From the "thank goodness" file comes a story about a study that compared self-diagnostic apps and human physicians. The physicians were correct 72% of the time while the apps were accurate only 34% of the time based on the same information.
The test may have some issues:
“There are major methodologic problems with the approach that was used,” Mark Graber, a fellow at Research Triangle Institute International who researches health care quality and diagnostics and was not involved in the study, writes in an email. “The physicians in the study had essentially as much time as they wanted to evaluate and research each case; this is hardly comparable to actual practice. Its likely that the specific methods used overestimated the physician performance and underestimated ‘symptom checker’ performance.”
However, it’s not surprising to see online symptom checkers wrong most of the time, they typically use a very limited set of criteria. As long as they get the patient to talk with their doctor they have essentially done their job.
Source: IEEE Spectrum
This story first appeared in the Klick Wire, delivered 7AM every Monday. Sign up to get the Wire today!