The Trajectories of Online Mental Health Information Seeking: Modeling Search Behavior Before and After Completion of Self-report Screens.

There is an appreciable mental health treatment gap in the United States. Efforts to bridge this gap and improve resource accessibility have led to the provision of online, clinically-validated tools for mental health self-assessment. In theory, these screens serve as an invaluable component of information-seeking, representing the preparative and action-oriented stages of this process while altering or reinforcing the search content and language of individuals as they engage with information online. Accordingly, this work investigated the association of screen completion with mental health-related search behaviors. Three-year internet search histories from N=7,572 Microsoft Bing users were paired with their respective depression, anxiety, bipolar disorder, or psychosis online screen completion and sociodemographic data available through Mental Health America. Data was transformed into network representations to model queries as discrete steps with probabilities and times-to-transition from one search type to another. Search data subsequent to screen completion was also modeled using Markov chains to simulate likelihood trajectories of different search types through time. Differences in querying dynamics relative to screen completion were observed, with searches involving treatment, diagnosis, suicidal ideation, and suicidal intent commonly emerging as the highest probability behavioral information seeking endpoints. Moreover, results pointed to the association of low risk states of psychopathology with transitions to extreme clinical outcomes (i.e., active suicidal intent). Future research is required to draw definitive conclusions regarding causal relationships between screens and search behavior.

Depression deconstructed: Wearables and passive digital phenotyping for analyzing individual symptoms.

Wearable technology enables unobtrusive collection of longitudinally dense data, allowing for continuous monitoring of physiology and behavior. These digital phenotypes, or device-based indicators, are frequently leveraged to study depression. However, they are usually considered alongside questionnaire sum-scores which collapse the symptomatic gamut into a general representation of severity. To explore the contributions of passive sensing streams more precisely, associations of nine passive sensing-derived features with self-report responses to Center for Epidemiologic Studies Depression (CES-D) items were modeled. Using data from the NetHealth study on N=469 college students, this work generated mixed ordinal logistic regression models to summarize contributions of pulse, movement, and sleep data to depression symptom detection. Emphasizing the importance of the college context, wearable features displayed unique and complementary properties in their heterogeneously significant associations with CES-D items. This work provides conceptual and exploratory blueprints for a reductionist approach to modeling depression within passive sensing research.

Dysregulated Emotion and Trying Substances in Childhood: Insights from a Large Nationally Representative Cohort Study.

OBJECTIVE: Transdiagnostic perspectives on the shared origins of mental illness posit that dysregulated emotion may represent a key driving force behind multiple forms of psychopathology, including substance use disorders. The present study examined whether a link between dysregulated emotion and trying illicit substances could be observed in childhood. METHOD: In a large (N = 7,418) nationally representative sample of children (Mage = 9.9), individual differences in emotion dysregulation were indexed using child and parent reports of frequency of children's emotional outbursts, as well as children's performance on the emotional N-Back task. Two latent variables, derived from either parental/child-report or performance-based indicators, were evaluated as predictors of having ever tried alcohol, tobacco, or marijuana. RESULTS: Results showed that reports of dysregulated emotion were linked to a greater likelihood of trying both alcohol and tobacco products. These findings were also present when controlling for individual differences in executive control and socioeconomic status. CONCLUSIONS: These results suggest that well-established links between dysregulated negative emotion and substance use may emerge as early as in childhood and also suggest that children who experience excessive episodes of uncontrollable negative emotion may be at greater risk for trying substances early in life.

Second-to-Second Affective Responses to Images Correspond With Affective Reactivity, Variability, and Instability in Daily Life.

Two distinct literatures have evolved to study within-person changes in affect over time. One literature has examined affect dynamics with millisecond-level resolution under controlled laboratory conditions, and the second literature has captured affective dynamics across much longer timescales (e.g., hours or days) within the relatively uncontrolled but more ecologically valid conditions of daily life. Despite the importance of linking these literatures, very little research has been done so far. In the laboratory, peak affect intensities and reaction durations were quantified using a paradigm that captures second-to-second changes in subjective affect elicited by provocative images. In two studies, analyses attempted to link these micro-dynamic indexes to fluctuations in daily affect ratings collected via daily protocols up to 4 weeks later. Although peak intensity and reaction duration scores from the laboratory did not consistently relate to daily scores pertaining to affect variability or instability, the total magnitude of changes in affect following images did display relationships of this type. In addition, higher peaks in the laboratory predicted larger intensity reactions to salient daily events. Together, the studies provide insights into the mechanisms through which correspondences and noncorrespondences between laboratory reactivity indices and daily affect dynamic measures can be expected.

Evaluating the Impact of Mask Mandates and Political Party Affiliation on Mental Health Internet Search Behavior in the United States During the COVID-19 Pandemic: Generalized Additive Mixed Model Framework.

BACKGROUND: The impacts of the COVID-19 pandemic on mental health worldwide and in the United States have been well documented. However, there is limited research examining the long-term effects of the pandemic on mental health, particularly in relation to pervasive policies such as statewide mask mandates and political party affiliation. OBJECTIVE: The goal of this study was to examine whether statewide mask mandates and political party affiliations yielded differential changes in mental health symptoms across the United States by leveraging state-specific internet search query data. METHODS: This study leveraged Google search queries from March 24, 2020, to March 29, 2021, in each of the 50 states in the United States. Of the 50 states, 39 implemented statewide mask mandates-with 16 of these states being Republican-to combat the spread of COVID-19. This study investigated whether mask mandates were associated differentially with mental health in states with and without mandates by exploring variations in mental health search queries across the United States. In addition, political party affiliation was examined as a potential covariate to determine whether mask mandates had differential associations with mental health in Republican and Democratic states. Generalized additive mixed models were implemented to model associations among mask mandates, political party affiliation, and mental health search volume for up to 7 months following the implementation of a mask mandate. RESULTS: The results of generalized additive mixed models revealed that search volume for "restless" significantly increased following a mask mandate across all states, whereas the search volume for "irritable" and "anxiety" increased and decreased, respectively, following a mandate for Republican states in comparison with Democratic states. Most mental health search terms did not exhibit significant changes in search volume in relation to mask mandate implementation. CONCLUSIONS: These findings suggest that mask mandates were associated nonlinearly with significant changes in mental health search behavior, with the most notable associations occurring in anxiety-related search terms. Therefore, policy makers should consider monitoring and providing additional support for these mental health symptoms following the implementation of public health-related mandates such as mask mandates. Nevertheless, these results do not provide evidence for an overwhelming impact of mask mandates on population-level mental health in the United States.

A machine learning investigation into the temporal dynamics of physical activity-mediated emotional regulation in adolescents with anorexia nervosa and healthy controls.

OBJECTIVE: Anorexia nervosa (AN) is commonly experienced alongside difficulties of emotion regulation (ER). Previous works identified physical activity (PA) as a mechanism for AN sufferers to achieve desired affective states, with evidence towards mitigation of negative affect. However, temporal associations of PA with specific emotional state outcomes are unknown. METHOD: Using lag-ensemble machine learning and feature importance analyses, 888 affect-based ecological momentary assessments across N = 75 adolescents with AN (N = 44) and healthy controls (N = 31) were analysed to explore significance of past PA, measured through passively collected wrist-worn actigraphy, with subsequent self-report momentary affect change across 9 affect constructs. RESULTS: Among AN adolescents, later lags (≥2.5 h) were important in predicting change across negative emotions (hostility, sadness, fear, guilt). AN-specific model performance on held-out test data revealed the holistic "negative affect" construct as significantly predictable. Only joviality and self-assurance, both positively-valenced constructs, were significantly predictable among healthy-control-specific models. DISCUSSION: Results recapitulated previous findings regarding the importance of PA in negative ER for AN individuals. Moreover, PA was found to play a uniquely prominent role in predicting negative affect 4.5-6 h later among AN adolescents. Future research into the PA-ER dynamic will benefit from targeting specific negative emotions across greater temporal scales.

Applying ensemble machine learning models to predict individual response to a digitally delivered worry postponement intervention.

OBJECTIVE: Generalized anxiety disorder (GAD) is a prevalent mental health disorder that often goes untreated. A core aspect of GAD is worry, which is associated with negative health outcomes, accentuating a need for simple treatments for worry. The present study leveraged pretreatment individual differences to predict personalized treatment response to a digital intervention. METHODS: Linear mixed-effect models were used to model changes in daytime and nighttime worry duration and frequency for 163 participants who completed a six-day worry postponement intervention. Ensemble-based machine learning regression and classification models were implemented to predict changes in worry across the intervention. Model feature importance was derived using SHapley Additive exPlanation (SHAP). RESULTS: Moderate predictive performance was obtained for predicting changes in daytime worry duration (test r2 = 0.221, AUC = 0.77) and nighttime worry frequency (test r2 = 0.164, AUC = 0.72), while poor predictive performance was obtained for nighttime worry duration and daytime worry frequency. Baseline levels of worry and subjective health complaints were most important in driving model predictions. LIMITATIONS: A complete-case analysis was leveraged to analyze the present data, which was collected from participants that were Dutch and majority female. CONCLUSIONS: This study suggests that treatment response to a digital intervention for GAD can be accurately predicted using baseline characteristics. Particularly, this worry postponement intervention may be most beneficial for individuals with high baseline worry but fewer subjective health complaints. The present findings highlight the complexities of and need for further research into daily worry dynamics and the personalizable utility of digital interventions.

Using passive sensor data to probe associations of social structure with changes in personality: A synthesis of network analysis and machine learning.

Social network analysis (SNA) is an increasingly popular and effective tool for modeling psychological phenomena. Through application to the personality literature, social networks, in conjunction with passive, non-invasive sensing technologies, have begun to offer powerful insight into personality state variability. Resultant constructions of social networks can be utilized alongside machine learning-based frameworks to uniquely model personality states. Accordingly, this work leverages data from a previously published study to combine passively collected wearable sensor information on face-to-face, workplace social interactions with ecological momentary assessments of personality state. Data from 54 individuals across six weeks was used to explore the relative importance of 26 unique structural and nodal social network features in predicting individual changes in each of the Big Five (5F) personality states. Changes in personality state were operationalized by calculating the weekly root mean square of successive differences (RMSSD) in 5F state scores measured daily via self-report. Using only SNA-derived features from wearable sensor data, boosted tree-based machine learning models explained, on average, approximately 28-30% of the variance in individual personality state change. Model introspection implicated egocentric features as the most influential predictors across 5F-specific models, with network efficiency, constraint, and effective size measures among the most important. Feature importance profiles for each 5F model partially echoed previous empirical findings. Results support future efforts focusing on egocentric components of SNA and suggest particular investment in exploring efficiency measures to model personality fluctuations within the workplace setting.

Anxiety, depression, and substance experimentation in childhood.

Previous research has demonstrated that adults with comorbid depressive and anxiety disorders are significantly more likely to show pathological use of drugs or alcohol. Few studies, however, have examined associations of this type in children. A better understanding of the relationships between affective disorders and substance experimentation in childhood could help clarify the complex ways in which pathological substance use symptoms develop early in life. The present study included 11,785 children (Mage = 9.9) participating in the Adolescent Brain Cognitive Development (ABCD) study. Depressive and anxiety disorder diagnoses were evaluated as concurrent predictors of experimentation with alcohol and tobacco. A series of linear regressions revealed that children with either depressive or anxiety disorders were significantly more likely to experiment with alcohol or tobacco. However, children with both depressive and anxiety diagnoses were not more likely to experiment than children without a diagnosis. These results suggest that anxiety or depressive diagnoses in childhood may be associated with a greater likelihood of substance experimentation, but severe psychological distress may suppress these effects.

Adolescent Emotion Regulation and Future Psychopathology: A Prospective Transdiagnostic Analysis.

Transdiagnostic frameworks posit a causal link between emotion regulation (ER) ability and psychopathology. However, there is little supporting longitudinal evidence for such frameworks. Among N = 1,262 adolescents, we examined the prospective bidirectional relationship between ER and future pathological anxiety, depression, and substance dependence symptoms in 10 assessment waves over 7 years. In Random-intercept cross-lagged panel models, within-person results do not reveal prospective lag-1 effects of either ER or symptoms. However, between-person analyses showed that dispositional ER ability at baseline predicted greater risk for developing clinically significant depression, anxiety, and substance dependence over the 7-year follow-up period. These findings provide some of the first direct evidence of prospective effects of ER on future symptom risk across affect-related disorders, and should strengthen existing claims that ER ability represents a key transdiagnostic risk factor.

Using the COVID-19 Pandemic to Assess the Influence of News Affect on Online Mental Health-Related Search Behavior Across the United States: Integrated Sentiment Analysis and the Circumplex Model of Affect.

BACKGROUND: The digital era has ushered in an unprecedented volume of readily accessible information, including news coverage of current events. Research has shown that the sentiment of news articles can evoke emotional responses from readers on a daily basis with specific evidence for increased anxiety and depression in response to coverage of the recent COVID-19 pandemic. Given the primacy and relevance of such information exposure, its daily impact on the mental health of the general population within this modality warrants further nuanced investigation. OBJECTIVE: Using the COVID-19 pandemic as a subject-specific example, this work aimed to profile and examine associations between the dynamics of semantic affect in online local news headlines and same-day online mental health term search behavior over time across the United States. METHODS: Using COVID-19-related news headlines from a database of online news stories in conjunction with mental health-related online search data from Google Trends, this paper first explored the statistical and qualitative affective properties of state-specific COVID-19 news coverage across the United States from January 23, 2020, to October 22, 2020. The resultant operationalizations and findings from the joint application of dictionary-based sentiment analysis and the circumplex theory of affect informed the construction of subsequent hypothesis-driven mixed effects models. Daily state-specific counts of mental health search queries were regressed on circumplex-derived features of semantic affect, time, and state (as a random effect) to model the associations between the dynamics of news affect and search behavior throughout the pandemic. Search terms were also grouped into depression symptoms, anxiety symptoms, and nonspecific depression and anxiety symptoms to model the broad impact of news coverage on mental health. RESULTS: Exploratory efforts revealed patterns in day-to-day news headline affect variation across the first 9 months of the pandemic. In addition, circumplex mapping of the most frequently used words in state-specific headlines uncovered time-agnostic similarities and differences across the United States, including the ubiquitous use of negatively valenced and strongly arousing language. Subsequent mixed effects modeling implicated increased consistency in affective tone (SpinVA ß=-.207; P<.001) as predictive of increased depression-related search term activity, with emotional language patterns indicative of affective uncontrollability (FluxA ß=.221; P<.001) contributing generally to an increase in online mental health search term frequency. CONCLUSIONS: This study demonstrated promise in applying the circumplex model of affect to written content and provided a practical example for how circumplex theory can be integrated with sentiment analysis techniques to interrogate mental health-related associations. The findings from pandemic-specific news headlines highlighted arousal, flux, and spin as potentially significant affect-based foci for further study. Future efforts may also benefit from more expansive sentiment analysis approaches to more broadly test the practical application and theoretical capabilities of the circumplex model of affect on text-based data.