New study seeks to ‘notably’ improve ovarian cancer survival rates

Morgan Liotta

1/07/2021 3:41:51 PM

The world-first research will use artificial intelligence to predict risk factors of the fatal cancer over the next 15 years.

Woman clutching stomach
Abdominal or pelvic pain can be a symptom of ovarian cancer.

Three per day.

That’s how many women die in Australia from ovarian cancer, making it the 10th most-commonly diagnosed cancer among females.

In 2020 alone, 1532 women in Australia were diagnosed with ovarian cancer, while another 1068 died. Of those diagnosed, 60% are aged 60 or over and 33% aged 40−59.
Often dubbed ‘the silent killer’, ovarian cancer usually has a late diagnosis due to vague symptoms and few known causes. The cancer has a five-year survival rate of less than 30% for women with late-stage cancer.
Now a world-first study aims to determine risk and aid early diagnosis to prevent death from the most fatal reproductive cancer.
Led by the University of South Australia’s Australian Centre for Precision Health with backing from the Medical Research Future Fund, the study will map the genetic and physical risks of ovarian cancer, based on the health records of 273,000 women from the UK Biobank database, which contains in-depth information from 500,000 UK participants between 2010−16.

The four-year research project will engage the help of artificial intelligence (AI) in the form of a machine learning model, which automatically analyses data to identify patterns of risk. It will then accurately predict which women will develop ovarian cancer in the next 15 years.

Lead researcher and nutritional epidemiologist, Professor Elina Hypponen, said early diagnoses will ‘notably’ improve survival rates.
‘If we can identify women who are at greatest risk, we can triage them for more intense screening, improving early detection and prognosis,’ she said.
‘We know that age, endometriosis, obesity and ovulation are risk factors, and there has been great interest in seeing if these risks might be modified using hormones or other medications, such as oral contraceptives or aspirin.’

Genetics and lifestyle modifications such as diet may also play a part in modifying ovarian cancer risk, according to Professor Hypponen, and a ‘computational approach’ will narrow down those most at risk.

The machine learning model will identify which factors can either increase or reduce the risks of ovarian cancer.
Focus will be on metabolomics, the small molecules involved in breaking down fats for energy, hormonal data and blood biomarkers to better predict the risks.

Professor Hypponen is confident the study will improve survival rates.
‘Globally, this is the first and largest study of ovarian cancer to include such a comprehensive analysis of risk factors,’ she said.
‘We believe we can make significant headway in a very short time into the causes, detection and prevention of ovarian cancer.’
And GPs have a role in early risk assessment using the new AI model, Professor Hypponen told newsGP.
‘GPs can support women both in terms of establishing their risk of ovarian cancer, and in helping to empower women to reduce this risk,’ she said.
‘Simply increasing the awareness about the signs and symptoms of ovarian cancer may help women to take action earlier, and as we learn more, GPs may have a role in providing lifestyle advice and in directing entry to more intensive screening or other prevention programs.’
Log in below to join the conversation.

ovarian cancer preventive health reproductive health risk assessment

newsGP weekly poll What areas of healthcare were you hoping would get more funding in this year's Federal Budget?

newsGP weekly poll What areas of healthcare were you hoping would get more funding in this year's Federal Budget?



Login to comment