Is Skin Testing AI More Accurate Than Doctors?

by | Sep 29, 2019 | Artificial Intelligence (AI), Blog, News

ai testing dermatology

AI Diagnosis Technology

In our world today, technological advances are vast, varied and surround us at every turn. From the computers we use in everyday life to the healthcare we rely on: AI technology has become more important than ever. Online today, you can test for allergies, cancerous moles, skin diseases and more through the help of an online specialist, doctor or dermatologist. 

This move to seek medical help online has enabled a new wave of development in Artificial Intelligence, forcing the medical industry to consider this vital tool for diagnosis and research. AI technology has reached such accuracy that many in the medical industry are unable to overlook its strengths, especially when compared to a GP Doctor. 

With AI moving so fast across healthcare it was inevitable that it would land on Skin Allergies and Diseases as the scope of the technology broadens. The question, of course, is whether this AI technology is more accurate than a Doctor?

There are various studies and research papers carried out on this subject alone, but a recent study by google has brought the debate into the public eye once more. We’re going to focus on a key finding in this study: Skin Testing AI has been proven to be more accurate than a family doctor. Admittedly this is something that has long been researched within the dermatology industry but the focus has almost entirely centred on Melanoma and Cancerous moles. Frequently, as demonstrated in this study, the AI intelligence is more accurate than a doctor and in fact, more accurate than a Dermatologist when testing for Melanoma.

The new Google AI study, however, focuses on an area that we have long researched here at First Derm: Skin allergies, Rashes and beyond. The study tested only 26 allergies vs our 33 allergies but what is of particular interest is the results achieved when diagnosing skin diseases compared to a Doctor. The challenges a Doctor faces when diagnosing skin diseases has long been discussed as demonstrated by a 1981 research piece by Dr. David L. Ramsay and Dr. Alissa Benimoff Fox named ‘The ability of primary care physicians to recognize the common dermatoses’  – this research paper highlighted that Doctors achieved only a 16% accuracy in some cases whereas a Dermatologist achieved 93% (in some cases 100% accuracy).  

Since 1981, Doctors have of course improved in accuracy whilst technology has advanced alongside. We’re now at a stage where it is no longer Dermatologists that we compare Doctors to, but AI. The recent Google study demonstrated that across all 26 skin diseases that were tested for, the AI was proven to be more accurate as displayed in the table below:

Credit: Google

As demonstrated, the DLS (AI deep learning system) proves to be far more accurate than a Doctor (PCP) even when diagnosing the number 1 most likely condition. It also narrowly beats dermatologists and outright beats all professionals and experts when forming a diagnosis of the top 3 most likely conditions.

What Does This Mean For You?

The advances in medical AI are designed to improve the accuracy of doctors, dermatologists and nurses. Not only this, but it opens up many more possibilities when it comes to your own personal healthcare. AI has now been shown to test more accurately than Doctors and even Dermatologists in many cases. Give our skin image search a try and get your results within seconds, if that’s not a positive, then what is?

Ask a Dermatologist

Anonymous, fast and secure!

Over 15,000+ Readers

Get fresh content from First Derm

Ask a Dermatologist

Anonymous, fast and secure!

1 (415) 234-4124
Share This