Don't Get Burned!
Which sunscreens work, which fall short—and why you can’t always rely on packaging labels.
As a kid in Brazil, Sonia Sousa fell in love with Isaac Asimov’s Fantastic Voyage, the story of a submarine crew who shrink to microscopic size and travel through the bloodstream of a wounded scientist. When she finished the book, Sousa recalls, “I walked into the living room and told my mother, ‘I’m going to be a scientist and I’m going to be able to look inside the body.’” Her mother was skeptical, reminding Sonia that she’d previously declared her ambition to become a Formula 1 driver.
Sonia stuck to her dream. She earned a PhD in spectroscopy and joined the Silicon Valley start-up scene. Now, as the cofounder and CEO of Kenzen, she’s pioneering new ways not just to peer inside our bodies, but to understand how we choose to live in them—and to improve our chances of doing so better, longer—using tiny sensors, big data, and the portable supercomputers we call smartphones.
All day, every day, we leave a data trail. Fitness bands and smart bras monitor our heart rate, count our steps, track our sleep. Google searches, social media posts, and online purchases offer clues to our mental and physical health. Smartphones don’t just house our calendars, e-mail, photos, and music—they also record where we go, how much we move, what games we play, how often we call Mom. When we finally put them down, they have a pretty good idea we’ve gone to sleep.
Next, if Kenzen has its way, you’ll have a small monitor stuck to your side, reading your every drop of sweat. The company’s patches will soon be analyzing the perspiration of the San Francisco 49ers, the Houston Rockets, and FC Dallas soccer players, picking up on minute shifts in sodium, potassium, and pH; next year, Kenzen plans to roll out versions that check glucose (calories and energy expenditure), cortisol (stress), and lactate (muscle recovery). The goal is to spot health problems before serious trouble develops. “Our body is talking to us all the time. We just can’t hear,” Sousa says. Kenzen’s system is “like a megaphone with a translator” that could, say, warn a construction worker of incipient heatstroke or tell a diabetic her glucose has dropped before she’d think to pause for a finger prick.
Whether for an individual or an entire population, this kind of aggressive measuring adds up to an ever-swelling stream of data. The carrot currently being chased by countless tech entrepreneurs, medical centers, and academic researchers is not just another “ultimate” tracking device (though they’re in hot pursuit of that, too) but a way to harness the data from the ones we’re already plugged into: figuring out how to collect, combine, and interpret all that information. And then how to use it—without becoming obnoxious, intrusive, or just plain creepy. (Some would argue that if our watches are ordering us to stand up on the hour, and our phones know we’ve ovulated before we do, we’ve already crossed that Rubicon.)
As sensors get more pervasive, more connected, and either more low-profile or far chicer, the measured life will increasingly become, well, regular old life. “What we call smart clothes today will eventually just be called clothes,” proclaimed Stephane Marceau, the cofounder and CEO of Montreal-based OMsignal, at a recent conference on wearable tech. Instead of an optional wristband, Marceau’s company wired up something most women really can’t exercise without—a sports bra.
In the meantime, the many things measuring you will find ways to sync up. Under Armour has already equipped its SpeedForm Gemini 2 running shoe with a full suite of accompanying gadgetry, including a scale and an app that tracks your progress. Sure, the ELLE editor who tested the system found the task of getting its various bits to “speak” to each other more irritating than informative—not to mention a buzzkill to the bliss of lacing up and racing out the door. But these are early days. Now imagine smart refrigerators that talk to smart scales that feed directly to your cardiologist’s office—or your trainer’s. Camera apps that clock the calorie counts in all those artfully composed Instagram foodie shots and report back to your online grocery cart. Digital tattoos that could unlock your front door and trade data with a handshake. Smart toilets that monitor changes in intestinal microbes (more on these, page 220) and flag your Walgreens account. Eventually these may seem as mundane as the previously unimaginable monitors now wrapped around so many wrists.
Intel anthropologist Genevieve Bell, PhD, whose job is to ponder the future of technology, calls the trend “mass precision.” For the first time, “we have the ability to have both these large data sets and also deep data sets about an individual,” she says.
The mass part—aka the kind of big data rendered by, say, the nearly 50 million trackers Fitbit has sold to date, or the 2.1 billion smartphone users on the planet—offers the chance to spot new patterns. You might have heard that it’s a bad idea to weigh yourself every day. Don’t believe it. Analyzing data from its Aria wireless scale, Fitbit discovered that people who weigh themselves daily are more likely to lose weight than those who don’t—74 percent versus 65 percent in the first month. And they lose more: an average of 3 pounds in the first month and 9 pounds in the first six months, versus 1 pound and 2.5 pounds for those who weigh themselves two or three times a week. The frequent reminder seems key to staying on track.
Fitbit’s findings record life “in the wild,” as users actually live it, without the fallibilities of self-reporting or the artificial environment of a lab. Consider insomnia, says Shelten Yuen, PhD, the company’s vice president for research and development: “The standard for care right now is you self-report—you find that you’re drowsy; you go see your doctor; the doctor says, ‘Why don’t you go to a sleep lab?’ Sleep labs are highly accurate environments in which you can monitor a person’s physiology and sleep, but they’re very different from your normal sleep environment—and it’s usually just one night in that sleep clinic.” No, your Fitbit is not equipped with all the tubes and wires you’d be attached to in a lab—yet. But for starters, consider what could happen if you hooked up a sleep-tracking band with your calendar and your food diary: more of those patterns. “Maybe I’d sleep better if my last meeting of the day wasn’t with my boss,” Bell says. “Or maybe I’d sleep better if I didn’t have all that food at dinner.”
Mass data can hide important individual factors, but mass precision teases them out—finding individualized takeaways from among the masses. Ever wonder why vegans and Paleos seem equally convinced that they’ve found the one true way to weight loss? Bell cites a diet study published last November in which researchers at Israel’s Weizmann Institute of Science continuously monitored the glucose of 800 people for a week. Even when everyone ate the same food, they showed very different blood sugar changes after meals. Crunching the data, researchers found distinctive patterns—notably, different intestinal microbes—that suggested which diets would work best for which people. Tested on another group of 100, the patterns held up.
Or take my migraines. Like most sufferers, I have conflicting hunches about possible causes. Not enough caffeine, too much caffeine, not enough sleep, too much sleep, red wine with dinner, or is it prosecco? I’ve probably missed a lot of nice wine for no good reason. Figuring out what’s going on would require carefully tracking many kinds of data from my life—what I eat, when I sleep, what I’m working on—as well as looking for consistent triggers across many different migraine sufferers.
Similarly, combining enough real-time data might even answer a great medical mystery: What causes menopausal hot flashes—in general or in a particular woman? “Everybody knows that you sweat and you get flushed. Nobody knows what triggers this crazy temperature imbalance,” Sousa says.
David Stark, MD, medical director of the new Mount Sinai Institute for Next Generation Healthcare, is building a clinic that incorporates the data from patients’ devices. Stark, who did a Stanford postdoc in biomedical informatics on top of his pediatric neurology training, sees the measured life as a chance to get a truer picture of well-being. “Health happens every day,” he says. “In your home, where you live and work and eat and sleep, not in the doctor’s office.”
“What very small, easy-to-do thing can have a great impact on people’s lives over time?” That’s the billion-dollar question Jay Blahnik dangled before the engineers who helped mastermind the Apple Watch’s fitness components. Now the status wearable offers users velvet-glove reminders (a friendly ping and subtle vibration) to move, exercise, and even stand up, incentivizing them with onscreen colored rings that fill in as they reach “move goals.” But after two years of prodding humanity to speed up, Blahnik’s team has a different message: Hit pause and breathe.
It’s a little ironic for a smart watch to encourage us to disconnect, isn’t it?
It’s not lost on us that people’s attachment to our products might be causing them more anxiety. They take fewer moments of quiet time; they can’t just sit for a minute without checking their social feed. We know the brain is wired to have moments of calm and clarity. By talking to lots of experts, including an addiction specialist, about deep breathing as a tool for everything from drug addiction to quitting cigarettes, we found that it can relax you even when you can’t clear your mind perfectly. It triggers the parasympathetic nervous system.
So how does the watch’s new deep breathing app work?
There are a lot of recommended ways to breathe, but generally the exhale is about 50 percent longer than the inhale, amounting to about seven breaths per minute. We focused on short sessions; one to five minutes—we found that people who were comfortable doing more than five minutes tended to already have a really great habit established. We learned that if you dial it up to 20 minutes, that might make somebody feel one minute isn’t helpful, when the science shows it really can be.
Why does the watch track moving versus standing—isn’t there a crossover?
There’s a lot of compelling research showing that exercise can’t undo being incredibly sedentary. Lots of hours spent sitting is a separate risk factor. The part that’s not incredibly clear is how long you should stand per hour. We believe you should count all movement. World health organizations are interested in this: People only seem to count the sweaty moments, when a brisk walk to work may do more to lengthen your life than an intense workout.
If the optimal standing amount is unknown, why cue us to stand for one minute every hour?
We found that globally there’s a notion of an hour—meetings change on the hour, classes rotate on the hour. There’s also a real intuitive notion of a minute. So basically, if you’ve stood for a minute, you’ve earned that hour.
How have you seen people respond?
At a store event in Tokyo, after 50 minutes, the whole audience stood up! We all got the reminder at [about] the same time. There’s real social positivity to it that ends up changing a family, a tribe, a culture—suddenly nobody feels comfortable sitting for long.
Over the last few months, I’ve been doing some serious navel gazing. Well, more like belly-button-bacteria sampling. And cheek swabbing. And spitting copiously into plastic tubes that I’ve then sent away in the U.S. mail. One day, a nurse even came to the ELLE office and removed several vials of blood from my arm. What I’ve learned from all of this is that I have moderately elevated cholesterol and medical alert–low vitamin D levels; I’m more genetically primed for endurance sports than power sports; and I have a lower-than-average chance of getting wrinkly or saggy as a result of sun exposure. I’ve also confirmed a lot of what I already know: I’m 98 percent likely to have blue or green eyes (nailed it), 91 percent likely to have little or no unibrow (phew!), 58 percent likely to prefer salty snacks (pass the chips!), and 75 percent likely to be able to smell asparagus pee (alas, I can). Such has been my initiation into the plethora of self-testing kits and Web-based protocols that, without requiring a single doctor’s appointment, herald a brave new world in which we can examine, analyze, and monitor the minutiae of our own bodies from the inside out.
When 23andMe first introduced direct-to-consumer genetic testing in 2007, it meant that anyone with $999 to spare (today it’s $199) could get a snapshot of certain trait-determining snippets of his or her genetic code. Since then, many biotech companies have begun to take advantage of increasingly inexpensive gene-sequencing technology to provide easy test-at-home kits, while others have devised new ways to quantify human wellness—all designed to cater to the life-hacking generation’s obsession with being smarter, faster, and healthier than ever before. These new methods, most of which require the sampling of one unsavory bodily fluid or another, go beyond anything a noninvasive wearable device can currently deliver. By testing everything from gut flora to white blood cells, they promise customized diet, exercise, and lifestyle regimens that can—in theory, at least—help us “optimize” (an industry buzzword, to be sure) our innermost workings.
In 2009, a trio of PhDs—Gil Blander, David Lester, and Christian Reich—founded InsideTracker, a service that analyzes blood biomarkers, molecules associated with vitamin and mineral levels, hormonal activity, and so on. The platform’s first core group of users were professional athletes (including, Blander says, “hundreds, maybe even thousands, of CrossFitters”) seeking to improve their performance, but they’ve since expanded to a much wider demographic. “Most of our users are in their thirties, forties, and fifties, because at that age you see you are not immortal,” he says. “But some just want to lose weight; some want to sleep better.”
Here’s how it works: Your blood sample (drawn at any Quest Diagnostics clinic or, for an extra fee, in your home by a licensed phlebotomist) is scanned for markers such as cholesterol, cortisol, testosterone, glucose, and vitamin B12, the results of which can then be viewed online. Taking into account one’s age, gender, ethnicity, and activity level, you get a list of foods, vitamins, or exercise programs—all drawn from peer-reviewed scientific studies and vetted by scientists, nutritionists, physiologists, and biologists from the likes of Harvard, Tufts, and MIT—that should help move the needle, so to speak, on whatever markers are less than optimal. To lower my elevated LDL cholesterol, for example, I’m told to consider eating more beans, starting a high-intensity interval-training program, and supplementing with berberine, a plant-derived alkaloid with a raft of studies showing it improves cardiovascular health.
Although Blander emphasizes that InsideTracker is “a wellness solution, not a medical solution” (the service doesn’t test biomarkers related directly to disease, and the rare user who receives a red-alert result will be sent a direct e-mail suggesting they make a doctor’s appointment), he believes that the ability to scrutinize changes in one’s biochemistry empowers users to safeguard their own health. “After the car industry started recommending routine maintenance in the 1980s, the life span of a car increased from around 100,000 miles to 200,000 miles,” he says. “So my hope and my belief is that just by doing InsideTracker, we might be able to increase our longevity and our quality of life using simple interventions.”
Already, Blander says, “many” users (he doesn’t disclose the percentage) have shifted from diabetic to prediabetic status, or from prediabetic to normal glucose levels, after following the recommendations; and although 60 percent of users are initially found to be biologically older than their chronological age in the platform’s InnerAge analysis—based on the five biomarkers most associated with longevity—many test younger each time they run further blood work.
And yes, there will be further blood work. As with wearable monitors, there’s a gaming aspect to InsideTracker: Of course you’ll want to do another round of testing in three months, and maybe again after that, so that you can see just how optimized you’ve become. This vigilance doesn’t come cheap: InsideTracker’s Ultimate kit, which gives the most thorough analysis, starts at $499. (The other big player in blood biomarkers, WellnessFX, offers a $925 Premium package, which tests an expanded range of fertility hormones and thyroid functions and includes a 40-minute consultation with an MD, who gives, according to the website, “concierge-level recommendations.”)
In addition to the vitamin D deficit, my first InsideTracker screening showed low iron levels. So I dutifully consumed more peanut butter and spinach, and made sure not to eat iron-rich foods at the same time as calcium-rich foods (they can compete for absorption). When I had a follow-up test, I saw modest improvement in the ferritin marker, but others had gone awry—now I suddenly had the aforementioned high cholesterol, as well as a slight spike in ALT, an enzyme that can signal liver damage. I felt a surge of panic. Was it that ill-advised week of nightly cocktails? The cheeseburger I ate the night before the test? Though Blander tells me the changes are so small it could have been either, I couldn’t help but worry that it was something worse. I ordered umpteen supplements from Amazon, next-day delivery, and vowed never to drink again (that didn’t last). I felt consumed by the urge to course-correct, be perfect, be, yes, optimized. But guess what? The only way to know if I’ve gotten everything back on track is to get tested again. Ka-ching!
Whereas a blood test can give you a snapshot of internal biological processes that change day to day—and can be modified by lifestyle choices—genetics tell you what you can’t alter but can, in some cases, be able to work around. For example, if you carry a gene that indicates you’ll benefit more from high-intensity training than from cardio, you won’t waste any more time on the treadmill. One such home-testing system, FitnessGenes, provides personalized workout plans as well as advice on things like what time of day you should train, based on whether you carry variants that can affect circadian rhythm; another, DNAFit, customizes a nutrition plan based on your genetically determined responses to carbs, saturated fat, and lactose.
Boston-based biotech start-up ORIG3N currently offers three hyperspecialized LifeProfile kits: FitCode (which tests genes related to athletic performance for $149), Aura (skin condition and aging; $99), and Superhero (outlier genes, such as those that signal fast-twitch muscle reflexes and accelerated learning capacity; $29). When I visit ORIG3N’s slick, light-filled lab in Boston’s Innovation District, the hub of the booming East Coast biotech biz, the company’s scientists put my cheek-swab sample to the Superhero test using an automated genotyping machine—and find that I am disappointingly unremarkable. While ORIG3N’s kits don’t give specifically actionable advice, such as whether you should be doing bench presses or sprints, they do tell you how your gene variants compare to the rest of the population. For example, my results show that I am mostly average in things like sun sensitivity and postworkout muscle recovery, but I do carry a single nucleotide polymorphism, found in only 5 percent of the population, that may make me extrasensitive to dietary sugar (finally, an excuse to skip dessert). This type of testing, CEO Robin Y. Smith says, “is lively and fun. It’s a great icebreaker into the world of genetics, because it’s not doing it in a way that’s scary or medical. People are like, ‘Hey, this is a really cool thing to know about myself.’”
Interestingly, the LifeProfile kits are only a small part of ORIG3N’s work: The company’s main project, called LifeCapsule, is focused on cryogenically banking adult stem cells for use in scientific research. Derived from the blood of adult donors, these blank-slate, or pluripotent, cells can be used to grow new heart, nerve, or liver cells in vitro. (The enthusiastic ORIG3N team shows me, under a microscope, how the cells retain the biochemical characteristics of their original owners: Turns out a stem cell taken from a patient with cardiac arrhythmia will, if made into a heart cell, pulse with the exact same arrhythmia.) Their use of adult-derived stem cells—based on Nobel Prize–winning technology developed in 2006 by Japanese scientist Shinya Yamanaka—alleviates ethical issues associated with using tissue derived from human embryos, and enables researchers and pharmaceutical companies to directly test the toxicity of medications on living, responsive human cells, rather than running less-reliable trials on mice.
Smith likens the current state of regenerative medicine to the Internet of the ’90s. “In 1999, all these regular consumers were saying, ‘What is this Internet thing?’ It seemed to come out of nowhere, but in actuality people had been working on it for 15 years,” he says. “In about five years, things like spinal repair, cardiac repair, and growing your own tissue outside of your body are going to happen. We’re laying the foundations for that.”
In ORIG3N’s big-picture vision, the genetic data gathered from the LifeProfile kits will work in concert with the stem cell bio-repository (several large tanks, humming along the wall of a lab, already contain thousands of samples) to assist in the study of diseases such as Parkinson’s and Alzheimer’s, enabling scientists to compare ages and populations as well as chromosomal variations to find a cure. Their faith in this mission is so compelling, in fact, that at their labs I end up donating blood to LifeCapsule and signing a consent form saying that they can do absolutely anything with my cells (divorced, I am assured, from my identity) in the pursuit of research. I can’t say for sure, but I think I might have agreed to be cloned.
At this point, even non-kombucha drinkers know the importance of our microbiome—the bazillions of bacteria that live on and in our bodies, believed to influence everything from our weight to our moods to our propensity to develop certain diseases. To send some of my internal critters off to San Francisco–based uBiome, which sequences individual microbial DNA, I follow instructions to swab used toilet paper (sorry for that image), swish the swab around in a fixing solution, try not to gag, and send it away. The company offers two options: a gut-only test (the aforementioned yuck swab; $89), or a five-site test, for which you also swab the nose, behind your ears, mouth, and genitals ($399). uBiome analyzes which bacteria species you host and in what proportions, then reveals how your flora stacks up against that of, say, a vegetarian, a heavy drinker, or an omnivore. It’s a fascinating in-depth portal into your own ecosystem, but while the company provides info on the health benefit (or detriment) with which each type of bacteria is associated (Bacteroidetes, for example, may protect against obesity; Firmicutes, which tend to be dominant in American samples, are linked to weight gain), it stops short—like all of these highly regulated at-home tests—of rendering medical diagnoses.
“We can tell you how your probiotic is working, how diverse your microbiome is, and how it changes over time in response to the foods you eat and lifestyle changes like exercising more or drinking more water,” says cofounder Jessica Richman, an Oxford-educated PhD. “But for regulatory reasons, we can’t tell people what’s in their microbiome with a high level of specificity without having a doctor’s prescription.” Soon, though, uBiome plans to release a clinical test for physicians to administer, which, she says, “will have much more detail about pathogens and more prescriptive health advice.” In theory, your doctor could use such a kit to prescribe a customized probiotic blend or identify an illness.
uBiome is essentially crowd-funded, having launched after raising more than $350,000 from roughly 2,500 Indiegogo backers in 2013. In keeping with that, it is working for the greater good—opening up its accumulated data to researchers at Harvard, Johns Hopkins, and Stanford, and establishing a platform for what Richman calls “citizen science”: Amateur enthusiasts can suggest or help organize studies to be undertaken by uBiome’s research partners. (Any uBiome user can opt in or out of these studies when sending in their sample.) Currentexamples on the uBiome site: an inflammatory bowel disease study, an examination of the oral microbes of smokers, and a deep dive into “eye crusties.”
In an interesting intersection between narcissism and altruism, the ultimate outcome of all of this incessant testing may be better-quality studies, increasingly expeditious drug trials, and better health care for all. Apple is already sharing much of the mind-boggling amount of health data it collects with researchers via the Apple ResearchKit, a program allowing iPhone and Apple Watch users to opt in to various studies. With such humongous data sets to draw from, scientists will soon be able to study human biology in a much different, more inclusive way than ever before.
Elizabeth Iorns, PhD, the cofounder of Science Exchange, a Silicon Valley startup that acts as a marketplace for shared science experiments, refers to a recent study by Pfizer and Massachusetts General Hospital that tapped into 23andMe’s data to identify 17 genetic markers linked to depression: “1.2 million people have had their genotyping done by 23andMe, and most have allowed their results to be used for medical research. That scale is super-interesting because you can answer questions with large sample sizes better than the traditional way we do research, where you have to collect the patients and it takes years and years. Now we’re crowd-sourcing it.”
It also empowers patients, arming them with information that was previously kept in various doctors’ offices—as well as interlinking data that used to be siloed. “I don’t think it’s too grandiose to say that it’s like the printing press,” says uBiome’s Richman, “in that you used to have the one book that was owned by the church, and you had to go to the church to read the book and get the official answer. Before the Internet, you had to go to the doctor to get the answer because the doctor had studied for many years and could give you an answer. Now we can all have access to that kind of information. That doesn’t mean that doctors aren’t valuable—it will always be true that someone who spends 30 years working on something will know a lot more than anyone else—but as a type of massive social change, I think health care will be controlled by the patients. We’re the ones who care most about our health.”
Will we live longer, healthier lives as a result? That remains to be seen. In my experience, there’s still something a little unsatisfying about these tests, both together and separately. I now have all of these little pieces of myself, like a puzzle, but really, where am I in there? To echo King Lear, who is it that can tell me who I am? My acidophilus? A protein swimming in my bloodstream? Something in the wisp and whorl of my DNA strands? We all want the big answers: Is there some specter of disease that lurks microscopically in my mitochondria that will change my life? What is in my control and what is beyond it? At this point, none of these tests can tell us any of this. What they can do, to take a positive spin, is tell us how superhuman it’s possible for us to become—or, at the very least, guide us toward making more-informed choices. If you know you’re genetically prone to getting sunspots, maybe you’ll be more vigilant about SPF; if you know you’re metabolically sensitive to caffeine, maybe you’ll lay off the Red Bull. Perhaps it’s just that simple. They give us information and tools—the rest is up to us.
“Whose intern are you?” an ELLE fashion intern asked one afternoon a few weeks ago, breaking the silence as we rode the elevator.
Do I lack the commanding presence of an actual employee? Maybe. But that question didn’t even cross my mind. “I actually work here,” I said, not the least bit displeased despite the fact that the misidentification knocked me years back in my career.
“Oh, I thought you were, like, 20.”
“Nope, 31!” I declared proudly.
How old one looks often has little to do with how old one looks. I have a feeling people glance at me, and in that .6947 seconds it takes to form a (wholly unscientific) judgment, they’re more influenced by my shiny Disney princess sticker–adorned notebook and my zanily patterned culottes than by what’s actually happening on my face. But if you want to know—and address—what is really happening on your face, sometimes the human eye (especially one’s own) feels a little too fallible. Olay Skin Advisor, the brand’s just-launched online complexion assessor, is designed to deliver the cold, hard truth:
You log in, take a makeup-free selfie in even lighting, and answer a brief questionnaire about your skin-care preferences and current regimen. The computer analyzes your photo, deducing your “best” areas, “improvement” areas, and how old your skin actually appears—more on this in a second—and then lists corresponding product recommendations. The point is not to depress or elate, but rather to eliminate drugstore-aisle angst: Now you can use actual facts—not just how obsessed you happen to be with those (real or imagined) enlarged pores/forehead lines at any given moment—to ascertain your skin-care needs.
Sounds straightforward enough, but teaching a computer to judge something as variable as the human face is incredibly complex. Advisor is based on a school of artificial intelligence called deep learning, which is not totally unlike the process that went into building Samantha, the disembodied techno–Scarlett Johansson that Joaquin Phoenix fell for in Her. Samantha is a computer operating system who talks and feels and thinks like a free agent; she can even grasp abstractions, such as miffed undertones in a conversation. Similarly, Advisor appears to have a range of thinking that surpasses what we imagine to be programmable. Deep learning, a type of machine intellect that uses algorithms to transmit information in both linear and nonlinear ways, is inspired by the way the human brain processes visual information. Just as a baby, looking at dog after dog after dog, learns to piece together the fact that a certain type of snout, fur, and paws make up...a dog!, deep learning uses multiple cognitive layers to identify an image. “The lower layers are doing simple processing tasks, such as detecting edges and spots; those detected low-level features are fed into the next layer, which can combine those edges and spots into more complex shapes; those shapes are in turn fed into a higher layer, and so on,” says Jun Xu, PhD, Procter & Gamble principal scientist of bioinformatics and one of the creators of Advisor. Facebook employs deep learning to identify and auto-tag your friends; Google’s search function, Apple’s Siri, and self-driving cars also rely on the process. Further proof that deep learning is the future: Intel recently purchased deep learning–savvy start-up Nervana Systems, reportedly for more than $400 million.
For its initial tests, Olay fed thousands of faces of women ages 18 and over of all ethnicities into Advisor; now that the company is launching the program globally, it’s hoping to get to 500,000 faces by the end of December. Olay engineers didn’t program Advisor to seek signs of aging; rather, the program uses its growing database to continually layer new attributes and imperfections into its perceptions of the face, in order to deeply understand all the variations of, say, the 27-year-old face, and thereby differentiate it from one that reads as 26 or 28—or 68. “Every time it receives a new selfie, it fine-tunes its knowledge of what the face of a certain age looks like, essentially growing smarter with every use,” says Olay principal scientist Frauke Neuser, PhD. Advisor rates overall skin texture as well as five key zones (forehead, cheek, chin, crow’s-feet, undereye) and then, says Neuser, “combines all of this to make the best guess.”
To test Advisor’s accuracy, in March 2016 Olay took the program to the American Academy of Dermatology convention to pit it against the skin-age–assessing powers of 350 dermatologists. Advisor proved more accurate than doctors 94 percent of the time.
But accuracy can be a bitch. Perhaps it was that life-affirming elevator interaction, but I submitted myself to Advisor with zero hesitation. The machine’s verdict: I look 29. My crow’s-feet are my “best area”; undereye is my “improvement area,” for which the computer recommended Olay Ultimate Eye Cream.
I know what you’re thinking: Great! What’s the problem? But the verdict stung ever so slightly. And a colleague whose actual age is 39 but whose Advisor age is 36—with room for improvement identified around her mouth, an area she’d never given much thought to—experienced a similar rush of angst. Point is, good news still feels a little bad, in that even if you’re aging well, there’s no doubt: You are aging. Blame our culture—heck, blame women’s magazines—but ridiculous as it sounds, it’s hard not to hear that as confirmation of a negative. But hey, it beats the alternative! “The tool isn’t telling a woman something she’s never thought before,” Neuser says. “Advisor is simply looking at you and taking away the human bias.” My takeaway: I’m all for technology that helps me figure out the smartest way to take care of my skin. But let’s hold tight to the adage “Age is but a number.”
*ANSWER KEY (A) Actual Age: 24. Skin Age: 25. (B) AA: 41. SA: 40. (C) AA: 47. SA: 32. (D) AA: 46. SA: 40. (E) AA: 37. SA: 29. (F) AA: 27. SA: 32. (G) AA: 36. SA: 34.
Which sunscreens work, which fall short—and why you can’t always rely on packaging labels.
You know Ashley Graham as the world's most glorious, body-positive model. Now get ready to meet her as a sexual revolutionary (who gives laugh-out-loud bedroom advice).
Warm-weather fun can wreak havoc on your strands. Treat them to a little TLC with these easy tricks from the pros.
From creamy smoothie bowls to satisfying soups and veg-packed grain bowls, these whole-food lunches and dinners will keep you feeling happy and healthy. Inspired by global ﬂavors and brimming with seasonal produce, these dishes are livened up by ingredients like fragrant herbs, superfood powders, nuts, seeds and more.