Search

Brain circuit functioning and connectivity between specific regions allow us to learn, remember, recognize and think as humans. In this paper, we ask the question if mobile sensing from phones can predict brain functional connectivity. We study the brain resting-state functional connectivity (RSFC) between the ventromedial prefrontal cortex (vmPFC) and the amygdala, which has been shown by neuroscientists to be associated with mental illness such as anxiety and depression. We discuss initial results and insights from the NeuroSence study, an exploratory study of 105 first year college students using neuroimaging and mobile sensing across one semester. We observe correlations between several behavioral features from students' mobile phones and connectivity between vmPFC and amygdala, including conversation duration (r=0.365, p

We hypothesize that behavioral patterns of people are reflected in how they interact with their mobile devices and that continuous sensor data passively collected from their phones and wearables can infer their job performance. Specifically, we study day-today job performance (improvement, no change, decline) of N=298 information workers using mobile sensing data and offer data-driven insights into what data patterns may lead to a high-performing day. Through analyzing workers' mobile sensing data, we predict their performance on a handful of job performance questionnaires with an F-1 score of 75%. In addition, through numerical analysis of the model, we get insights into how individuals must change their behavior so that the model predicts improvements in their job performance. For instance, one worker may benefit if they put their phone down and reduce their screen time, while another worker may benefit from getting more sleep.

Background Across college campuses, the prevalence of clinically relevant depression or anxiety is affecting more than 27% of the college population at some point between entry to college and graduation. Stress and self-esteem have both been hypothesized to contribute to depression and anxiety levels. Although contemporaneous relationships between these variables have been well-defined, the causal relationship between these mental health factors is not well understood, as frequent sampling can be invasive, and many of the current causal techniques are not well suited to investigate correlated variables. Objective This study aims to characterize the causal and contemporaneous networks between these critical mental health factors in a cohort of first-year college students and then determine if observed results replicate in a second, distinct cohort. Methods Ecological momentary assessments of depression, anxiety, stress, and self-esteem were obtained weekly from two cohorts of first-year college students for 40 weeks (1 academic year). We used the Peter and Clark Momentary Conditional Independence algorithm to identify the contemporaneous (t) and causal (t-1) network structures between these mental health metrics. Results All reported results are significant at P Conclusions This paper is an initial attempt to describe the contemporaneous and causal relationships among these four mental health metrics in college students. We replicated previous research identifying concurrent relationships between these variables and extended them by identifying causal links among these metrics. These results provide support for the vulnerability model of depression and anxiety. Understanding how causal factors impact the evolution of these mental states over time may provide key information for targeted treatment or, perhaps more importantly, preventative interventions for individuals at risk for depression and anxiety.

BACKGROUND The vast majority of people worldwide have been impacted by coronavirus disease (COVID-19). In addition to the millions of individuals who have been infected with the disease, billions of individuals have been asked or required by local and national governments to change their behavioral patterns. Previous research on epidemics or traumatic events suggests that this can lead to profound behavioral and mental health changes; however, researchers are rarely able to track these changes with frequent, near-real-time sampling or compare their findings to previous years of data for the same individuals. OBJECTIVE By combining mobile phone sensing and self-reported mental health data among college students who have been participating in a longitudinal study for the past 2 years, we sought to answer two overarching questions. First, have the behaviors and mental health of the participants changed in response to the COVID-19 pandemic compared to previous time periods? Second, are these behavior and mental health changes associated with the relative news coverage of COVID-19 in the US media? METHODS Behaviors such as the number of locations visited, distance traveled, duration of phone usage, number of phone unlocks, sleep duration, and sedentary time were measured using the StudentLife smartphone sensing app. Depression and anxiety were assessed using weekly self-reported ecological momentary assessments of the Patient Health Questionnaire-4. The participants were 217 undergraduate students, with 178 (82.0%) students providing data during the Winter 2020 term. Differences in behaviors and self-reported mental health collected during the Winter 2020 term compared to previous terms in the same cohort were modeled using mixed linear models. RESULTS During the first academic term impacted by COVID-19 (Winter 2020), individuals were more sedentary and reported increased anxiety and depression symptoms (PPP=.03) were significantly associated with COVID-19–related news. CONCLUSIONS Compared with prior academic terms, individuals in the Winter 2020 term were more sedentary, anxious, and depressed. A wide variety of behaviors, including increased phone usage, decreased physical activity, and fewer locations visited, were associated with fluctuations in COVID-19 news reporting. While this large-scale shift in mental health and behavior is unsurprising, its characterization is particularly important to help guide the development of methods to reduce the impact of future catastrophic events on the mental health of the population.

BackgroundWorldwide, the vast majority of people have been impacted by COVID-19. While millions of individuals have become infected, billions of individuals have been asked or required by local and national governments to change their behavioral patterns. Previous research on epidemics or traumatic events suggest this can lead to profound behavioral and mental health changes, but rarely are researchers able to track these changes with frequent, near real-time sampling or compare these to previous years of data on the same individuals.ObjectivesWe seek to answer two overarching questions by combining mobile phone sensing and self-reported mental health data among college students participating in a longitudinal study for the past two years. First, have behaviors and mental health changed in response to the COVID-19 pandemic as compared to previous time periods within the same participants? Second, did behavior and mental health changes track the relative news coverage of COVID-19 in the US media?MethodsBehaviors were measured using the StudentLife mobile smartphone sensing app. Depression and anxiety were assessed using weekly self-reported Ecological Momentary Assessments (EMAs). Differences in behaviors and self-reported mental health collected during the Winter 2020 term (the term in which the coronavirus pandemic started), as compared to prevous terms in the same cohort, were modeled using mixed linear models.ResultsDuring the initial COVID-19 impacted academic term (Winter 2020), individuals were more sedentary and reported increased anxiety and depression symptoms (P

Schizophrenia is a severe psychiatric disorder. We use the CrossCheck study dataset to develop methods to predict whether or not a patient with schizophrenia is going to relapse from mobile phone data. Out of 75 patients in the year long randomized controlled trial only 27 relapse episodes occur. We apply various techniques to address predicting rare events in a longitudinal dataset. We apply resampling methods combining oversampling relapse examples and undersampling non-relapse examples and impute missing data. To avoid overfitting, we apply feature selection and transformation (i.e., PCA) to reduce the feature dimensionality. We find the best relapse prediction result using the first 100 principal components from both passive sensing and self-reports with 30-day prediction windows (precision=26.8%, recall=28.4%). If we demand the recall to be greater than 50%, we find the best result using 25 principle components from both passive sensing and self-reports with 30-day prediction windows (precision=15.4%, recall=51.6%).

BACKGROUND Across college campuses, the prevalence of clinically relevant depression or anxiety is affecting more than 27% of the college population at some point between entry to college and graduation. Stress and self-esteem have both been hypothesized to contribute to depression and anxiety levels. Although contemporaneous relationships between these variables have been well-defined, the causal relationship between these mental health factors is not well understood, as frequent sampling can be invasive, and many of the current causal techniques are not well suited to investigate correlated variables. OBJECTIVE This study aims to characterize the causal and contemporaneous networks between these critical mental health factors in a cohort of first-year college students and then determine if observed results replicate in a second, distinct cohort. METHODS Ecological momentary assessments of depression, anxiety, stress, and self-esteem were obtained weekly from two cohorts of first-year college students for 40 weeks (1 academic year). We used the Peter and Clark Momentary Conditional Independence algorithm to identify the contemporaneous (t) and causal (t-1) network structures between these mental health metrics. RESULTS All reported results are significant at Pt-1 rp, cohort 1 [C1]=–0.082, cohort 2 [C2]=–0.095) and itself (t-1 rp, C1=0.388, C2=0.382) in both cohorts. Anxiety was causally influenced by stress (t-1 rp, C1=0.095, C2=0.104), self-esteem (t-1 rp, C1=–0.067, C2=–0.064, P=.002), and itself (t-1 rp, of C1=0.293, C2=0.339) in both cohorts. A causal link between anxiety and depression was observed in the first cohort (t-1 rp, C1=0.109) and only observed in the second cohort with a more liberal threshold (t-1 rp, C2=0.044, P=.03). Self-esteem was only causally influenced by itself (t-1 rp, C1=0.389, C2=0.393). Stress was only causally influenced by itself (t-1 rp, C1=0.248, C2=0.273). Anxiety had positive contemporaneous links to depression (t rp, C1=0.462, C2=0.444) and stress (t rp, C1=0.354, C2=0.358). Self-esteem had negative contemporaneous links to each of the other three mental health metrics, with the strongest negative relationship being stress (t rp, C1=–0.334, C2=–0.340), followed by depression (t rp, C1=–0.302, C2=–0.274) and anxiety (t rp, C1=–0.256, C2=–0.208). Depression had positive contemporaneous links to anxiety (previously mentioned) and stress (t rp, C1=0.250, C2=0.231). CONCLUSIONS This paper is an initial attempt to describe the contemporaneous and causal relationships among these four mental health metrics in college students. We replicated previous research identifying concurrent relationships between these variables and extended them by identifying causal links among these metrics. These results provide support for the vulnerability model of depression and anxiety. Understanding how causal factors impact the evolution of these mental states over time may provide key information for targeted treatment or, perhaps more importantly, preventative interventions for individuals at risk for depression and anxiety.

Background The vast majority of people worldwide have been impacted by coronavirus disease (COVID-19). In addition to the millions of individuals who have been infected with the disease, billions of individuals have been asked or required by local and national governments to change their behavioral patterns. Previous research on epidemics or traumatic events suggests that this can lead to profound behavioral and mental health changes; however, researchers are rarely able to track these changes with frequent, near-real-time sampling or compare their findings to previous years of data for the same individuals. Objective By combining mobile phone sensing and self-reported mental health data among college students who have been participating in a longitudinal study for the past 2 years, we sought to answer two overarching questions. First, have the behaviors and mental health of the participants changed in response to the COVID-19 pandemic compared to previous time periods? Second, are these behavior and mental health changes associated with the relative news coverage of COVID-19 in the US media? Methods Behaviors such as the number of locations visited, distance traveled, duration of phone usage, number of phone unlocks, sleep duration, and sedentary time were measured using the StudentLife smartphone sensing app. Depression and anxiety were assessed using weekly self-reported ecological momentary assessments of the Patient Health Questionnaire-4. The participants were 217 undergraduate students, with 178 (82.0%) students providing data during the Winter 2020 term. Differences in behaviors and self-reported mental health collected during the Winter 2020 term compared to previous terms in the same cohort were modeled using mixed linear models. Results During the first academic term impacted by COVID-19 (Winter 2020), individuals were more sedentary and reported increased anxiety and depression symptoms (P Conclusions Compared with prior academic terms, individuals in the Winter 2020 term were more sedentary, anxious, and depressed. A wide variety of behaviors, including increased phone usage, decreased physical activity, and fewer locations visited, were associated with fluctuations in COVID-19 news reporting. While this large-scale shift in mental health and behavior is unsurprising, its characterization is particularly important to help guide the development of methods to reduce the impact of future catastrophic events on the mental health of the population.

Investigating users' interruptibility as an indicator of his/her attention status has been essential in recent pervasive computing where the users' attention resources get scarce against ever increasing amounts of information. In this paper, we address research problems related to the users' available interruptibility, their physical activities, and their current locations and situations. We propose the “Interruptibility Map”, a geographical tool for analyzing and visualizing the user's local interruptibility status in the context of smart city research. Our map describes where citizens are expected to feel more or less interruptive against notifications produced by computing devices, which are known to have negative effects on work productivity, emotion, and psychological state. We conducted a continuous analysis from our previous research and a new additional in-the-wild user study for 2 weeks with 29 participants to investigate the relationship between one's interruptibility and their locations and situations. As a highlight of our findings, we found certain pairs of user activity change and a location that showed better interruptibility to users, such as an activity change of “when user's riding car(bus) stops” in the bus commute situation.