A mobile health project at Stevens Institute of Technology in Hoboken, N.J., funded by the National Science Foundation is taking a novel approach to mHealth apps by leveraging advanced sensors built into smartphones, as well as external wearable sensors, the school announced this week. Unlike currently available mHealth apps that rely on users manually entering data, a smartphone-enabled social and physical compass system (SENSCOPS) has been developed to provide tailored health recommendations based on automatically collected data.
Yingying Chen, director of the Data Analysis and Information Security Lab in Stevens' Department of Electrical and Computer Engineering, is the researcher who received the NSF grant for her work on the SENSCOPS, which collects physiological data, such as heart rate, respiratory rate, and body temperature. By continuously collecting and monitoring such measurements of daily activity, users are able to receive feedback responses to their everyday lifestyle choices to better manage their health.
According to researchers at Stevens, SENSCOPS has the potential to reduce healthcare costs as an effective method of preventative care. As healthcare costs continue to rise, policymakers are looking to preventative care to alleviate the burden on the U.S. economy. The adoption of mHealth applications and technologies could significantly lower healthcare costs, which overwhelmingly are spent on the treatment of chronic disease.
The automated data collection ability makes SENSCOPS particularly beneficial for vulnerable populations who may not have the capacity to take care of themselves, such as seniors and children with emotional behavior disorders. For the latter, in particular, the analyzed data can be used to infer helpful information, such as behavioral side effects of certain drugs and environments that trigger certain stereotypical behaviors. Feedback is sent to users about further actions they can take to proactively limit activities that may lead to future illnesses, or methods of adapting problematic behaviors into socially acceptable responses.
In related research, researchers at the Georgia Institute of Technology are aiding autism diagnosis and management with a wearable sensor system to help detect harmful "problem behaviors." In tests of the technology on a child on the autism spectrum, the sensors were able to detect problem-behavior episodes with 81 percent accuracy, and classify them with 70 percent accuracy.
To learn more:
- read the announcement