Healthcare IT’s Achilles’ Heel: Sensors

A future version of this device will actively scream at you to run faster.

I’ve been wearing a Nike FuelBand for about a week now, and it’s already changed how I view so-called “Big Data.”

For several quarters, tech publications and pundits alike have crowed about the benefits we’re soon to collectively reap from healthcare analytics. In theory, sensors attached to our bodies (and appliances such as the fridge) will send a stream of health-related data—everything from calorie and footstep counts to blood pressure and sleep activity—to the cloud, which will analyze it for insight; doctors and other healthcare professionals will use that data to tailor treatments or advise changes in behavior and diet. If nothing else, it could translate into significant revenues for everyone from data-analytics firms to hardware builders.

That healthcare data could also come from a variety of sources, not just a set of devices or sensors—if you shop for food online, for example, that information could end up folded into the larger dataset. “There are many elements of what we do every day,” Susan Desmond-Hellmann, chancellor at the University of California, San Francisco, said during a Forbes Healthcare Summit earlier in 2013, “if it’s talking into our iPhone, where we do our grocery shopping, our exercise habits, there are many behavioral outputs that others like Amazon, like Google, are measuring about us that our caregivers don’t have access to and we as patients can’t use.”

Access aside, one of the most crucial elements in that equation could have a long way to go before it’s sufficiently sophisticated to support the rest of the ecosystem. My FuelBand seamlessly connects with my iPhone, which displays colorful graphs of my physical activity. It’s a tracking system that seems somewhat imprecise, at least to my highly subjective view, when running five-point-five miles through a heavy snowstorm racks up 1,749 “points” (despite all the huffing and puffing), but merely swinging my arm around for three minutes quickly racks up 150 points or more. (In other words, it’s not great on accurately gauging some types of activity.) Nor do these “smart bracelets” calculate caloric intake, a vital fitness gauge; with FitBit, a competing device, users must manually input their daily food intake.

Health apps for mobile devices aren’t much better when it comes to accurately recording physiological information; the need to manually input data makes them somewhat cumbersome to use, and people often give up after a few days or weeks. But more automated methods are coming: Oracle, for example, has invested in research firm Proteus, which develops FDA-approved ingestible sensors that can be slipped inside a pharmaceutical; once the patent swallows that particular pill, the sensor begins communicating with another sensor worn on the skin. Oracle and Proteus plan to collaborate on clinical trials that will improve the ability of medical researchers to draw precise data from the sensors.

Once more sensitive hardware arrives on the market—whether in the form of wristbands, digital pills, or something else entirely—it could give doctors, researchers, and patients better access to “good” data that can actually make a difference in research and treatment. But given the current state of monitoring hardware—and perhaps many folks’ aversion to giving up their personal data to the cloud—it may take some time to reach that plateau.


Image: Nike