Using the internet to self-diagnose that weird rash on your arm is fairly common. But the verdict is still out on whether or not direct-to-consumer diagnostic apps are effective or safe, according to a new review published in the journal Diagnosis. 

“Apps were found to vary widely in functionality, accuracy, safety and effectiveness, although the usefulness of this evidence was limited by a frequent failure to provide results by named individual app,” authors of the review wrote. “Overall, the current evidence base on [direct to consumer], interactive diagnostic apps is sparse in scope, uneven in the information provided and inconclusive with respect to safety and effectiveness, with no studies of clinical risks and benefits involving real-world consumer use.”

Researchers noted that the world of self-diagnostic tools is moving beyond a quick Google search and into more sophisticated apps, with benefits including faster and more targeted information for the general public. Since the FDA has exempted low-risk apps from needing its approval there is, often, very little screening, according to the authors. 

“Nonetheless, there are as [of] yet no accepted vetting processes enabling clinicians or patients to distinguish between reliable apps and 'digital snake oil,'” authors wrote. “Diagnostic apps specifically have received scant attention in comparison to health management ones, even in overviews of the field.”

Researchers then combed through a number of databases for scientific journals. After reading through these sources they identified four research questions: What clinical condition do these app address? What functionality is involved in producing a tentative diagnosis? What methodologies are evaluators using to assess these apps? And what are the results of app evaluations, including evidence on risks and benefits?”

The team of researchers zeroed in on 30 peer-reviewed articles and research letters and six non-peer reviewed articles that met their definition. Ten of the articles focused on dermatology, with the other 20 covering a broad range of conditions from sexually transmitted diseases to mental health. 

Authors of the review looked at how the apps were evaluated and found that previous studies conducted on the apps tended to include multiple platforms. Many of these evaluations also narrowed in on privacy concerns. When it came to diagnostic evaluations, researchers noted that results varied. 

In terms of app functionality, researchers found that 20 of the apps had users answer a medical symptom questionnaire and then applied an algorithm to match them to conditions. Another 12 apps used an applied image processing technology from smartphone photos. A handful used crowdsourcing to diagnose. 

The researchers said that in the future there needs to be action steps in the areas of research, policy and practice. They said that their research highlights the need for more evaluation when it comes to these tools. 

“Patient diagnosis is evolving 'from art to digital data-driven science', both within and outside the exam room,” researchers wrote. “DTC diagnostic technology is rapidly evolving: the second half of 2017, for example, witnessed the widespread online dissemination of a depression-assessment questionnaire, as well as with the debut of smartphone enhancements utilizing sensors and AI that target the same condition. The pace of change should inspire urgency to improve the evidence base on app performance. However, most of the studies we identified simply described various apps’ attributes, a finding similar to the conclusions of a broad systematic review of mHealth apps.”