company pointed out that MILTON will continue to improve as it adds new capabilities. For example, adding extra proteomic data will allow MILTON to predict a broader set of diseases.
A Word of Warning
Prof Dusko Ilic, of Stem Cell Sciences, King’s College London (KCL), also spoke to Sky News about some of the ethical concerns he has: “I have some concerns regarding its ethical use.
“The powerful predictive abilities of this tool could, if unregulated, be misused by health insurance companies or employers to assess individuals without their knowledge or consent. This could lead to discrimination and a breach of privacy.
“Strict guidelines and oversight will be critical in ensuring that the benefits of MILTON are realised in an ethical and responsible manner.”
There was more AI news connected to the UK recently as the country’s Lord Chancellor signed an international treaty designed to protect people from the threats posed by artificial intelligence.
