AI study reveals prostate cancer consists of two distinct subtypes

13th March 2024

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.

Parkinson’s disease subtypes revealed using machine learning models

14th August 2023

Use of machine learning has enabled scientists to accurately predict four subtypes of Parkinson’s disease based on images of patient-derived stem cells.

Parkinson’s disease is a neurodegenerative condition that affects both movement and cognition. Symptoms and progression vary based on the underlying disease subtype, although it has not been possible to accurately differentiate between these subtypes.

This may well change in the near future as a team based at the Francis Crick Institute and UCL Queen Square Institute of Neurology, together with the technology company Faculty AI, have shown that machine learning can accurately predict subtypes of Parkinson’s disease using images of patient-derived stem cells.

The work, which was published in the journal Nature Machine intelligence, generated a machine learning-based model that could simultaneously predict the presence of Parkinson’s disease as well as its primary mechanistic subtype in human neurons.

In the study, researchers generated stem cells from a patients’ own cells and chemically created four different subtypes of Parkinson’s disease: two involving pathways leading to toxic build-up of the protein α-synuclein and two involving pathways leading to defunct mitochondria. Together, this created a ’human’ model of the disease.

Next, researchers imaged these disease models and ‘trained’ the machine learning algorithm to recognise each subtype, from which it was then able to predict the particular subtype.

Prediction of Parkinson’s disease subtype

The machine learning model enabled researchers to accurately identify a disease state from a healthy control state.

With quantitative cellular profile-based classifiers, the models were able to achieve an accuracy of 82%. In contrast, image-based deep neural networks could predict control and four distinct disease subtypes with an accuracy of 95%.

The machine learning-trained classifiers were able to achieve a level of accuracy across all subtypes, using the organellar features of the mitochondria, with the additional contribution of the lysosomes, confirming the biological importance of these pathways in Parkinson’s disease.

James Evans, a PhD student at the Francis Crick Institute and UCL, and co-first author with Karishma D’Sa and Gurvir Virdi, said: ‘Now that we use more advanced image techniques, we generate vast quantities of data, much of which is discarded when we manually select a few features of interest.

‘Using AI in this study enabled us to evaluate a larger number of cell features, and assess the importance of these features in discerning disease subtype. Using deep learning, we were able to extract much more information from our images than with conventional image analysis. We now hope to expand this approach to understand how these cellular mechanisms contribute to other subtypes of Parkinson’s.‘

Sonia Gandhi, assistant research director and group leader of the Neurodegeneration Biology Laboratory at the Francis Crick Institute, who was also involved in the study, said: ‘We don’t currently have treatments which make a huge difference in the progression of Parkinson’s disease. Using a model of the patient’s own neurons, and combining this with large numbers of images, we generated an algorithm to classify certain subtypes – a powerful approach that could open the door to identifying disease subtypes in life.

‘Taking this one step further, our platform would allow us to first test drugs in stem cell models, and predict whether a patient’s brain cells would be likely to respond to a drug, before enrolling into clinical trials. The hope is that one day this could lead to fundamental changes in how we deliver personalised medicine.‘