main article image
Ollyy/Shutterstock

Self-Diagnosing Online Yields Mostly Irrelevant Results, Researchers Say

MYLES GOUGH
8 MAY 2015

Most of us are guilty of turning to Google when we're sick or injured in the hopes of avoiding that dreaded trip to the doctor's office or hospital. Unfortunately, these attempts to self-diagnose often end up sending us down a rabbit-hole of misinformation, and can leave us more confused and scared than when we started.

 

During an investigation into how search engines can be optimised for health-related queries, a team of researchers at the Queensland University of Technology (QUT) in Australia found that around 50 percent of the top 10 results from symptom-related searches are irrelevant.

The practice of relying on Internet search engines for medical wisdom and advice is hugely prevalent. Google estimates that one in 20 searches, from its roughly 100 billion searches each month, is for health-related information.

But more often than not, users don't get what they're looking for, says engineer Guido Zuccon from QUT's Information Systems School.

After a detailed analysis of the results from medically-focussed searches using popular sites Google and Bing, Zuccon and his colleagues found that most of the returned information was irrelevant. He says this is problematic because it could lead to self-diagnosis and/or self-treatment, which may not be the best course of action.

"Our results revealed only about three of the first 10 results were highly useful for self-diagnosis and only half of the top 10 were somewhat relevant to the self-diagnosis of the medical condition," Zuccon said in a press release.

The QUT researchers surveyed participants to find out what common search terms they might use for a given medical condition. They showed them images of conditions including alopecia, or hair loss; jaundice, which causes a yellow discolouration of the skin; and psoriasis, which can result in a rash or lesions on the skin.

For jaundice, some of the search terms included things like: "yellow eyes", "eye illness", and "white part of the eye turned green". The researchers used these search terms and analysed the results.

"Because on average only three of the first 10 results were highly useful, people either keep searching or they get the wrong advice which can be potentially harmful for someone's health," Zuccon said.

In addition to getting confused and frustrated by the lack of relevant information turning up in searches, he says it's also possible for people trying to self-diagnose to experience something known as 'cyberchondria' - an unfounded escalation of concerns when you start discovering that your mild symptoms are also characteristic of much scarier diseases.

"If you don't get a clear diagnosis after one search you would likely be tempted to keep searching," said Zuccon. "So if you had searched for the symptoms of something like a bad head cold, you could end up thinking you had something far more serious, like an issue with the brain.

"This is partly down to searcher bias and partly down to the way the search engines work. For example, pages about brain cancer are more popular than pages about the flu so the user is driven to these results."

But it's not all bad. Search engines, which are obviously incredibly useful tools, performed much better when the name of the illness in question was already known. So for instance, if someone could search for psoriasis, rather than something like "annoying skin itch" or "red rash on skin", they'd get more reliable, more relevant results.

Still, for the time being, Zuccon says the results show it's best not to rely on the Internet to self diagnose. The next step for the researchers is to improve search engine algorithms in order to promote the most useful pages for medical searches.