Can machine learning predict ovarian cancer survival?
Machine learning software can lead the way towards more personalised medicine, predicting patient outcomes with significantly more accuracy than current methods
Researchers at Imperial College London and the University of Melbourne have created new machine learning software that can forecast the survival rates and response to treatments of patients with ovarian cancer.
The software has been able to predict the prognosis of patients with ovarian cancer significantly more accurately than current methods. It can also predict what treatment would be most effective for patients following diagnosis, paving the way for more personalised medicine.
Ovarian cancer is the sixth most common cancer in women, with 6,000 new cases every year in the UK. However, the long-term survival rate is just 35-40 per cent, as the disease is often only diagnosed in later stages once symptoms such as bloating are noticeable.
Professor Eric Aboagye, lead author and Professor of Cancer Pharmacology and Molecular Imaging at Imperial, said: “There is an urgent need to find new ways to treat the disease. Our technology is able to give clinicians more detailed and accurate information on how patients are likely to respond to different treatments, which could enable them to make better and more targeted treatment decisions.”
Doctors currently diagnose ovarian cancer in a number of ways: including a blood test to look for a substance called CA125 – an indication of cancer - followed by a CT scan that uses x-rays and a computer to create detailed pictures of the ovarian tumour. This helps clinicians know how far the disease has spread and determines the type of treatment patients receive, such as surgery and chemotherapy.
However, the scans cannot give clinicians detailed insight into patients’ likely overall outcomes or the probable effect of a therapeutic intervention. The new software aims to address these problems.
The trial used a mathematical software tool called TEXLab to identify the aggressiveness of tumours in CT scans and tissue samples from 364 women with ovarian cancer between 2004 and 2015. It examined four biological characteristics of the tumours which significantly influence overall survival - structure, shape, size and genetic makeup - to assess the patients’ prognosis. The patients were then given a score known as Radiomic Prognostic Vector (RPV) which indicates how severe the disease is.
The researchers then compared the results with blood tests and current prognostic scores used by doctors to estimate survival probability. They found that the software was up to four times more accurate for predicting deaths from ovarian cancer than standard methods.
The hope, therefore, is that the technology can be used to stratify ovarian cancer patients into groups based on the subtle differences in the texture of their cancer on CT scans, rather than classification based on what type of cancer they have or how advanced it is.
The team also found that five per cent of patients with high RPV scores had a life expectency of less than two years. High RPV was also associated with chemotherapy resistance and poor surgical outcomes, suggesting that RPV can be used as a potential biomarker to predict how patients would respond to treatments.
The researchers are also planning to carry out a larger study to see how accurately the software can predict the outcomes of surgery and drug therapies for individual patients, adding further powerful tools for doctors to use.
