This is a story that has a lot of good reporting, but by focusing on one company in the facial-recognition field, it leaves too many questions unanswered. The possibilities with facial recognition software are profound, and yet we don’t know from this story whether they truly could be used effectively for identifying and treating disease or whether they will be relegated mainly to sideshow status.
It’s also difficult to understand the “market” for this startup if most patients in the U.S. have access to genetic testing, which is needed for an actual diagnosis.
For developing countries or areas without access to genetic testing, facial recognition software could help providers narrow the list of disorders. Still, outside the most common genetic disorders (such as Down’s syndrome), it seems unlikely that this software will be useful in the absence of confirmatory testing.
There are no prices in this story. Cost is critical, particularly as this is proposed as helpful in resource-poor settings.
The story quantifies benefits for a related bit of science but not for the core product being described in the piece. For that, it says, “Face2Gene declined to provide similar numbers for their technology. ‘Since Face2Gene is a search and reference informational tool, the terms sensitivity and specificity are difficult to apply to our output,’ Gelbman cautioned.”
If we don’t know anything about sensitivity and specificity, we’re not sure how this can play any role in helping with diagnosis, even in narrowing the list of possible/probable disorders. The story needed to explore this problem more.
There is no explanation of harms here, but with any screening test (or “reference informational tool” as Face2Gene calls itself), there is a risk of overdiagnosis or incorrect diagnosis, without confirmatory genetic testing. That could be devastating to parents of affected children for example. Even though the company says that the software should not be used as a diagnostic tool, the allure to do so “off label” is there.
Because the story jumps from descriptions of what Face2Gene does to a project from the NIH and then back to the company, it gives the impression that this is strong science with a proven track record. Also, the first anecdote talks about one of the NIH scientists having a “superpower” that allows him to diagnose disorders by looking at faces. It’s a metaphor, of course, but it underscores the overall impression that this emerging technology is on very solid footing. Yet, other than one set of numbers from one study, we are given no evidence of that footing.
It’s not exactly clear where the NIH work and the company’s work begin and end. It talks about NIH-funded researchers gathering photos and uploading those to Face2Gene. That should be made more clear.
An outside expert to comment on whether this is useful would have been helpful.
The story makes clear that there is physician experience, as well as genetic tests, as alternatives. Because the software-makers insist this new tool is not to be used for diagnoses, we’re still not sure what the benefit of this new technology would be, and why it’s needed, though.
It’s not clear if this technology is available to anyone or if it is entirely in the research phase. This sounds developmental, but it was not clear. On visiting their website, it appears that it is already available for use.
It’s clearly established that’s what “new” here is using facial recognition software to diagnose genetic disorders.
The story does not rely on a news release.
Systematic, Criteria-Driven
Monday at #ADA2021, an infectious disease epidemiologist, a journalist, and a researcher shared perspectives on communication of risk in the era of COVID-19: http://ow.ly/ROfR30rMeE7 @AstleyCM @garyschwitzer @berthahidalgo @ADA_DiabetesPro
Shoutouts to @susan_bewley @drkevinknopf @MichaelBaum11 in this call for more than fawning coverage from press releases for these kinds of stories.
Also, linked history inside goes back 5 years just on Grail apparently trying to become Holy Grail. https://twitter.com/garyschwitzer/status/1408849696416841731
Comments
Please note, comments are no longer published through this website. All previously made comments are still archived and available for viewing through select posts.
Our Comments Policy
But before leaving a comment, please review these notes about our policy.
You are responsible for any comments you leave on this site.
This site is primarily a forum for discussion about the quality (or lack thereof) in journalism or other media messages (advertising, marketing, public relations, medical journals, etc.) It is not intended to be a forum for definitive discussions about medicine or science.
We will delete comments that include personal attacks, unfounded allegations, unverified claims, product pitches, profanity or any from anyone who does not list a full name and a functioning email address. We will also end any thread of repetitive comments. We don”t give medical advice so we won”t respond to questions asking for it.
We don”t have sufficient staffing to contact each commenter who left such a message. If you have a question about why your comment was edited or removed, you can email us at feedback@healthnewsreview.org.
There has been a recent burst of attention to troubles with many comments left on science and science news/communication websites. Read “Online science comments: trolls, trash and treasure.”
The authors of the Retraction Watch comments policy urge commenters:
We”re also concerned about anonymous comments. We ask that all commenters leave their full name and provide an actual email address in case we feel we need to contact them. We may delete any comment left by someone who does not leave their name and a legitimate email address.
And, as noted, product pitches of any sort – pushing treatments, tests, products, procedures, physicians, medical centers, books, websites – are likely to be deleted. We don”t accept advertising on this site and are not going to give it away free.
The ability to leave comments expires after a certain period of time. So you may find that you’re unable to leave a comment on an article that is more than a few months old.
You might also like