Differential temporal utility of passively sensed smartphone features for depression and anxiety symptom prediction: a longitudinal cohort study.

While studies show links between smartphone data and affective symptoms, we lack clarity on the temporal scale, specificity (e.g., to depression vs. anxiety), and person-specific (vs. group-level) nature of these associations. We conducted a large-scale (n = 1013) smartphone-based passive sensing study to identify within- and between-person digital markers of depression and anxiety symptoms over time. Participants (74.6% female; M age = 40.9) downloaded the LifeSense app, which facilitated continuous passive data collection (e.g., GPS, app and device use, communication) across 16 weeks. Hierarchical linear regression models tested the within- and between-person associations of 2-week windows of passively sensed data with depression (PHQ-8) or generalized anxiety (GAD-7). We used a shifting window to understand the time scale at which sensed features relate to mental health symptoms, predicting symptoms 2 weeks in the future (distal prediction), 1 week in the future (medial prediction), and 0 weeks in the future (proximal prediction). Spending more time at home relative to one's average was an early signal of PHQ-8 severity (distal ß = 0.219, p = 0.012) and continued to relate to PHQ-8 at medial (ß = 0.198, p = 0.022) and proximal (ß = 0.183, p = 0.045) windows. In contrast, circadian movement was proximally related to (ß = -0.131, p = 0.035) but did not predict (distal ß = 0.034, p = 0.577; medial ß = -0.089, p = 0.138) PHQ-8. Distinct communication features (i.e., call/text or app-based messaging) related to PHQ-8 and GAD-7. Findings have implications for identifying novel treatment targets, personalizing digital mental health interventions, and enhancing traditional patient-provider interactions. Certain features (e.g., circadian movement) may represent correlates but not true prospective indicators of affective symptoms. Conversely, other features like home duration may be such early signals of intra-individual symptom change, indicating the potential utility of prophylactic intervention (e.g., behavioral activation) in response to person-specific increases in these signals.

Small Steps over time: A longitudinal usability test of an automated interactive text messaging intervention to support self-management of depression and anxiety symptoms.

BACKGROUND: Digital mental health interventions (DMHIs) offer potential solutions for addressing mental health care gaps, but often suffer from low engagement. Text messaging is one promising medium for increasing access and sustaining user engagement with DMHIs. This paper examines the Small Steps SMS program, an 8-week, automated, adaptive text message-based intervention for depression and anxiety. METHODS: We conducted an 8-week longitudinal usability test of the Small Steps SMS program, recruiting 20 participants who met criteria for major depressive disorder and/or generalized anxiety disorder. Participants used the automated intervention for 8 weeks and completed symptom severity and usability self-report surveys after 4 and 8 weeks of intervention use. Participants also completed individual interviews to provide feedback on the intervention. RESULTS: Participants responded to automated messages on 70 % of study days and with 85 % of participants sending responses to messages in the 8th week of use. Usability surpassed established cutoffs for software that is considered acceptable. Depression symptom severity decreased significantly over the usability test, but reductions in anxiety symptoms were not significant. Participants noted key areas for improvement including addressing message volume, aligning message scheduling to individuals' availability, and increasing the customizability of content. LIMITATIONS: This study does not contain a control group. CONCLUSIONS: An 8-week automated interactive text messaging intervention, Small Steps SMS, demonstrates promise with regard to being a feasible, usable, and engaging method to deliver daily mental health support to individuals with symptoms of anxiety and depression.

Specific associations of passively sensed smartphone data with future symptoms of avoidance, fear, and physiological distress in social anxiety.

Background: Prior literature links passively sensed information about a person's location, movement, and communication with social anxiety. These findings hold promise for identifying novel treatment targets, informing clinical care, and personalizing digital mental health interventions. However, social anxiety symptoms are heterogeneous; to identify more precise targets and tailor treatments, there is a need for personal sensing studies aimed at understanding differential predictors of the distinct subdomains of social anxiety. Our objective was to conduct a large-scale smartphone-based sensing study of fear, avoidance, and physiological symptoms in the context of trait social anxiety over time. Methods: Participants (n = 1013; 74.6 % female; M age = 40.9) downloaded the LifeSense app, which collected continuous passive data (e.g., GPS, communication, app and device use) over 16 weeks. We tested a series of multilevel linear regression models to understand within- and between-person associations of 2-week windows of passively sensed smartphone data with fear, avoidance, and physiological distress on the self-reported Social Phobia Inventory (SPIN). A shifting sensor lag was applied to examine how smartphone features related to SPIN subdomains 2 weeks in the future (distal prediction), 1 week in the future (medial prediction), and 0 weeks in the future (proximal prediction). Results: A decrease in time visiting novel places was a strong between-person predictor of social avoidance over time (distal ß = -0.886, p = .002; medial ß = -0.647, p = .029; proximal ß = -0.818, p = .007). Reductions in call- and text-based communications were associated with social avoidance at both the between- (distal ß = -0.882, p = .002; medial ß = -0.932, p = .001; proximal ß = -0.918, p = .001) and within- (distal ß = -0.191, p = .046; medial ß = -0.213, p = .028) person levels, as well as between-person fear of social situations (distal ß = -0.860, p < .001; medial ß = -0.892, p < .001; proximal ß = -0.886, p < .001) over time. There were fewer significant associations of sensed data with physiological distress. Across the three subscales, smartphone data explained 9-12 % of the variance in social anxiety. Conclusion: Findings have implications for understanding how social anxiety manifests in daily life, and for personalizing treatments. For example, a signal that someone is likely to begin avoiding social situations may suggest a need for alternative types of exposure-based interventions compared to a signal that someone is likely to begin experiencing increased physiological distress. Our results suggest that as a prophylactic means of targeting social avoidance, it may be helpful to deploy interventions involving social exposures in response to decreases in time spent visiting novel places.

Analyzing text message linguistic features: Do people with depression communicate differently with their close and non-close contacts?

BACKGROUND: Relatively little is known about how communication changes as a function of depression severity and interpersonal closeness. We examined the linguistic features of outgoing text messages among individuals with depression and their close- and non-close contacts. METHODS: 419 participants were included in this 16-week-long observational study. Participants regularly completed the PHQ-8 and rated subjective closeness to their contacts. Text messages were processed to count frequencies of word usage in the LIWC 2015 libraries. A linear mixed modeling approach was used to estimate linguistic feature scores of outgoing text messages. RESULTS: Regardless of closeness, people with higher PHQ-8 scores tended to use more differentiation words. When texting with close contacts, individuals with higher PHQ-8 scores used more first-person singular, filler, sexual, anger, and negative emotion words. When texting with non-close contacts these participants used more conjunctions, tentative, and sadness-related words and fewer first-person plural words. CONCLUSION: Word classes used in text messages, when combined with symptom severity and subjective social closeness data, may be indicative of underlying interpersonal processes. These data may hold promise as potential treatment targets to address interpersonal drivers of depression.

System design of a text messaging program to support the mental health needs of non-treatment seeking young adults.

Young adults (ages 18-25) experience the highest levels of mental health problems of any adult age group, but have the lowest mental health treatment rates. Text messages are the most used feature on the mobile phone and provide an opportunity to reach non-treatment engaged users throughout the day in a conversational manner. We present the design of an automated text message-based intervention for symptom self-management. The intervention comprises: (1) psychological strategies (i.e., types of evidence-based techniques leveraged to achieve symptom reduction) and (2) interaction types or the form that intervention content takes as it is delivered to and elicited from users.

The relationship between text message sentiment and self-reported depression.

BACKGROUND: Personal sensing has shown promise for detecting behavioral correlates of depression, but there is little work examining personal sensing of cognitive and affective states. Digital language, particularly through personal text messages, is one source that can measure these markers. METHODS: We correlated privacy-preserving sentiment analysis of text messages with self-reported depression symptom severity. We enrolled 219 U.S. adults in a 16 week longitudinal observational study. Participants installed a personal sensing app on their phones, which administered self-report PHQ-8 assessments of their depression severity, collected phone sensor data, and computed anonymized language sentiment scores from their text messages. We also trained machine learning models for predicting end-of-study self-reported depression status using on blocks of phone sensor and text features. RESULTS: In correlation analyses, we find that degrees of depression, emotional, and personal pronoun language categories correlate most strongly with self-reported depression, validating prior literature. Our classification models which predict binary depression status achieve a leave-one-out AUC of 0.72 when only considering text features and 0.76 when combining text with other networked smartphone sensors. LIMITATIONS: Participants were recruited from a panel that over-represented women, caucasians, and individuals with self-reported depression at baseline. As language use differs across demographic factors, generalizability beyond this population may be limited. The study period also coincided with the initial COVID-19 outbreak in the United States, which may have affected smartphone sensor data quality. CONCLUSIONS: Effective depression prediction through text message sentiment, especially when combined with other personal sensors, could enable comprehensive mental health monitoring and intervention.

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

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.

Evaluation of a recommender app for apps for the treatment of depression and anxiety: an analysis of longitudinal user engagement.

Objective: While depression and anxiety are common mental health issues, only a small segment of the population has access to standard one-on-one treatment. The use of smartphone apps can fill this gap. An app recommender system may help improve user engagement of these apps and eventually symptoms. Methods: IntelliCare was a suite of apps for depression and anxiety, with a Hub app that provided app recommendations aiming to increase user engagement. This study captured the records of 8057 users of 12 apps. We measured overall engagement and app-specific usage longitudinally by the number of weekly app sessions ("loyalty") and the number of days with app usage ("regularity") over 16 weeks. Hub and non-Hub users were compared using zero-inflated Poisson regression for loyalty, linear regression for regularity, and Cox regression for engagement duration. Adjusted analyses were performed in 4561 users for whom we had baseline characteristics. Impact of Hub recommendations was assessed using the same approach. Results: When compared to non-Hub users in adjusted analyses, Hub users had a lower risk of discontinuing IntelliCare (hazard ratio = 0.67, 95% CI, 0.62-0.71), higher loyalty (2- to 5-fold), and higher regularity (0.1-0.4 day/week greater). Among Hub users, Hub recommendations increased app-specific loyalty and regularity in all 12 apps. Discussion/Conclusion: Centralized app recommendations increase overall user engagement of the apps, as well as app-specific usage. Further studies relating app usage to symptoms can validate that such a recommender improves clinical benefits and does so at scale.

IntelliCare: An Eclectic, Skills-Based App Suite for the Treatment of Depression and Anxiety.

BACKGROUND: Digital mental health tools have tended to use psychoeducational strategies based on treatment orientations developed and validated outside of digital health. These features do not map well to the brief but frequent ways that people use mobile phones and mobile phone apps today. To address these challenges, we developed a suite of apps for depression and anxiety called IntelliCare, each developed with a focused goal and interactional style. IntelliCare apps prioritize interactive skills training over education and are designed for frequent but short interactions. OBJECTIVE: The overall objective of this study was to pilot a coach-assisted version of IntelliCare and evaluate its use and efficacy at reducing symptoms of depression and anxiety. METHODS: Participants, recruited through a health care system, Web-based and community advertising, and clinical research registries, were included in this single-arm trial if they had elevated symptoms of depression or anxiety. Participants had access to the 14 IntelliCare apps from Google Play and received 8 weeks of coaching on the use of IntelliCare. Coaching included an initial phone call plus 2 or more texts per week over the 8 weeks, with some participants receiving an additional brief phone call. Primary outcomes included the Patient Health Questionnaire-9 (PHQ-9) for depression and the Generalized Anxiety Disorder-7 (GAD-7) for anxiety. Participants were compensated up to US $90 for completing all assessments; compensation was not for app use or treatment engagement. RESULTS: Of the 99 participants who initiated treatment, 90.1% (90/99) completed 8 weeks. Participants showed substantial reductions in the PHQ-9 and GAD-7 (P<.001). Participants used the apps an average of 195.4 (SD 141) times over the 8 weeks. The average length of use was 1.1 (SD 2.1) minutes, and 95% of participants downloaded 5 or more of the IntelliCare apps. CONCLUSIONS: This study supports the IntelliCare framework of providing a suite of skills-focused apps that can be used frequently and briefly to reduce symptoms of depression and anxiety. The IntelliCare system is elemental, allowing individual apps to be used or not used based on their effectiveness and utility, and it is eclectic, viewing treatment strategies as elements that can be applied as needed rather than adhering to a singular, overarching, theoretical model. TRIAL REGISTRATION: Clinicaltrials.gov NCT02176226; http://clinicaltrials.gov/ct2/show/NCT02176226 (Archived by WebCite at http://www.webcitation/6mQZuBGk1).

Uptake and Usage of IntelliCare: A Publicly Available Suite of Mental Health and Well-Being Apps.

BACKGROUND: Treatments for depression and anxiety have several behavioral and psychological targets and rely on varied strategies. Digital mental health treatments often employ feature-rich approaches addressing several targets and strategies. These treatments, often optimized for desktop computer use, are at odds with the ways people use smartphone applications. Smartphone use tends to focus on singular functions with easy navigation to desired tools. The IntelliCare suite of apps was developed to address the discrepancy between need for diverse behavioral strategies and constraints imposed by typical app use. Each app focuses on one strategy for a limited subset of clinical aims all pertinent to depression and anxiety. This study presents the uptake and usage of apps from the IntelliCare suite following an open deployment on a large app marketplace. METHODS: Thirteen lightweight apps, including 12 interactive apps and one Hub app that coordinates use across those interactive apps, were developed and made free to download on the Google Play store. De-identified app usage data from the first year of IntelliCare suite deployment were analyzed for this study. RESULTS: In the first year of public availability, 5,210 individuals downloaded one or more of the IntelliCare apps, for a total of 10,131 downloads. Nearly a third of these individuals (31.8%) downloaded more than one of these apps. The modal number of launches for each of the apps was 1, however the mean number of app launches per app ranged from 3.10 to 16.98, reflecting considerable variability in the use of each app. CONCLUSIONS: The use rate of the IntelliCare suite of apps is higher than public deployments of other comparable digital resources. Our findings suggest that people will use multiple apps and provides support for the concept of app suites as a useful strategy for providing diverse behavioral strategies.

A single vs. multi-sensor approach to enhanced detection of smartphone placement.

In this paper, the authors evaluate the ability to detect on-body device placement of smartphones. A feasibility study is undertaken with N=5 participants to identify nine key locations, including in the hand, thigh and backpack, using a multitude of commonly available smartphone sensors. Sensors examined include the accelerometer, magnetometer, gyroscope, pressure and light sensors. Each sensor is examined independently, to identify the potential contributions it can offer, before a fused approach, using all sensors is adopted. A total of 139 features are generated from these sensors, and used to train five machine learning algorithms, i.e. C4.5, CART, Naïve Bayes, Multilayer Perceptrons, and Support Vector Machines. Ten-fold cross validation is used to validate these models, achieving classification results as high as 99%.

Harnessing context sensing to develop a mobile intervention for depression.

BACKGROUND: Mobile phone sensors can be used to develop context-aware systems that automatically detect when patients require assistance. Mobile phones can also provide ecological momentary interventions that deliver tailored assistance during problematic situations. However, such approaches have not yet been used to treat major depressive disorder. OBJECTIVE: The purpose of this study was to investigate the technical feasibility, functional reliability, and patient satisfaction with Mobilyze!, a mobile phone- and Internet-based intervention including ecological momentary intervention and context sensing. METHODS: We developed a mobile phone application and supporting architecture, in which machine learning models (ie, learners) predicted patients' mood, emotions, cognitive/motivational states, activities, environmental context, and social context based on at least 38 concurrent phone sensor values (eg, global positioning system, ambient light, recent calls). The website included feedback graphs illustrating correlations between patients' self-reported states, as well as didactics and tools teaching patients behavioral activation concepts. Brief telephone calls and emails with a clinician were used to promote adherence. We enrolled 8 adults with major depressive disorder in a single-arm pilot study to receive Mobilyze! and complete clinical assessments for 8 weeks. RESULTS: Promising accuracy rates (60% to 91%) were achieved by learners predicting categorical contextual states (eg, location). For states rated on scales (eg, mood), predictive capability was poor. Participants were satisfied with the phone application and improved significantly on self-reported depressive symptoms (beta(week) = -.82, P < .001, per-protocol Cohen d = 3.43) and interview measures of depressive symptoms (beta(week) = -.81, P < .001, per-protocol Cohen d = 3.55). Participants also became less likely to meet criteria for major depressive disorder diagnosis (b(week) = -.65, P = .03, per-protocol remission rate = 85.71%). Comorbid anxiety symptoms also decreased (beta(week) = -.71, P < .001, per-protocol Cohen d = 2.58). CONCLUSIONS: Mobilyze! is a scalable, feasible intervention with preliminary evidence of efficacy. To our knowledge, it is the first ecological momentary intervention for unipolar depression, as well as one of the first attempts to use context sensing to identify mental health-related states. Several lessons learned regarding technical functionality, data mining, and software development process are discussed. TRIAL REGISTRATION: Clinicaltrials.gov NCT01107041; http://clinicaltrials.gov/ct2/show/NCT01107041 (Archived by WebCite at http://www.webcitation.org/60CVjPH0n).