Dataset Information

Using novel mobile sensors to assess stress and smoking lapse.

ABSTRACT: Mobile sensors can now provide unobtrusive measurement of both stress and cigarette smoking behavior. We describe, here, the first field tests of two such methods, cStress and puffMarker, that were used to examine relationships between stress and smoking behavior and lapse from a sample of 76 smokers motivated to quit smoking. Participants wore a mobile sensors suite, called AutoSense, which collected continuous physiological data for 4 days (24-hours pre-quit and 72-hours post-quit) in the field. Algorithms were applied to the physiological data to create indices of stress (cStress) and first lapse smoking episodes (puffMarker). We used mixed effects interrupted autoregressive time series models to assess changes in heart rate (HR), cStress, and nicotine craving across the 4-day period. Self-report assessments using ecological momentary assessment (EMA) of mood, withdrawal symptoms, and smoking behavior were also used. Results indicated that HR and cStress, respectively, predicted smoking lapse. These results suggest that measures of traditional psychophysiology, such as HR, are not redundant with cStress; both provide important information. Results are consistent with existing literature and provide clear support for cStress and puffMarker in ambulatory clinical research. This research lays groundwork for sensor-based markers in developing and delivering sensor-triggered, just-in-time interventions that are sensitive to stress-related lapser risk factors.

SUBMITTER: Nakajima M

PROVIDER: S-EPMC9195636 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using novel mobile sensors to assess stress and smoking lapse.

Nakajima Motohiro M Lemieux Andrine M AM Fiecas Mark M Chatterjee Soujanya S Sarker Hillol H Saleheen Nazir N Ertin Emre E Kumar Santosh S al'Absi Mustafa M

International journal of psychophysiology : official journal of the International Organization of Psychophysiology 20201113

Mobile sensors can now provide unobtrusive measurement of both stress and cigarette smoking behavior. We describe, here, the first field tests of two such methods, cStress and puffMarker, that were used to examine relationships between stress and smoking behavior and lapse from a sample of 76 smokers motivated to quit smoking. Participants wore a mobile sensors suite, called AutoSense, which collected continuous physiological data for 4 days (24-hours pre-quit and 72-hours post-quit) in the fiel ...[more]

PMID: 33189770

Similar Datasets

Project description:INTRODUCTION:Smoking prevalence continues to be high over the world and smoking-induced diseases impose a heavy burden on the medical care system. As believed by many researchers, a promising way to promote healthcare and well-being at low cost for the large vulnerable smoking population is through eHealth solutions by providing self-help information about smoking cessation. But in the absence of first-hand knowledge about smoking habits in daily life settings, systems built on these methods often fail to deliver proactive and tailored interventions for different users and situations over time, thus resulting in low efficacy. To fill the gap, an observational study has been developed on the theme of objective and non-biased monitoring of smoking habits in a longitudinal and ambulatory mode. This paper presents the study protocol. The primary objective of the study is to reveal the contextual and physiological pattern of different smoking behaviours using wearable sensors and mobile phones. The secondary objectives are to (1) analyse cue factors and contextual situations of smoking events; (2) describe smoking types with regard to users' characteristics and (3) compare smoking types between and within subjects. METHODS AND ANALYSES:This is an observational study aimed at reaching 100 participants. Inclusion criteria are adults aged between 18 and 65 years, current smoker and office worker. The primary outcome is a collection of a diverse and inclusive data set representing the daily smoking habits of the general smoking population from similar social context. Data analysation will revolve around our primary and secondary objectives. First, linear regression and linear mixed model will be used to estimate whether a factor or pattern have consistent (p value<0.05) correlation with smoking. Furthermore, multivariate multilevel analysis will be used to examine the influence of smokers' characteristics (sex, age, education, socioeconomic status, nicotine dependence, attitudes towards smoking, quit attempts, etc), contextual factors, and physical and emotional statuses on their smoking habits. Most recent machine learning techniques will also be explored to combine heterogeneous data for classification of smoking events and prediction of craving. ETHICS AND DISSEMINATION:The study was designed together by an interdisciplinary group of researchers, including psychologist, psychiatrist, engineer and user involvement coordinator. The protocol was reviewed and approved by the ethical review board of UZ Leuven on 18 April 2016, with an approval number S60078. The study will allow us to characterise the types of smokers and triggering events. These findings will be disseminated through peer-reviewed articles.

Project description:Background: While preliminary evidence suggests that sensors may be employed to detect presence of low mood it is still unclear whether they can be leveraged for measuring depression symptom severity. This study evaluates the feasibility and performance of assessing depressive symptom severity by using behavioral and physiological features obtained from wristband and smartphone sensors. Method: Participants were thirty-one individuals with Major Depressive Disorder (MDD). The protocol included 8 weeks of behavioral and physiological monitoring through smartphone and wristband sensors and six in-person clinical interviews during which depression was assessed with the 17-item Hamilton Depression Rating Scale (HDRS-17). Results: Participants wore the right and left wrist sensors 92 and 94% of the time respectively. Three machine-learning models estimating depressive symptom severity were developed-one combining features from smartphone and wearable sensors, one including only features from the smartphones, and one including features from wrist sensors-and evaluated in two different scenarios. Correlations between the models' estimate of HDRS scores and clinician-rated HDRS ranged from moderate to high (0.46 [CI: 0.42, 0.74] to 0.7 [CI: 0.66, 0.74]) and had moderate accuracy with Mean Absolute Error ranging between 3.88 ± 0.18 and 4.74 ± 1.24. The time-split scenario of the model including only features from the smartphones performed the best. The ten most predictive features in the model combining physiological and mobile features were related to mobile phone engagement, activity level, skin conductance, and heart rate variability. Conclusion: Monitoring of MDD patients through smartphones and wrist sensors following a clinician-rated HDRS assessment is feasible and may provide an estimate of changes in depressive symptom severity. Future studies should further examine the best features to estimate depressive symptoms and strategies to further enhance accuracy.

Project description:IntroductionMachine learning algorithms such as elastic net regression and backward selection provide a unique and powerful approach to model building given a set of psychosocial predictors of smoking lapse measured repeatedly via ecological momentary assessment (EMA). Understanding these predictors may aid in developing interventions for smoking lapse prevention.MethodsIn a randomized-controlled smoking cessation trial, smartphone-based EMAs were collected from 92 participants following a scheduled quit date. This secondary analysis utilized elastic net-penalized cox proportional hazards regression and model approximation via backward elimination to (1) optimize a predictive model of time to first lapse and (2) simplify that model to its core constituent predictors to maximize parsimony and generalizability.ResultsElastic net proportional hazards regression selected 17 of 26 possible predictors from 2065 EMAs to model time to first lapse. The predictors with the highest magnitude regression coefficients were having consumed alcohol in the past hour, being around and interacting with a smoker, and having cigarettes easily available. This model was reduced using backward elimination, retaining five predictors and approximating to 93.9% of model fit. The retained predictors included those mentioned above as well as feeling irritable and being in areas where smoking is either discouraged or allowed (as opposed to not permitted).ConclusionsThe strongest predictors of smoking lapse were environmental in nature (e.g., being in smoking-permitted areas) as opposed to internal factors such as psychological affect. Interventions may be improved by a renewed focus of interventions on these predictors.ImplicationsThe present study demonstrated the utility of machine learning algorithms to optimize the prediction of time to smoking lapse using EMA data. The two models generated by the present analysis found that environmental factors were most strongly related to smoking lapse. The results support the use of machine learning algorithms to investigate intensive longitudinal data, and provide a foundation for the development of highly tailored, just-in-time interventions that can target on multiple antecedents of smoking lapse.

Project description:This paper describes the development and test of a smartphone application to quit smoking using cognitive behavioral therapy (CBT). The tool includes recommendations from US Clinical Practice Guidelines (USCPG), drawing on the potential of smartphones and complying with the health App (mHealth) assessment standards. The mHealth created, called NoFumo+, is structured by 4 weeks treatment, implements the USCPG 5A recommendations (ask, advise, assess, assist, and arrange) and incorporates a CBT. It also includes complementary information, monitoring of the smoking behavior, social support for users, proposals for alternative activities to smoking, and innovative gamification to encourage and reward adherence. To technical development, a multidisciplinary team was formed (healthcare, research, and software engineers) that made theoretical decisions on both technical issues and the incorporation of therapeutic techniques. The validation was carried out in two phases; the first in the laboratory by a group of experts in information and communication technologies and CBTs (n = 15) and the second, a field study with smokers (n = 10). The standards for the development of mHealth recommended by the Andalusian Healthcare Quality Agency and the App quality evaluation guidelines of the Catalonian ICT Foundation for Social Health were used as assessment protocols by the experts' panel and the smokers' group, respectively. Experts' assessment results were satisfactory and some improving changes were suggested, such as to add more gamification elements. The group of smokers rated the mHealth as 100% easy to use and effective for quit smoking and understandable by the 83.3%. They also found No Fumo + quite useful to have the information available at all times. The obtained evidence after a complete two-phased validation study, with experts and potential users, shows a mHealth with high quality and easy to use. Finally, investigation project registered in ClinicalTrials.gov with reference to this trial is registered with NCT045402004.

Dataset Information

Using novel mobile sensors to assess stress and smoking lapse.

Publications

Using novel mobile sensors to assess stress and smoking lapse.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets