‘Dr Google’ could be used in the future to spot ovarian cancer cases up to a year earlier, researchers have suggested.
Women battling the disease looked up symptoms including weight loss, bladder problems and bloating up to 360 days before being referred to a specialist.
Google also saw a ‘spike’ in urinary symptom searches – a key warning sign of the cancer – up to four months before a GP referral.
Pelvic pain also seemingly emerged 70 days in advance.
Imperial College London researchers, who tracked the Google search histories of 235 women, claimed the data ‘offers enormous potential within health and disease screening’ — even though patients have long been advised against Googling their symptoms.
Women battling the disease looked up symptoms including weight loss , bladder problems and bloating up to 360 days before being referred to a specialist. Google also saw a ‘spike’ in urinary symptom searches – a key warning sign of the cancer – up to four months before a GP referral. Pelvic pain also seemingly emerged 70 days in advance
The disease kills 11 women on average every day in Britain, or 4,000 a year. It also kills three times as many people in the US every year, figures show. When symptoms are caused by ovarian cancer they tend to be persistent, with the National Institute for Health and Care Excellence (NICE) recommending your GP arrange tests if you experience these symptoms 12 or more times per month
The team also said it challenged the long-held belief that ovarian cancer is a ‘silent killer’, with most women thought to show little signs of the illness.
Lead author Dr Jennifer Barcroft said: ‘Our results show it is possible to use search engine data to understand how conditions present, and that this may have use in early disease detection.
‘Online search data offers enormous potential within health and disease screening, given the widespread use of the internet worldwide.
‘We hope that our research will drive interest in this novel area of research.’
Ovarian cancer is the sixth most common cancer in the UK. The disease kills around 11 women every day in Britain, on average, or 4,000 a year.
It also kills three times as many women in the US every year, figures show.
It is often diagnosed late because symptoms are vague and can include indigestion, pelvic or abdominal pain, loss of appetite, constipation, and needing to urinate more often.
Around 93 per cent of women diagnosed live five years or more if it’s spotted at the earliest stage, compared with just 13 per cent diagnosed at stage four.
About a fifth of women with ovarian cancer are also diagnosed in A&E, often when it is too late for any treatment.
Fellow researcher Dr Srdjan Saso, gynaecological cancer surgeon, called the disease ‘one of the most lethal cancers for women’.
He added: ‘The focus, therefore, remains on facilitating early disease detection.’
Brits involved in the study had their data obtained with consent using Google Takeout — a tool allowing people to download a copy of their data stored within Google products.
Using the tool’s health search filters, researchers tracked the differences in Google searches between women who did, and did not, have ovarian cancer.
Writing in the journal BMC Medicine, they said there were differences between those with and without positive diagnoses ‘noted as early as 360 days in advance of GP referral’.
The predictions became more accurate around 60 days in advance of a referral.
Professor Ingemar Cox, a computer science expert at University College London and senior study author, however, warned the findings also ‘raise important ethical and privacy concerns, which need to be resolved’.
It comes as a damning report last month revealed UK survival rates for five common cancers drastically lag behind other high-income nations.
Just 37.1 per cent of Brits diagnosed with Ovarian cancer between 2010 and 2014 expected to still be alive five years later.
By contrast, the rate stood at 46.2 per cent, 43.2 per cent and 40.3 per cent in Norway, Australia and Canada.
While the level of progress for cancer survival for some forms of the disease has been rapid, such as for breast and prostate cancers, others, like those for lung and pancreas have only improved at a snail’s pace
Even for patients who did get treatment, they were forced to endure longer waits — raising the risk of their disease spreading and slashing survival odds.
Health leaders have consistently warned that an array of key cancer targets have not been hit in recent years.
They have also estimated 40,000 cancers went undiagnosed during the first year of pandemic alone.
Official NHS data for December on cancer waiting times shows just seven in 10 (74.2 per cent) of patients urgently referred for suspected cancer were diagnosed or had cancer ruled out within 28 days. The target is 75 per cent.
Just nine in ten (91.1 per cent) waiting a month or less for their first cancer treatment to begin after a decision to proceed with surgery, chemotherapy or radiotherapy.
The target is 96 per cent but this has never been met.