Cookie policy notice

By continuing to use this site you agree to our cookies policy below:
Since 26 May 2011, the law now states that cookies on websites can ony be used with your specific consent. Cookies allow us to ensure that you enjoy the best browsing experience.

This site is intended for health professionals only

At the heart of general practice since 1960

GPs twice as good as apps at diagnosing illness, study finds

GPs outperform symptom checker apps by two to one when diagnosing illnesses, new US research has revealed in the first ever study of its kind.

The study, which comes as NHS patients will be able to register with GPs and get medical advice through a smartphone app by the end of next year, found that physicians were far more accurate than the symptom-checker apps, listing the correct diagnosis first 72.1% of the time, compared with 34% of the time for the digital platforms.

And 84% percent of clinicians listed the correct diagnosis in the top three possibilities, compared with 51% for the digital symptom-checkers.

The difference between physician and computer performance was most dramatic in more severe and less common conditions, the research revealed. It was smaller for less acute and more common illnesses.

The researchers, from Harvard Medical School and Boston-based Brigham and Women’s Hospital, used 45 standardised patient cases to test the accuracy of 234 GPs against 23 symptom checkers.

The cases were scenarios that included the symptoms and history of the patient, but did not contain physical exam or test findings, and ranged from very serious diagnoses to benign situations.

Senior investigator Ateev Mehrotra, an associate professor of health care policy at Harvard Medical School, said: 'While the computer programs were clearly inferior to physicians in terms of diagnostic accuracy, it will be critical to study future generations of computer programs that may be more accurate.

'Clinical diagnosis is currently as much art as it is science, but there is great promise for technology to help augment clinical diagnoses. That is the true value proposition of these tools.’

The research, Comparison of Physician and Computer Diagnostic Accuracy is published in JAMA Internal Medicine.

 

Readers' comments (7)

  • Definitely reason then for Jeremy to cut primary care funding even more and invest it all in Apps, the logic is as clear as his other great ideas and plans.

    Unsuitable or offensive? Report this comment

  • Not sure apps or GPs come out brilliantly from this test. But expect if the GPs could have done a physical exam they would have been a lot further ahead.

    So actual pecking order probably:
    - GPs in person
    - virtual GP
    - apps

    But for relatively new technology, apps aren't that far behind the virtual GP...

    Unsuitable or offensive? Report this comment

  • Comparing performance of apps to the 111 algorithm would be interesting.

    Unsuitable or offensive? Report this comment

  • Apps are probably
    a thousand times
    better than politicians at
    running the country

    P;)

    Unsuitable or offensive? Report this comment

  • In my area, many pharmacists do not open on Saturday!

    Unsuitable or offensive? Report this comment

  • Differences in diagnosing is one thing but over diagnosing and overburdening a system has many other knock on effects. Interesting to see how Apps fair against these criteria too.

    Unsuitable or offensive? Report this comment

  • The new Health Secretary app is allegedly twice as performant as Jeremy Hunt , and is more user friendly

    Unsuitable or offensive? Report this comment

Have your say

IMPORTANT: On Wednesday 7 December 2016, we implemented a new log in system, and if you have not updated your details you may experience difficulties logging in. Update your details here. Only GMC-registered doctors are able to comment on this site.