Prostate tumours evolve in two distinct disease types, a new artificial intelligence (AI) study by the Pan Prostate Cancer Group has revealed, which may lead to better diagnosis and tailored treatments in future.
This international consortium of researchers, led by the universities of Oxford and Manchester, analyses genetic data from thousands of prostate cancer samples across nine countries and is aiming 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.
For this particular study, they used AI neural networks to process data on changes in the DNA of prostate cancer samples from 159 patients in the UK.
Samples were taken after radical prostatectomy in patients with intermediate or lower risk prostate adenocarcinoma who were otherwise treatment naive.
Published in the journal Cell Genomics, the results generated an evolutionary tree that took multiple routes to two ‘evotypes’, or subgroups, of prostate cancer.
These two prostate cancer subtypes were confirmed by using two other mathematical approaches applied to different aspects of the data, as well as being validated in other independent datasets from Canada and Australia.
It is hoped that these findings could save thousands of lives in future by revolutionising how prostate cancer is diagnosed and providing tailored treatments to individual patients according to a genetic test, which will also be delivered using AI, the researchers said.
Professor Colin Cooper, professor of cancer genetics at the University of East Anglia’s Norwich Medical School, who was involved in the research, said: ‘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.
‘We hope that the findings will not only save lives through better diagnosis [of prostate cancer] and tailored treatments in the future, but they may help researchers working in other cancer fields better understand other types of cancer too.’
Prof David Wedge, lead researcher and professor of cancer genomics and data science at the Manchester Cancer Research Centre, added: ‘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.
‘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.’
As well as this project in prostate cancer, AI is being used in a number of new clinical studies into disease areas such as cardiovascular disease.
And neural networks in particular have previously been used, for example, in an AI study of Parkinson’s disease, which revealed four subtypes of the disease.
