Dreamit Health alum Somatix announced the results of a pilot study testing SmokeBeat, the company’s smoking cessation monitoring solution. The results were published by Oxford University Press’ peer-reviewed journal, “Nicotine and Tobacco Research.”

The article, “Effect of real-time monitoring and notification of smoking episodes on smoking reduction: a pilot study of a novel smoking cessation app,” by Prof. Reuven Dar, from Tel Aviv University School of Psychological Sciences, outlines how SmokeBeat, a novel app powered by a data analytics software platform, processes information from the sensors embedded in wearables. This novel software platform relies on an original algorithm to identify in real-time hand-to-mouth gestures that characterize smoking a cigarette. Prof. Dar examined whether monitoring and notifying smokers about smoking episodes immediately via the SmokeBeat app would lead to a reduction in smoking.

“We were impressed with the results,” said Prof. Dar. “The SmokeBeat algorithm detected correctly more than 80% of the smoking episodes and produced very few false alarms. According to both self-report and detection of smoking episodes by the SmokeBeat system, smokers in the experimental condition showed a significant decline in their smoking rate while there was no change in the smoking rate of the control group. These results suggest that the SmokeBeat real-time automatic monitoring and notification feature may facilitate smoking reduction in smokers motivated to make life-improving changes.”

The pilot study included 40 smokers, (nine women and 31 men) who expressed a goal to reduce or quit smoking. Each was assigned randomly the SmokeBeat app for 30 days or to a wait-list control group. All participants completed questionnaires at baseline and at the end of the study, including their level of smoking during the test period. Smokers in the experimental group were notified whenever the SmokeBeat system detected a smoking episode and were asked to confirm or deny it.

SmokeBeat can leverage real-time CBT (Cognitive Behavior Therapy) principle-based intervention, providing smokers with personally tailored support information – reminders, probes, coping tactics – at just the right time. It also performs ongoing effectiveness assessment for treatments tailored specifically to individual smokers.

“The academic validation of our products, and collaboration with Prof. Dar, is enormously important to Somatix as it coincides with the launch of our smoking tracking and monitoring solution. It is our belief that SmokeBeat will improve user compliance and adherence with prescribed cessation therapies for optimal treatment efficacy,” said Eran Ofir, CEO of Somatix. “Peer-review publication of these findings is a significant affirmation as the Oxford University Press Journal, Nicotine and Tobacco Research selected to publish Prof. Dar’s research results.”

SmokeBeat leverages Big Data analysis for correlating smoking episodes with other analytics, to assess smoking patterns. The platform offers a set of key features such as automated smoking detection so that smokers do not have to record manually their smoking habits. It provides physicians, clinics and other health-service providers, as well as payors (health insurance companies) and the smokers themselves complete, ongoing information regarding treatment success in relation to predefined goals.

 

About Somatix

Big Data analytics software company Somatix is a pioneer in body motion detection for wearable-based preventative and rehabilitative healthcare, and well-being enhancement. Somatix BMD™ utilizes commercial off-the-shelf smartwatches, smartbands and other connected devices, advanced adaptive machine learning and predictive analytics, to precisely track and accurately recognize a range of hand gestures. Somatix digital health solutions ultimately enable enterprises, health insurance companies, clinics and elderly caregivers, among others, to costeffectively monitor, determine and improve the overall physical and emotional state of the people under their care.

[google74afd8188c8bfa4b.html]