Study finds that prostate cancer is not a single disease, according to AI analysis

Researchers have utilized artificial intelligence (AI) to uncover a previously unidentified type of aggressive prostate cancer, potentially transforming the way the disease is detected and managed, ultimately saving countless lives.

A study published in the journal Cell Genomics reveals that prostate cancer, which affects one in eight men in their lifetime, has two distinct subtypes, called evotypes.

They said the findings, led by researchers from the University of Oxford and the University of Manchester in the UK, could help provide tailored treatments for each individual patient based on the genetic test, which is also delivered by artificial intelligence.

“Our study shows that prostate tumors develop through multiple pathways, leading to two different types of disease,” said lead researcher Dan Woodcock of the University of Oxford.

“This understanding is key because it allows us to classify tumors based on how the cancer develops, rather than just individual gene mutations or expression patterns,” Woodcock said.

The researchers worked together as part of an international consortium called The Pan Prostate Cancer Group, founded by researchers from The Institute of Cancer Research (ICR) and the University of East Anglia, UK, to analyze genetic data from thousands of prostate cancer samples around the world. in nine countries.

The team’s collaboration with Cancer Research UK (CRUK) aims to develop a genetic test that, when combined with conventional staging and classification, can provide a more accurate prognosis for each patient, enabling tailored treatment decisions.

Researchers used artificial intelligence to examine changes in the DNA of prostate cancer samples using whole-genome sequencing from 159 patients.

Using an AI technique called neural networks, they identified two distinct cancer groups among these patients. These two groups were confirmed using two other mathematical approaches applied to different aspects of the data. This finding was confirmed in other independent data from Canada and Australia.

They went on to integrate all the data to create an evolutionary tree showing how the two subtypes of prostate cancer develop, eventually converging on two distinct types of the disease called “evotypes.”

“This insight allows us to distinguish between disease types. This has not been done before because it is more complex than HER2 in, for example, breast cancer,” says Professor David Wedge from Manchester Cancer Research Centre, who led the study.

“This understanding is key because it allows us to classify tumors based on their evolutionary trajectory, rather than just individual gene mutations or expression patterns,” Wedge said.

Professor Colin Cooper, from UEA’s Norwich Medical School, stressed that although prostate cancer is responsible for a large proportion of men’s cancer deaths, it is more commonly the disease that men die from rather than from it.

This means that unnecessary treatment can often be avoided, saving men from side effects such as incontinence and impotence.

“This study is really important because until now we thought that prostate cancer was just one type of the disease. But only now, with advances in artificial intelligence, have we been able to show that there are actually two different subtypes at play,” he added.