Fit­ness trackers accounted for more than half of the 35 mil­lion wear­able devices in use at the end of 2014, according to a report by global ana­lyst CCS Insight. Here, Stephen Intille, the co-​​founder of Northeastern’s per­sonal health infor­matics doc­toral pro­gram and an asso­ciate pro­fessor with joint appoint­ments in the Bouvé Col­lege of Health Sci­ences and the Col­lege of Com­puter and Infor­ma­tion Sci­ence, explains what we can expect from fit­ness tech in 2015.

In 2015 we are likely to see the introduction of even more watch-like devices that are capable of gathering fitness data but also serving other personal and productivity needs. Industry will compete to add an increasing number of sensors to the devices, measuring information such as body motion, location, heart rate, galvanic skin response (i.e., sweating), and skin temperature. The newest devices already have sophisticated input/output options, such as touch screens, radio frequency identification tags, and speech input, as well as audio and tactile output. The somewhat bulky devices introduced in 2013-14 will slim down and become more stylish, and developers will figure out user interface conventions that make the devices easier to use.

The biggest surprise in 2015 may not be how consumers use these devices for health, but rather an increasing awareness that the devices improve the utility of the mobile phone. A smartwatch that can automatically detect whether its user is walking, for instance, can make interaction with that person’s mobile phone more pleasant and efficient, such as by automatically changing availability states and the way in which people are notified of messages. The good news is that people will get in the habit of using these devices for everyday tasks, and that will create more opportunities to use the devices to also support health.

Fitness trackers will definitely play a role in the future of our healthcare, as our “sick” care system transitions toward proactive, wellness-based care. Convenient, continuous, and autonomous data gathering on health-related behaviors will be necessary if we are to cost-effectively help hundreds of millions of Americans stay healthy and fit, while at the same time reducing their need for costly clinical and specialist care.

Nevertheless, the PricewaterhouseCoopers study is a somewhat troubling example of how industry and consumer enthusiasm for the commercial devices may exceed the scientific evidence demonstrating their effectiveness. Few well-designed studies have shown that use of wearable fitness technologies leads to long-term, sustainable health and sustained healthy behavior in the general population. In fact, anecdotal evidence suggests that many consumer fitness devices may be abandoned not long after purchase, relegated to the same drawers as pedometers, home exercise videos, food portion measurement cups, and weights. There is a risk that the public and business community will become prematurely disgruntled with the promise of wearable fitness technology before the truly novel uses and benefits of the technology are discovered and definitively proven. As researchers, we have our work cut out for us.

We are working in two areas: improving health behavior measurement using mobile phones and wearable devices, and then using that information to create new just-in-time interventions that help people make and sustain desired behavior changes. In particular, we are exploring how mobile phones and smartwatches can be used to incrementally build up mathematical models of a person’s typical behavior so that we can identify habits. The phone or watch does what it can automatically, inferring some information about physical activity and sleep patterns, but it also asks for information from the person when it needs it. The trick is to figure out ways of doing this so that the user doesn’t feel burdened, even though the automatic sensing will never be perfect.

At the same time, we are developing ideas for how real-time knowledge of what the person is doing can be used to influence behavior by providing computer- and human-generated feedback timed precisely at actionable points of decision. Our goal is to create novel interventions that help people change habits and then maintain those habits for very long periods of time. We want to take advantage of the ability of the computer to patiently and ever-presently measure and model behavior and decision making, and then to use that information to intervene in a compelling way, just when a person is most receptive to help.