# Smartband/smartphone-based automatic smoking detection and real time mindfulness intervention

> **NIH NIH R34** · YALE UNIVERSITY · 2020 · $376,875

## Abstract

PROJECT SUMMARY
Smoking is the leading cause of preventable death in the US. Effective smoking cessation interventions are
available but underutilized. Smoking cessation interventions delivered by smartphone apps are a promising
tool for helping smokers quit. Delivery of treatments via smartphone apps may maximize the likelihood of use
by smokers and the potential impact on smoking behavior. However, currently available smartphone apps for
smoking cessation have not exploited their unique potential advantages to aid quitting. Notably, no available
apps utilize wearable technologies; all current apps require users to self-report their smoking; and no apps
deliver treatment automatically contingent upon smoking. Therefore, this pilot trial will test the feasibility of
using a smartband to detect and track smoking and deliver brief smoking cessation interventions by
smartphone app in real time. The interventions to be delivered will be brief mindfulness exercises that have
been previously shown to reduce craving and smoking. This trial uses SmokeBeat, a novel mobile technology
platform that uses multimodal data from wristband sensors to monitor and detect smoking, notify smokers
about their smoking in real time and deliver real time interventions triggered by detected smoking episodes.
SmokeBeat also applies machine learning to smoking tracking data to identify individual smoking patterns and
deliver real time interventions targeted at predicted smoking episodes. This trial tests a three-step intervention
to reduce smoking, in which smokers first become aware of their smoking and triggers by tracking smoking;
then gain a clear recognition of the actual effects of smoking by “mindful smoking”; and finally learn to work
mindfully with cravings rather than smoke. Briefly, daily smokers (N=200, ≥5 cig/day) will wear a smartband to
detect and notify them of smoking for 21 days and obtain individual smoking profiles; detected smoking will
then trigger a “mindful smoking” exercise for the next 7 days leading up to their quit date at 30 days; after
which another mindfulness exercise (“RAIN”: recognize, accept, investigate and note cravings rather than
smoke) will be delivered prior to each predicted smoking episode according to their individual smoking profile
for 30 days post-quit. Aim 1 will be to determine treatment fidelity. Fidelity measures will be: (1) percent of
smoking episodes correctly detected; (2) percent of “mindful smoking” exercises correctly triggered by
smoking; and (3) users’ real time ratings of how timely “RAIN” was delivered to predicted smoking episodes.
Aim 2 will be to determine adherence to treatment. Adherence measures will be: (1) percent of time spent
wearing the smartband; (2) percent of smoking notifications answered; (3) percent of ecological momentary
assessment (EMA) ratings (e.g., timeliness and others) answered; and (4) percent of mindfulness exercises
completed. Aim 3 will be to determine the acceptability of treatment. ...

## Key facts

- **NIH application ID:** 9925202
- **Project number:** 5R34AT010365-02
- **Recipient organization:** YALE UNIVERSITY
- **Principal Investigator:** Kathleen A. GARRISON
- **Activity code:** R34 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2020
- **Award amount:** $376,875
- **Award type:** 5
- **Project period:** 2019-05-15 → 2022-10-31

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/9925202

## Citation

> US National Institutes of Health, RePORTER application 9925202, Smartband/smartphone-based automatic smoking detection and real time mindfulness intervention (5R34AT010365-02). Retrieved via AI Analytics 2026-06-11 from https://api.ai-analytics.org/grant/nih/9925202. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*