Wearable Calorie Intake Tracking Devices Aren't There Yet

Although there are many promising “wearables” in the sports tracking and health monitoring arena (see Wearable Biometric Collectors: Coming Soon? in the last issue), one market promise that can be fairly described as hokum, at least so far, is the idea of wearable calorie intake tracking.

The folks at TechHive have recently weighed in on the real-world accuracy of several calorie tracking wristbands now on the market, with not so promising appraisals. Activity tracking wristbands from companies like Jawbone and Nike can do a pretty good job of telling us what’s happening on the back end of the “calorie in, calorie out” equation. They use accelerometers to monitor our exercise, then map that data against user-supplied criteria like age, height and weight. The wristbands then squeeze all this information through crude algorithms to tell us roughly how many calories we’ve burned.

Yet the “calorie in” measurement remains a wearables industry challenge. Many activity tracking wristbands integrate food-logging tools in their mobile apps to record calorie intake, but these functions are too time-consuming and clumsy. What the fitness-tech space really needs is a breakthrough in calorie intake tracking—some kind of sensor-laden wristband that automatically records how many calories we’re consuming in the food we eat.

Automatic calorie intake tracking is the next great thing, but it simply isn't there yet.

The trouble is, last year two fit-tech companies claiming breakthroughs in automatic calorie intake tracking have, as TechHive puts it, “crawled out of the crowd-funding woodwork.” Last October a wristband called AIRO was introduced, claiming spectroscopic sensors that can “divine calorie intake through the surface of one’s skin.” The company has since refunded pre-order payments from initial crowd-funding backers. There’s also GoBe, a wristband announced in Marchthat claims to “automatically tell you how many calories you consume and burn throughout the day.”

But the GoBe wristband uses a rudimentary impedance sensor to measure fluid levels in body tissue. This fluid-level data is then used to “calculate caloric intake through your skin, by reading the amount of glucose in your cells.”

To assess this claim, TechHive interviewed Ries Robinson, who has a medical degree from the University of New Mexico, a Masters in mechanical engineering from Stanford, and more than 20 years experience in developing systems for the optical measurement of body tissue. “The physical reality is, this is just ridiculous,” he says. “It doesn’t work at a medical level. It doesn’t work at a practical level.”

Wristbands, smart glasses and even smart jewelry are starting to emerge with extraordinary claims in what might be considered a “wearable gold rush.” For every Intel, Apple or Samsung there is a start-up with dubious and sometimes outrageous product claims avoiding traditional venture-capital sources by beelining to crowd-funding for development. As TechHive notes, “The GoBe wristband looks like a complete, finished product—glossy and polished, with a cleverly designed companion app. The entire package appears right at home next to the Jawbone UPs and Nike FuelBands of the world. But does it even deserve to be considered a viable (let alone competitive) product?”

And Airo Health can't explain in detail how the AIRO wristband tracks calories with a spectroscopic sensor, even backpedaling to state that it is more of a “nutrition sensor” than a “calorie sensor.” Based on published information about AIRO, it seems the wristband uses a miniaturized spectroscopic sensor similar to the technology once under development that attempted non-invasive blood glucose monitoring for diabetics—in essence using a very small flashlight and camera: An LED array shines different wavelengths of light through the skin, while a highly sensitive photo detector determines which wavelengths have been absorbed, and which have been reflected. The system then uses an algorithm to analyze this optical data to estimate calorie intake.

Airo Health denies that AIRO is a system primarily monitoring blood glucose levels. But they admit that the AIRO system has greater success in tracking carbohydrates than other types of food. Airo Health suspended its crowd-funded pre-order campaign in large part because they couldn’t produce reliable, scalable results beyond the lab environment, they say.

TechHive writes, “Robinson’s takeaway is that AIRO is focused on blood glucose, just like the GoBe system, and this is already an invalid calorie-tracking model, as it doesn’t account for dietary proteins and fats. But even more damaging, if we assume AIRO is 'just' a blood-glucose sensor, it still wouldn’t have enough science behind it to produce reliable results.”

They quote Robinson: “Is it plausible by using one or two light emitting diodes—which looks to be the case with AIRO—could you measure glucose in the tissue with that type of optical platform? The answer is no.”

Consumer tolerance for inaccuracy is already pretty high for activity tracking wearables. After all, accelerometer-based reports are inconsistent from platform to platform: If you wear three different activity trackers on your arm, each will report different step counts and calorie-burn numbers.

What’s more important to consumers, it seems, is that calorie burn reports prove accurate within the context of their own closed platforms. In turn, wristband manufacturers typically publish some type of claim regarding the accuracy of their step counts and calorie-burn algorithms. But it seems calorie intake tracking doesn't yet approach a minimum level of accountability. Companies will keep trying, but this “holy grail of fit-tech” has yet to emerge for real.

TechHive, “Wearable snake oil: The search for automatic calorie intake tracking in fit-tech wristbands,” by Jon Phillips, March 24, 2014, http://www.techhive.com/article/2110429/wearable-snake-oil-the-search-for-automatic-calorie intake-tracking-in-fit-tech-wristbands.html

(return to front page)