scholarly journals mPulse Mobile Sensing Model for Passive Detection of Impulsive Behavior: Exploratory Prediction Study

10.2196/25019 ◽  
2021 ◽  
Vol 8 (1) ◽  
pp. e25019
Author(s):  
Hongyi Wen ◽  
Michael Sobolev ◽  
Rachel Vitale ◽  
James Kizer ◽  
J P Pollak ◽  
...  
Keyword(s):  
Mental Health ◽  
Mobile Phone ◽  
Risk Taking ◽  
Sensation Seeking ◽  
Mobile Sensing ◽  
Self Report ◽  
Sensor Data ◽  
Impulsive Behavior ◽  
Battery Charging ◽  
Passive Sensing

Background Mobile health technology has demonstrated the ability of smartphone apps and sensors to collect data pertaining to patient activity, behavior, and cognition. It also offers the opportunity to understand how everyday passive mobile metrics such as battery life and screen time relate to mental health outcomes through continuous sensing. Impulsivity is an underlying factor in numerous physical and mental health problems. However, few studies have been designed to help us understand how mobile sensors and self-report data can improve our understanding of impulsive behavior. Objective The objective of this study was to explore the feasibility of using mobile sensor data to detect and monitor self-reported state impulsivity and impulsive behavior passively via a cross-platform mobile sensing application. Methods We enrolled 26 participants who were part of a larger study of impulsivity to take part in a real-world, continuous mobile sensing study over 21 days on both Apple operating system (iOS) and Android platforms. The mobile sensing system (mPulse) collected data from call logs, battery charging, and screen checking. To validate the model, we used mobile sensing features to predict common self-reported impulsivity traits, objective mobile behavioral and cognitive measures, and ecological momentary assessment (EMA) of state impulsivity and constructs related to impulsive behavior (ie, risk-taking, attention, and affect). Results Overall, the findings suggested that passive measures of mobile phone use such as call logs, battery charging, and screen checking can predict different facets of trait and state impulsivity and impulsive behavior. For impulsivity traits, the models significantly explained variance in sensation seeking, planning, and lack of perseverance traits but failed to explain motor, urgency, lack of premeditation, and attention traits. Passive sensing features from call logs, battery charging, and screen checking were particularly useful in explaining and predicting trait-based sensation seeking. On a daily level, the model successfully predicted objective behavioral measures such as present bias in delay discounting tasks, commission and omission errors in a cognitive attention task, and total gains in a risk-taking task. Our models also predicted daily EMA questions on positivity, stress, productivity, healthiness, and emotion and affect. Perhaps most intriguingly, the model failed to predict daily EMA designed to measure previous-day impulsivity using face-valid questions. Conclusions The study demonstrated the potential for developing trait and state impulsivity phenotypes and detecting impulsive behavior from everyday mobile phone sensors. Limitations of the current research and suggestions for building more precise passive sensing models are discussed. Trial Registration ClinicalTrials.gov NCT03006653; https://clinicaltrials.gov/ct2/show/NCT03006653

scholarly journals mPulse Mobile Sensing Model for Passive Detection of Impulsive Behavior: Exploratory Prediction Study (Preprint)

2020 ◽  
Author(s):  
Hongyi Wen ◽  
Michael Sobolev ◽  
Rachel Vitale ◽  
James Kizer ◽  
JP Pollak ◽  
...  
Keyword(s):  
Mental Health ◽  
Mobile Phone ◽  
Risk Taking ◽  
Sensation Seeking ◽  
Mobile Sensing ◽  
Self Report ◽  
Sensor Data ◽  
Impulsive Behavior ◽  
Battery Charging ◽  
Passive Sensing

BACKGROUND Mobile health technology has demonstrated the ability of smartphone apps and sensors to collect data pertaining to patient activity, behavior, and cognition. It also offers the opportunity to understand how everyday passive mobile metrics such as battery life and screen time relate to mental health outcomes through continuous sensing. Impulsivity is an underlying factor in numerous physical and mental health problems. However, few studies have been designed to help us understand how mobile sensors and self-report data can improve our understanding of impulsive behavior. OBJECTIVE The objective of this study was to explore the feasibility of using mobile sensor data to detect and monitor self-reported state impulsivity and impulsive behavior passively via a cross-platform mobile sensing application. METHODS We enrolled 26 participants who were part of a larger study of impulsivity to take part in a real-world, continuous mobile sensing study over 21 days on both Apple operating system (iOS) and Android platforms. The mobile sensing system (mPulse) collected data from call logs, battery charging, and screen checking. To validate the model, we used mobile sensing features to predict common self-reported impulsivity traits, objective mobile behavioral and cognitive measures, and ecological momentary assessment (EMA) of state impulsivity and constructs related to impulsive behavior (ie, risk-taking, attention, and affect). RESULTS Overall, the findings suggested that passive measures of mobile phone use such as call logs, battery charging, and screen checking can predict different facets of trait and state impulsivity and impulsive behavior. For impulsivity traits, the models significantly explained variance in sensation seeking, planning, and lack of perseverance traits but failed to explain motor, urgency, lack of premeditation, and attention traits. Passive sensing features from call logs, battery charging, and screen checking were particularly useful in explaining and predicting trait-based sensation seeking. On a daily level, the model successfully predicted objective behavioral measures such as present bias in delay discounting tasks, commission and omission errors in a cognitive attention task, and total gains in a risk-taking task. Our models also predicted daily EMA questions on positivity, stress, productivity, healthiness, and emotion and affect. Perhaps most intriguingly, the model failed to predict daily EMA designed to measure previous-day impulsivity using face-valid questions. CONCLUSIONS The study demonstrated the potential for developing trait and state impulsivity phenotypes and detecting impulsive behavior from everyday mobile phone sensors. Limitations of the current research and suggestions for building more precise passive sensing models are discussed. CLINICALTRIAL ClinicalTrials.gov NCT03006653; https://clinicaltrials.gov/ct2/show/NCT03006653

Positive risk-taking: Mixed-methods validation of a self-report scale and evidence for genetic links to personality and negative risk-taking

2019 ◽  
Author(s):  
Megan Wales Patterson ◽  
Lilla Pivnick ◽  
Frank D Mann ◽  
Andrew D Grotzinger ◽  
Kathryn C Monahan ◽  
...  
Keyword(s):  
Youth Development ◽  
Risk Taking ◽  
Sensation Seeking ◽  
Empirical Work ◽  
Well Being ◽  
Population Based ◽  
Self Report ◽  
Personality Factors ◽  
Positive Behaviors ◽  
Adolescent Risk

Adolescents are more likely to take risks. Typically, research on adolescent risk-taking has focused on its negative health and societal consequences. However, some risk-taking behaviors might be positive, defined here as behavior that does not violate the rights of others and that might advance socially-valuable goals. Empirical work on positive risk-taking has been limited by measurement challenges. In this study, we elicited adolescents’ free responses (n = 75) about a time they took a risk. Based on thematic coding, we identified positive behaviors described as risks and selected items to form a self-report scale. The resulting positive risk-taking scale was quantitatively validated in a population-based sample of adolescent twins (n = 1249). Second, we evaluated associations between positive risk-taking, negative risk-taking, and potential personality and peer correlates using a genetically informed design. Sensation seeking predicted negative and positive risk-taking equally strongly, whereas extraversion differentiated forms of risk-taking. Additive genetic influences on personality accounted for the total heritability in positive risk-taking. Indirect pathways from personality through positive and negative peer environments were identified. These results provide promising evidence that personality factors of sensation seeking and extraversion can manifest as engagement in positive risks. Increased understanding of positive manifestations of adolescent risk-taking may yield targets for positive youth development strategies to bolster youth well-being.

scholarly journals How Perceived Individual Safety Attitude Helps to Explain The Relationship Between Sensation Seeking and Risk-Taking Propensity in The Prediction of Individual Work Performance

2021 ◽  
Vol 11 (2) ◽  
pp. 191
Author(s):  
Woromita Fathlistya ◽  
Martina Dwi Mustika
Keyword(s):  
Risk Taking ◽  
Sensation Seeking ◽  
Work Performance ◽  
Individual Performance ◽  
Cross Sectional Study ◽  
Self Report ◽  
Cross Sectional ◽  
Individual Work ◽  
Safety Attitude ◽  
The Relationship

Understanding the attitudes of individuals toward safety is important for hospital prevention programs and could reduce safety-related accidents. This study investigates the effects of perceived individual safety attitude in explaining the relationship between sensation seeking and risk-taking propensity for rewards in predicting individual performance. An on-line cross-sectional study was undertaken in which 177 nurses who completed an objective task (BART) and self-report questionnaires. Path analysis results revealed that perceived individual safety attitude influenced the relationship between both sensation seeking and risk-taking propensity in predicting individual performance. Nurses with both sensation seeking and risk-taking propensity for rewards have negative perceptions toward individual safety attitude, which resulted in poor individual work performances. It is indicated that encourage performance by rewards is not always effective.

scholarly journals Not All Risks Are Equal: The Risk Taking Inventory for High-Risk Sports

2013 ◽  
Vol 35 (5) ◽  
pp. 479-492 ◽  
Author(s):  
Tim Woodman ◽  
Matt Barlow ◽  
Comille Bandura ◽  
Miles Hill ◽  
Dominika Kupciw ◽  
...  
Keyword(s):  
High Risk ◽  
Risk Taking ◽  
Sensation Seeking ◽  
Behavioral Activation ◽  
Self Esteem ◽  
Self Report ◽  
Confirmatory Factor Analyses ◽  
Confirmatory Factor ◽  
Two Factors ◽  
Population Attitudes

Although high-risk sport participants are typically considered a homogenous risk-taking population, attitudes to risk within the high-risk domain can vary considerably. As no validated measure allows researchers to assess risk taking within this domain, we validated the Risk Taking Inventory (RTI) for high-risk sport across four studies. The RTI comprises seven items across two factors: deliberate risk taking and precautionary behaviors. In Study 1 (n = 341), the inventory was refined and tested via a confirmatory factor analysis used in an exploratory fashion. The subsequent three studies confirmed the RTI’s good model–data fit via three further separate confirmatory factor analyses. In Study 2 (n = 518) and in Study 3 (n = 290), concurrent validity was also confirmed via associations with other related traits (sensation seeking, behavioral activation, behavioral inhibition, impulsivity, self-esteem, extraversion, and conscientiousness). In Study 4 (n = 365), predictive validity was confirmed via associations with mean accidents and mean close calls in the high-risk domain. Finally, in Study 4, the self-report version of the inventory was significantly associated with an informant version of the inventory. The measure will allow researchers and practitioners to investigate risk taking as a variable that is conceptually distinct from participation in a high-risk sport.

scholarly journals Cortical Thickness Links Impulsive Personality Traits and Risky Behavior

2019 ◽  
Vol 9 (12) ◽  
pp. 373 ◽  
Author(s):  
Rickie Miglin ◽  
Nadia Bounoua ◽  
Shelly Goodling ◽  
Ana Sheehan ◽  
Jeffrey M. Spielberg ◽  
...  
Keyword(s):  
Personality Traits ◽  
Sensation Seeking ◽  
Risky Behavior ◽  
Factor Model ◽  
Community Sample ◽  
Self Report ◽  
Impulsive Behavior ◽  
Behavior Scale ◽  
The Right

Impulsive personality traits are often predictive of risky behavior, but not much is known about the neurobiological basis of this relationship. We investigated whether thickness of the cortical mantle varied as a function of impulsive traits and whether such variation also explained recent risky behavior. A community sample of 107 adults (ages 18–55; 54.2% men) completed self-report measures of impulsive traits and risky behavior followed by a neuroimaging protocol. Using the three-factor model of impulsive traits derived from the UPPS-P Impulsive Behavior Scale, analysis of the entire cortical mantle identified three thickness clusters that related to impulsive traits. Sensation seeking was negatively related to thickness in the right pericalcarine cortex, whereas impulsive urgency was positively associated with thickness in the left superior parietal and right paracentral lobule. Notably, follow-up analyses showed that thickness in the right pericalcarine cortex also related to recent risky behavior, with the identified cluster mediating the association between sensation seeking and risky behavior. Findings suggest that reduced thickness in the pericalcarine region partially explains the link between sensation seeking and the tendency to engage in risky behavior, providing new insight into the neurobiological basis of these relationships.

scholarly journals Automated Screening for Social Anxiety, Generalized Anxiety, and Depression From Objective Smartphone-Collected Data: Cross-sectional Study (Preprint)

2021 ◽  
Author(s):  
Daniel Di Matteo ◽  
Kathryn Fotinos ◽  
Sachinthya Lokuge ◽  
Geneva Mason ◽  
Tia Sternat ◽  
...  
Keyword(s):  
Mental Health ◽  
Anxiety Disorder ◽  
Social Anxiety ◽  
Mental States ◽  
Self Report ◽  
Sensor Data ◽  
Generalized Anxiety ◽  
Sufficient Information ◽  
Cross Sectional ◽  
Automated Screening

BACKGROUND The lack of access to mental health care could be addressed, in part, through the development of automated screening technologies for detecting the most common mental health disorders without the direct involvement of clinicians. Objective smartphone-collected data may contain sufficient information about individuals’ behaviors to infer their mental states and therefore screen for anxiety disorders and depression. OBJECTIVE The objective of this study is to compare how a single set of recognized and novel features, extracted from smartphone-collected data, can be used for predicting generalized anxiety disorder (GAD), social anxiety disorder (SAD), and depression. METHODS An Android app was designed, together with a centralized server system, to collect periodic measurements of objective smartphone data. The types of data included samples of ambient audio, GPS location, screen state, and light sensor data. Subjects were recruited into a 2-week observational study in which the app was run on their personal smartphones. The subjects also completed self-report severity measures of SAD, GAD, and depression. The participants were 112 Canadian adults from a nonclinical population. High-level features were extracted from the data of 84 participants, and predictive models of SAD, GAD, and depression were built and evaluated. RESULTS Models of SAD and depression achieved a significantly greater screening accuracy than uninformative models (area under the receiver operating characteristic means of 0.64, SD 0.13 and 0.72, SD 0.12, respectively), whereas models of GAD failed to be predictive. Investigation of the model coefficients revealed key features that were predictive of SAD and depression. CONCLUSIONS We demonstrate the ability of a common set of features to act as predictors in the models of both SAD and depression. This suggests that the types of behaviors that can be inferred from smartphone-collected data are broad indicators of mental health, which can be used to study, assess, and track psychopathology simultaneously across multiple disorders and diagnostic boundaries.

scholarly journals The assessment of physical risk taking: Preliminary construct validation of a new behavioral measure

PLoS ONE ◽  
2021 ◽  
Vol 16 (10) ◽  
pp. e0258826
Author(s):  
Edward A. Smith ◽  
Stephen D. Benning
Keyword(s):  
Risk Taking ◽  
Real World ◽  
Sensation Seeking ◽  
Risky Behaviors ◽  
Self Report ◽  
Behavioral Measure ◽  
Behavioral Risk ◽  
Exploratory Investigation ◽  
Outcome Scores ◽  
Physical Risk

Risk taking is a complex heterogeneous construct that has proven difficult to assess, especially when using behavioral tasks. We present an exploratory investigation of new measure–the Assessment of Physical Risk Taking (APRT). APRT produces a variety of different outcome scores and is designed as a comprehensive assessment of the probability of success and failure, and magnitude of reward and punishment of different types of simulated physically risky behaviors. Effects observed on the simulated behaviors are hypothesized to reflect similar effects on real world physical risks. Participants (N = 224) completed APRT in a laboratory setting, half of whom had a 1.5 s delay interposed between button presses. Exploratory analyses utilizing generalized estimating equations examined the main effects and two-way interactions among five within-subject factors, as well as two-way interactions between the within-subject factors and Delay across four APRT outcome scores. Results indicated that Injury Magnitude and Injury Probability exerted stronger effects than any of the other independent variables. Participants also completed several self-report measures of risk taking and associated constructs (e.g., sensation seeking), which were correlated with APRT scores to assess the preliminary convergent and divergent validity of the new measure. After correcting for multiple comparisons, APRT scores correlated with self-reported risk taking in thrilling, physically dangerous activities specifically, but only for those who did not have a delay between APRT responses. This promising exploratory investigation highlights the need for future studies comparing APRT to other behavioral risk taking tasks, examining the robustness of the observed APRT effects, and investigating how APRT may predict real-world physical risk taking.

scholarly journals Examination of the SUPPS-P Impulsive Behavior Scale among Male and Female Youth: Psychometrics and Invariance

Children ◽  
2021 ◽  
Vol 8 (4) ◽  
pp. 283
Author(s):  
Pedro Pechorro ◽  
Rebecca Revilla ◽  
Victor H. Palma ◽  
Cristina Nunes ◽  
Cátia Martins ◽  
...  
Keyword(s):  
Psychometric Properties ◽  
Sensation Seeking ◽  
Critical Period ◽  
Self Report ◽  
Impulsive Behavior ◽  
Youth Delinquency ◽  
Crime Seriousness ◽  
Confirmatory Factor ◽  
School Sample ◽  
Behavior Scale

The UPPS-P Impulsive Behavior Scale is one of the most used and easily administered self-report measures of impulsive traits. The main objective of this study was to examine the psychometric properties of the shorter SUPPS-P scale among a school sample of 470 youth (Mage = 15.89 years, SD = 1.00) from Portugal, subdivided into males (n = 257, Mage = 15.97 years, SD = 0.98) and females (n = 213, Mage = 15.79 years, SD = 1.03). Confirmatory factor analysis results revealed that the latent five-factor structure (i.e., Negative urgency, Lack of perseverance, Lack of premeditation, Sensation seeking, and Positive urgency) obtained adequate fit and strong measurement invariance demonstrated across sex. The SUPPS-P scale also demonstrated satisfactory psychometric properties in terms of internal consistency, discriminant and convergent (e.g., with measures of youth delinquency, aggression) validities, and criterion-related validity (e.g., with crime seriousness). Findings support the use of the SUPPS-P scale in youth. Given the importance of adolescence as a critical period characterized by increases in impulsive behaviors, having a short, valid, reliable, and easily administered assessment of impulsive tendencies is important and clinically impactful.

scholarly journals Development of a Mobile Phone App to Support Self-Monitoring of Emotional Well-Being: A Mental Health Digital Innovation

2016 ◽  
Vol 3 (4) ◽  
pp. e49 ◽  
Author(s):  
Nikki Rickard ◽  
Hussain-Abdulah Arjmand ◽  
David Bakker ◽  
Elizabeth Seabrook
Keyword(s):  
Mental Health ◽  
Mobile Phone ◽  
Well Being ◽  
Mental Health Research ◽  
Primary Component ◽  
Self Report ◽  
Mobile Phone Technology ◽  
Health Apps ◽  
Health Organization ◽  
Health And Well Being

BackgroundEmotional well-being is a primary component of mental health and well-being. Monitoring changes in emotional state daily over extended periods is, however, difficult using traditional methodologies. Providing mental health support is also challenging when approximately only 1 in 2 people with mental health issues seek professional help. Mobile phone technology offers a sustainable means of enhancing self-management of emotional well-being.ObjectiveThis paper aims to describe the development of a mobile phone tool designed to monitor emotional changes in a natural everyday context and in real time.MethodsThis evidence-informed mobile phone app monitors emotional mental health and well-being, and it provides links to mental health organization websites and resources. The app obtains data via self-report psychological questionnaires, experience sampling methodology (ESM), and automated behavioral data collection.ResultsFeedback from 11 individuals (age range 16-52 years; 4 males, 7 females), who tested the app over 30 days, confirmed via survey and focus group methods that the app was functional and usable.ConclusionsRecommendations for future researchers and developers of mental health apps to be used for research are also presented. The methodology described in this paper offers a powerful tool for a range of potential mental health research studies and provides a valuable standard against which development of future mental health apps should be considered.

scholarly journals Evaluation of Changes in Depression, Anxiety, and Social Anxiety Using Smartphone Sensor Features: Longitudinal Cohort Study

10.2196/22844 ◽  
2021 ◽  
Vol 23 (9) ◽  
pp. e22844
Author(s):  
Jonah Meyerhoff ◽  
Tony Liu ◽  
Konrad P Kording ◽  
Lyle H Ungar ◽  
Susan M Kaiser ◽  
...  
Keyword(s):  
Mental Health ◽  
Cohort Study ◽  
Social Anxiety ◽  
Exercise Duration ◽  
Self Report ◽  
Sensor Data ◽  
Longitudinal Cohort Study ◽  
Generalized Anxiety ◽  
Longitudinal Cohort ◽  
Behavioral Features

Background The assessment of behaviors related to mental health typically relies on self-report data. Networked sensors embedded in smartphones can measure some behaviors objectively and continuously, with no ongoing effort. Objective This study aims to evaluate whether changes in phone sensor–derived behavioral features were associated with subsequent changes in mental health symptoms. Methods This longitudinal cohort study examined continuously collected phone sensor data and symptom severity data, collected every 3 weeks, over 16 weeks. The participants were recruited through national research registries. Primary outcomes included depression (8-item Patient Health Questionnaire), generalized anxiety (Generalized Anxiety Disorder 7-item scale), and social anxiety (Social Phobia Inventory) severity. Participants were adults who owned Android smartphones. Participants clustered into 4 groups: multiple comorbidities, depression and generalized anxiety, depression and social anxiety, and minimal symptoms. Results A total of 282 participants were aged 19-69 years (mean 38.9, SD 11.9 years), and the majority were female (223/282, 79.1%) and White participants (226/282, 80.1%). Among the multiple comorbidities group, depression changes were preceded by changes in GPS features (Time: r=−0.23, P=.02; Locations: r=−0.36, P<.001), exercise duration (r=0.39; P=.03) and use of active apps (r=−0.31; P<.001). Among the depression and anxiety groups, changes in depression were preceded by changes in GPS features for Locations (r=−0.20; P=.03) and Transitions (r=−0.21; P=.03). Depression changes were not related to subsequent sensor-derived features. The minimal symptoms group showed no significant relationships. There were no associations between sensor-based features and anxiety and minimal associations between sensor-based features and social anxiety. Conclusions Changes in sensor-derived behavioral features are associated with subsequent depression changes, but not vice versa, suggesting a directional relationship in which changes in sensed behaviors are associated with subsequent changes in symptoms.

Sign in / Sign up

Export Citation Format

Share Document