AI shows prostate cancer is not just one disease: Study

Scientists have used artificial intelligence (AI) to reveal a new form of aggressive prostate cancer which they said could help thousands of lives by revolutionising how the disease is diagnosed and treated in the future.

The study, published in the journal Cell Genomics, reveals that prostate cancer, which affects one in eight men in their lifetime, includes two different subtypes termed evotypes.

The findings, led by researchers at the University of Oxford, and the University of Manchester, UK, could help provide tailored treatments to each individual patient according to a genetic test which will also be delivered using AI, they said.

“Our research demonstrates that prostate tumours evolve along multiple pathways, leading to two distinct disease types,” said lead researcher Dan Woodcock, from the University of Oxford.

“This understanding is pivotal as it allows us to classify tumours based on how the cancer evolves rather than solely on individual gene mutations or expression patterns,” Woodcock said.

The researchers worked together as part of international consortium, called The Pan Prostate Cancer Group, set up by scientists at The Institute of Cancer Research (ICR) and The University of East Anglia, UK, to analyse genetic data from thousands of prostate cancer samples across nine countries.

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

The researchers used AI to study changes in the DNA of prostate cancer samples, using whole genome sequencing, from 159 patients.

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

They went on to integrate all the information to generate an evolutionary tree showing how the two subtypes of prostate cancer develop, ultimately converging into two distinct disease types termed ‘evotypes’.

“This realisation is what enables us to distinguish the disease types. This hasn’t been done before because it’s more complicated than HER2+ in breast cancer, for instance,” said Professor David Wedge of Manchester Cancer Research Centre, who led the study.

”This understanding is pivotal as it allows us to classify tumours based on their evolutionary trajectory rather than solely on individual gene mutations or expression patterns,” Wedge said.

Professor Colin Cooper, from UEA’s Norwich Medical School, highlighted that while prostate cancer is responsible for a large proportion of all male cancer deaths, it is more commonly a disease men die with rather than from.

This means that unnecessary treatment can often be avoided, sparing 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 disease. But it is only now, with advancements in artificial intelligence, that we have been able to show that there are actually two different subtypes at play,” he added.