'Dr Google' gives accurate diagnosis 'a third of the time'

Online symptom checkers are often inaccurate, scientists have warned. (Getty Images)

Many turn to “Dr Google” to “diagnose” a sore throat, abdominal cramp or mysterious rash.

With GP consultations going virtual amid the coronavirus outbreak, searching for answers online may seem the more convenient option.

Scientists from Edith Cowan University in Australia have discovered, however, these symptom checkers are only accurate around a third of the time.

This is concerning given Google is said to generate 70,000 health-related searches a minute.

Read more: Why you shouldn’t trust ‘Dr Google’

“While it may be tempting to use these tools to find out what may be causing your symptoms, most of the time they are unreliable at best and can be dangerous at worst,” said lead author Michella Hill.

“We've all been guilty of being 'cyberchondriacs' and googling at the first sign of a niggle or headache.

“The reality is these websites and apps should be viewed very cautiously as they do not look at the whole picture; they don't know your medical history or other symptoms”.

Symptom checkers should not replace face to face consultations once they are up and running, said the scientists. (Getty Images)

The scientists input symptoms of 48 medical conditions to 36 mobile and web-based symptom checkers available worldwide.

These checkers then use an algorithm or artificial intelligence to generate the most likely diagnoses.

Results, published in the Medical Journal of Australia, found the correct diagnosis was listed as the top result just 36% of the time.

It was in the first three results in slightly over half (52%) of cases.

Read more: What ‘Dr Google’ Means for The Future of Medical Care

Many symptom checkers advise users to seek face to face medical care if their condition seems serious.

The scientists found the recommendations on when and where to seek healthcare was accurate less than half (49%) the time.

“We found the advice for seeking medical attention for emergency and urgent care cases was appropriate around 60% of the time, but for non-emergencies that dropped to 30% to 40%,” said Hill.

“Generally the triage advice erred on the side of caution, which in some ways is good but can lead to people going to an emergency department when they really don't need to.”

The scientists also worry people with a serious health concern may become complacent if a symptom checker suggests it is nothing to be concerned about.

“For people who lack health knowledge, they may think the advice they're given is accurate or their condition is not serious when it may be”, said Hill.

Read more: Learning how to manage 'cyberchondria' — the constant urge to Google your health

The scientists added symptom checkers can be useful, but should not replace doctor consultations.

“These sites are not a replacement for going to the doctor, but they can be useful in providing more information once you do have an official diagnosis,” said Hill.

“We're also seeing symptom checkers being used to good effect with the current COVID-19 pandemic.”

King’s College London’s COVID-19 symptom tracker app is allowing scientists to better understand the spread of the infection.

COVID-19 is the respiratory disease that can be triggered by the coronavirus.

For symptom checkers in general, the Australian scientists called for more government regulation and data assurance.

“There is no real transparency or validation around how these sites are acquiring their data,” said Hill.

Amid the coronavirus pandemic, NHS patients can access accurate information via its website.

GP support and repeat prescriptions are available online.