Wednesday, November 15, 2006

Google Says You Have Insufficient Qi

EoR read about this study recently in the local paper, dismissing it as silly and rather pointless. A couple of people at the Princess Alexandra Hospital in Brisbane have assessed the usefulness of Google to diagnose illnesses and publised a paper in the British Medical Journal about it. They decided that Google delivered a correct diagnosis in 58% of cases. Unfortunately, there were only 26 cases, and the confidence interval varied from 38% to 77% in 95% of those cases. The study concluded that

As internet access becomes more readily available in outpatient clinics and hospital wards, the web is rapidly becoming an important clinical tool for doctors. The use of web based searching may help doctors to diagnose difficult cases.

Only one of the top three results from Google had to be correct to be classed as a "hit" (does this strike anyone as remarkably similar to the "skills" evidenced by psychics?).

As The Register points out

The "researchers" were also remarkably generous with their definition of a correct diagnosis. If one of the top three results returned by Google was correct, it was considered a success. So Google was returning false diagnosis up to 80 per cent of the time. You might as well throw darts at a spinning dartboard, tied to the back of a drunken horse. Yes, it's another of those pieces of research which start with a conclusion, works back to a premise, and then tries to pad out the bit in between (what used to get called "evidence") with garbage.

Given the types of results that Google is likely to throw up, you're more likely to be prescribed crystal therapy or colon cleansing utilising this method. The only way that EoR can possibly see it working is if the doctors already know what the diagnosis is, so that they can determine which of the myriad sites that pop up is the real one (assuming any is). Which rather defeats the purpose. Perhaps patients might like to google "making a will" before attending doctors using this latest methodology.

No comments:

Post a Comment

Note: only a member of this blog may post a comment.