Quantification of Smoking Characteristics Using Smartwatch Technology: Pilot Feasibility Study of New Technology

Smartband-based smoking detection and real-time brief mindfulness intervention: findings from a feasibility clinical trial

BACKGROUND

Smartbands can be used to detect cigarette smoking and deliver real time smoking interventions. Brief mindfulness interventions have been found to reduce smoking.

OBJECTIVE

This single arm feasibility trial used a smartband to detect smoking and deliver brief mindfulness exercises.

METHODS

Daily smokers who were motivated to reduce their smoking wore a smartband for 60 days. For 21 days, the smartband monitored, detected and notified the user of smoking in real time. After 21 days, a 'mindful smoking' exercise was triggered by detected smoking. After 28 days, a 'RAIN' (recognize, allow, investigate, nonidentify) exercise was delivered to predicted smoking. Participants received mindfulness exercises by text message and online mindfulness training. Feasibility measures included treatment fidelity, adherence and acceptability.

RESULTS

Participants (N=155) were 54% female, 76% white non-Hispanic, and treatment starters (n=115) were analyzed. Treatment fidelity cutoffs were met, including for detecting smoking and delivering mindfulness exercises. Adherence was mixed, including moderate smartband use and low completion of mindfulness exercises. Acceptability was mixed, including high helpfulness ratings and mixed user experiences data. Retention of treatment starters was high (81.9%).

CONCLUSIONS

Findings demonstrate the feasibility of using a smartband to track smoking and deliver quit smoking interventions contingent on smoking.

Pilot Testing of an mHealth App for Tobacco Cessation in People Living With HIV: Protocol for a Pilot Randomized Controlled Trial

BACKGROUND

An estimated 40% of people living with HIV smoke cigarettes. Although smoking rates in the United States have been declining in recent years, people living with HIV continue to smoke cigarettes at twice the rate of the general population. Mobile health (mHealth) technology is an effective tool for people living with a chronic illness, such as HIV, as currently 84% of households in the United States report that they have a smartphone. Although many studies have used mHealth interventions for smoking cessation, few studies have recruited people living with HIV who smoke.

OBJECTIVE

The objective of the pilot randomized controlled trial (RCT) is to examine the feasibility, acceptability, and preliminary efficacy of the Sense2Quit App as a tool for people living with HIV who are motivated to quit smoking.

METHODS

The Sense2Quit study is a 2-arm RCT for people living with HIV who smoke cigarettes (n=60). Participants are randomized to either the active intervention condition, which consists of an 8-week supply of nicotine replacement therapy, standard smoking cessation counseling, and access to the Sense2Quit mobile app and smartwatch, or the control condition, which consists of standard smoking cessation counseling and a referral to the New York State Smokers' Quitline. The Sense2Quit app is a mobile app connected through Bluetooth to a smartwatch that tracks smoking gestures and distinguishes them from other everyday hand movements. In the Sense2Quit app, participants can view their smoking trends, which are recorded through their use of the smartwatch, including how often or how much they smoke and the amount of money that they are spending on cigarettes, watch videos with quitting tips, information, and distractions, play games, set reminders, and communicate with a study team member.

RESULTS

Enrollment of study participants began in March 2023 and is expected to end in October 2023. All data collection is expected to be completed by the end of January 2024. This RCT will test the difference in outcomes between the control and intervention arms. The primary outcome will be the percentage of participants with biochemically verified 7-day point prevalence smoking or tobacco abstinence at their 12-week follow-up. Results from this pilot study will be disseminated to the research community following the completion of all data collection.

CONCLUSIONS

The Sense2Quit study leverages mHealth so that it can help smokers improve their efforts at smoking cessation. Our research has the potential to not only increase quitting rates among people living with HIV who may need a prolonged, tailored intervention but also inform further development of mHealth for people living with HIV. This mHealth study will contribute significant findings to the greater mHealth research community, providing evidence as to how mHealth should be developed and tested among the target population.

TRIAL REGISTRATION

ClinicalTrials.gov NCT05609032; https://clinicaltrials.gov/study/NCT05609032.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/49558.

E-cigarette puffing topography: The importance of assessing user behaviour to inform emissions testing

Analysis of the chemical composition of e-cigarette emissions is an important step in determining whether e-cigarettes offer both individual and population-level harm reduction potential. Commonly, e-cigarette emissions for chemical analysis are collected when using e-cigarettes according to standardised puffing regimens, such as those recommended by the International Organization for Standardization (ISO) or the Cooperation Centre for Scientific Research Relative to Tobacco (CORESTA). While the use of such standard puffing regimens affords a degree of uniformity between studies and are also recommended by regulatory authorities who require the submission of e-cigarette emissions data to make decisions regarding allowing a product to be commercially marketed, the standardised regimens do not necessarily reflect human puffing behaviour. This can lead to under- or over-estimating real-world emissions from e-cigarettes and inaccuracy in determining their harm reduction potential. In this review, we describe how human puffing behaviour (topography) information can be collected both in the clinical laboratory and in the real world using a variety of different methodologies. We further discuss how this information can be used to dictate e-cigarette puffing regimens for collecting emissions for chemical analyses and how this may lead to better predictions both of human yields of e-cigarette emissions constituents and of risk assessments to predict e-cigarette tobacco harm reduction potential.

Comprehensive and User-Analytics-Friendly Cancer Patient Database for Physicians and Researchers

Nuanced cancer patient care is needed, as the development and clinical course of cancer is multifactorial with influences from the general health status of the patient, germline and neoplastic mutations, co-morbidities, and environment. To effectively tailor an individualized treatment to each patient, such multifactorial data must be presented to providers in an easy-to-access and easy-to-analyze fashion. To address the need, a relational database has been developed integrating status of cancer-critical gene mutations, serum galectin profiles, serum and tumor glycomic profiles, with clinical, demographic, and lifestyle data points of individual cancer patients. The database, as a backend, provides physicians and researchers with a single, easily accessible repository of cancer profiling data to aid-in and enhance individualized treatment. Our interactive database allows care providers to amalgamate cohorts from these groups to find correlations between different data types with the possibility of finding "molecular signatures" based upon a combination of genetic mutations, galectin serum levels, glycan compositions, and patient clinical data and lifestyle choices. Our project provides a framework for an integrated, interactive, and growing database to analyze molecular and clinical patterns across cancer stages and subtypes and provides opportunities for increased diagnostic and prognostic power.

Detecting Medication-Taking Gestures Using Machine Learning and Accelerometer Data Collected Via Smartwatch Technology: A Feasibility Study (Preprint)

BACKGROUND

Medication adherence is a global public health challenge, as only approximately 50% of people adhere to their medication regimens. Medication reminders have shown promising results in terms of promoting medication adherence. However, practical mechanisms to determine whether a medication has been taken or not, once people are reminded, remain elusive. Emerging smartwatch technology may more objectively, unobtrusively, and automatically detect medication taking than currently available methods.

OBJECTIVE

This study aimed to examine the feasibility of detecting natural medication-taking gestures using smartwatches.

METHODS

A convenience sample (N=28) was recruited using the snowball sampling method. During data collection, each participant recorded at least 5 protocol-guided (scripted) medication-taking events and at least 10 natural instances of medication-taking events per day for 5 days. Using a smartwatch, the accelerometer data were recorded for each session at a sampling rate of 25 Hz. The raw recordings were scrutinized by a team member to validate the accuracy of the self-reports. The validated data were used to train an artificial neural network (ANN) to detect a medication-taking event. The training and testing data included previously recorded accelerometer data from smoking, eating, and jogging activities in addition to the medication-taking data recorded in this study. The accuracy of the model to identify medication taking was evaluated by comparing the ANN's output with the actual output.

RESULTS

Most (n=20, 71%) of the 28 study participants were college students and aged 20 to 56 years. Most individuals were Asian (n=12, 43%) or White (n=12, 43%), single (n=24, 86%), and right-hand dominant (n=23, 82%). In total, 2800 medication-taking gestures (n=1400, 50% natural plus n=1400, 50% scripted gestures) were used to train the network. During the testing session, 560 natural medication-taking events that were not previously presented to the ANN were used to assess the network. The accuracy, precision, and recall were calculated to confirm the performance of the network. The trained ANN exhibited an average true-positive and true-negative performance of 96.5% and 94.5%, respectively. The network exhibited <5% error in the incorrect classification of medication-taking gestures.

CONCLUSIONS

Smartwatch technology may provide an accurate, nonintrusive means of monitoring complex human behaviors such as natural medication-taking gestures. Future research is warranted to evaluate the efficacy of using modern sensing devices and machine learning algorithms to monitor medication-taking behavior and improve medication adherence.