New AI-Driven Symptom Checker to Launch in 2017

Health is, without a doubt, one of the most popular topics searched for when people go online.  Indeed, a UK study suggested that nearly half of all searches are health-related.

The thing is, not all of the information we find when we do these searches is particularly accurate. Indeed, one Belgian campaign urged people to not Google their symptoms precisely because it tended to do more harm than good. Much better, they suggest, to talk directly to a qualified professional instead.

That doesn’t stop the majority of us, however, from heading to Google as our first port of call when attempting to diagnose ourselves. So, an Israeli startup is especially interesting, as they are aiming to ensure people have accurate information that they can rely on in their time of need.

The venture, called Kang Health, consists of a website and app that utilize AI to ensure we get the best quality information possible.

A Digital Brain

The service aims to mine the web to search for your symptoms online, but rather than regurgitating somewhat ropy diagnoses, the system aims to use the information shared by the patient to better match them with the correct result.

This information could be demographic information or the symptoms they’re experiencing. This information is then cross-referenced with similar searches from similar people before then returning what it believes is the most accurate diagnosis, together with a recommendation to see a professional.

The information is validated by a couple of full-time doctors to ensure it is as accurate as possible, but given the breadth of possible information sought via the service I’m not sure how scalable that is.|

“Kang will liberate consumers from the shackles of the lowest common denominator of low quality health related online data...We don’t pertain to dispense medical advice; we are simply providing consumers with the ability to be directly involved in making decisions about their own body,” the company says.

Of course, they aren’t the only service aiming to provide more accurate triaging of symptoms. For instance, last summer, the telehealth platform Babylon launched a service that was fully AI-driven.

The service was tested both live against experienced doctors and nurses over a more prolonged period and performed strongly on both occasions. Indeed, the AI system was found to be both more accurate and considerably faster (and therefore cheaper) than human based triage services.

As our demands for health care grow ever larger, it seems inevitable that computers will have to evolve to play a more significant role. A number of platforms are innovating in the space, and it will be interesting to track how they perform in the marketplace over the coming year.