Predicting Depression in Adolescents Using Mobile and Wearable Sensors: Multimodal Machine Learning-Based Exploratory Study

Enhancing prediction of major depressive disorder onset in adolescents: A machine learning approach

Major Depressive Disorder (MDD) is a prevalent mental health condition that often begins in adolescence, with significant long-term implications. Indicated prevention programs targeting adolescents with mild symptoms have shown efficacy, yet the methods for identifying at-risk individuals need improvement. This study aims to evaluate the utility of Partial Least Squares Regression (PLSR) in predicting the onset of MDD among non-depressed adolescents, compared to traditional screening methods. The study recruited 1462 Portuguese adolescents aged 13-16, who were assessed using various self-report measures and followed for two years. Participants were randomly divided into training (70%, N = 1023) and testing (30%, N = 439) samples. PLSR models were developed to predict the occurrence of a major depressive episode (MDE) within two years, using 331 variables. The model's performance was compared to the Children's Depression Inventory (CDI) in predicting MDE onset. The best-fitting PLSR model with two components explained 19.1% and 16.9% of the variance in the training and testing samples, respectively, significantly outperforming the CDI, which explained 7.7% of the variance. The area under the ROC curve was 0.78 for PLSR, compared to 0.71 for CDI. An empirically derived cut-off point was used to create dichotomous risk categories, and it showed a significant difference in MDE rates between predicted high-risk and low-risk groups. The balanced accuracy of the PLSR model was 0.77, compared to 0.65 for the CDI method. The PLSR model effectively identified adolescents at risk for developing MDD, demonstrating superior predictive power over the CDI. This study supports the potential utility of ML techniques (e.g., PLSR) in enhancing early identification and prevention efforts for adolescent depression.

Predicting and Monitoring Symptoms in Patients Diagnosed With Depression Using Smartphone Data: Observational Study

BACKGROUND

Clinical diagnostic assessments and the outcome monitoring of patients with depression rely predominantly on interviews by professionals and the use of self-report questionnaires. The ubiquity of smartphones and other personal consumer devices has prompted research into the potential of data collected via these devices to serve as digital behavioral markers for indicating the presence and monitoring of the outcome of depression.

OBJECTIVE

This paper explores the potential of using behavioral data collected with smartphones to detect and monitor depression symptoms in patients diagnosed with depression. Specifically, it investigates whether this data can accurately classify the presence of depression, as well as monitor the changes in depressive states over time.

METHODS

In a prospective cohort study, we collected smartphone behavioral data for up to 1 year. The study consists of observations from 164 participants, including healthy controls (n=31) and patients diagnosed with various depressive disorders: major depressive disorder (MDD; n=85), MDD with comorbid borderline personality disorder (n=27), and major depressive episodes with bipolar disorder (n=21). Data were labeled based on depression severity using 9-item Patient Health Questionnaire (PHQ-9) scores. We performed statistical analysis and used supervised machine learning on the data to classify the severity of depression and observe changes in the depression state over time.

RESULTS

Our correlation analysis revealed 32 behavioral markers associated with the changes in depressive state. Our analysis classified patients who are depressed with an accuracy of 82% (95% CI 80%-84%) and change in the presence of depression with an accuracy of 75% (95% CI 72%-76%). Notably, the most important smartphone features for classifying depression states were screen-off events, battery charge levels, communication patterns, app usage, and location data. Similarly, for predicting changes in depression state, the most important features were related to location, battery level, screen, and accelerometer data patterns.

CONCLUSIONS

The use of smartphone digital behavioral markers to supplement clinical evaluations may aid in detecting the presence and changes in severity of symptoms of depression, particularly if combined with intermittent use of self-report of symptoms.

Psychotherapy 2.0 - Application context and effectiveness of sensor technology in psychotherapy with children and adolescents: A systematic review

Background

E-mental health applications have been increasingly used in the psychotherapeutic care of patients for several years. State-of-the-art sensor technology could be used to determine digital biomarkers for the diagnosis of mental disorders. Furthermore, by integrating sensors into treatment, relevant contextual information (e.g. field of gaze, stress levels) could be made transparent and improve the treatment of people with mental disorders. An overview of studies on this approach would be useful to provide information about the current status quo.

Methods

A systematic review of the use of sensor technology in psychotherapy for children and adolescents was conducted with the aim of investigating the use and effectiveness of sensory technology in psychotherapy treatment. Five databases were searched for studies ranging from 2000 to 2023. The study was registered by PROSPERO (CRD42023374219), conducted according to Cochrane recommendations and used the PRISMA reporting guideline.

Results

Of the 38.560 hits in the search, only 10 publications met the inclusion criteria, including 3 RCTs and 7 pilot studies with a total of 257 subjects. The study population consisted of children and adolescents aged 6 to 19 years with mental disorders such as OCD, anxiety disorders, PTSD, anorexia nervosa and autistic behavior. The psychotherapy methods investigated were mostly cognitive behavioral therapy (face-to-face contact) with the treatment method of exposure for various disorders. In most cases, ECG, EDA, eye-tracking and movement sensors were used to measure vital parameters. The heterogeneous studies illustrate a variety of potential useful applications of sensor technology in psychotherapy for adolescents. In some studies, the sensors are implemented in a feasible approach to treatment.

Conclusion

Sensors might enrich psychotherapy in different application contexts.However, so far there is still a lack of further randomized controlled clinical studies that provide reliable findings on the effectiveness of sensory therapy in psychotherapy for children and adolescents. This could stimulate the embedding of such technologies into psychotherapeutic process.https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42023374219, identifier [CRD42023374219].

Accurately predicting mood episodes in mood disorder patients using wearable sleep and circadian rhythm features

Wearable devices enable passive collection of sleep, heart rate, and step-count data, offering potential for mood episode prediction in mood disorder patients. However, current models often require various data types, limiting real-world application. Here, we develop models that predict future episodes using only sleep-wake data, easily gathered through smartphones and wearables when trained on an individual's sleep-wake history and past mood episodes. Using mathematical modeling to longitudinal data from 168 patients (587 days average clinical follow-up, 267 days wearable data), we derived 36 sleep and circadian rhythm features. These features enabled accurate next-day predictions for depressive, manic, and hypomanic episodes (AUCs: 0.80, 0.98, 0.95). Notably, daily circadian phase shifts were the most significant predictors: delays linked to depressive episodes, advances to manic episodes. This prospective observational cohort study (ClinicalTrials.gov: NCT03088657, 2017-3-23) shows sleep-wake data, combined with prior mood episode history, can effectively predict mood episodes, enhancing mood disorder management.

Digital phenotyping in bipolar disorder: Using longitudinal Fitbit data and personalized machine learning to predict mood symptomatology

BACKGROUND

Effective treatment of bipolar disorder (BD) requires prompt response to mood episodes. Preliminary studies suggest that predictions based on passive sensor data from personal digital devices can accurately detect mood episodes (e.g., between routine care appointments), but studies to date do not use methods designed for broad application. This study evaluated whether a novel, personalized machine learning approach, trained entirely on passive Fitbit data, with limited data filtering could accurately detect mood symptomatology in BD patients.

METHODS

We analyzed data from 54 adults with BD, who wore Fitbits and completed bi-weekly self-report measures for 9 months. We applied machine learning (ML) models to Fitbit data aggregated over two-week observation windows to detect occurrences of depressive and (hypo)manic symptomatology, which were defined as two-week windows with scores above established clinical cutoffs for the Patient Health Questionnaire-8 (PHQ-8) and Altman Self-Rating Mania Scale (ASRM) respectively.

RESULTS

As hypothesized, among several ML algorithms, Binary Mixed Model (BiMM) forest achieved the highest area under the receiver operating curve (ROC-AUC) in the validation process. In the testing set, the ROC-AUC was 86.0% for depression and 85.2% for (hypo)mania. Using optimized thresholds calculated with Youden's J statistic, predictive accuracy was 80.1% for depression (sensitivity of 71.2% and specificity of 85.6%) and 89.1% for (hypo)mania (sensitivity of 80.0% and specificity of 90.1%).

CONCLUSION

We achieved sound performance in detecting mood symptomatology in BD patients using methods designed for broad application. Findings expand upon evidence that Fitbit data can produce accurate mood symptomatology predictions. Additionally, to the best of our knowledge, this represents the first application of BiMM forest for mood symptomatology prediction. Overall, results move the field a step toward personalized algorithms suitable for the full population of patients, rather than only those with high compliance, access to specialized devices, or willingness to share invasive data.

Prediction of adolescent depression from prenatal and childhood data from ALSPAC using machine learning

Depression is a major cause of disability and mortality for young people worldwide and is typically first diagnosed during adolescence. In this work, we present a machine learning framework to predict adolescent depression occurring between ages 12 and 18 years using environmental, biological, and lifestyle features of the child, mother, and partner from the child's prenatal period to age 10 years using data from 8467 participants enrolled in the Avon Longitudinal Study of Parents and Children (ALSPAC). We trained and compared several cross-sectional and longitudinal machine learning techniques and found the resulting models predicted adolescent depression with recall (0.59 ± 0.20), specificity (0.61 ± 0.17), and accuracy (0.64 ± 0.13), using on average 39 out of the 885 total features (4.4%) included in the models. The leading informative features in our predictive models of adolescent depression were female sex, parental depression and anxiety, and exposure to stressful events or environments. This work demonstrates how using a broad array of evidence-driven predictors from early in life can inform the development of preventative decision support tools to assist in the early detection of risk for mental illness.

Passive sensing data predicts stress in university students: a supervised machine learning method for digital phenotyping

Introduction

University students are particularly susceptible to developing high levels of stress, which occur when environmental demands outweigh an individual's ability to cope. The growing advent of mental health smartphone apps has led to a surge in use by university students seeking ways to help them cope with stress. Use of these apps has afforded researchers the unique ability to collect extensive amounts of passive sensing data including GPS and step detection. Despite this, little is known about the relationship between passive sensing data and stress. Further, there are no established methodologies or tools to predict stress from passive sensing data in this group.

Methods

In this study, we establish a clear machine learning-based methodological pipeline for processing passive sensing data and extracting features that may be relevant in the context of mental health.

Results

We then use this methodology to determine the relationship between passive sensing data and stress in university students.

Discussion

In doing so, we offer the first proof-of-principle data for the utility of our methodological pipeline and highlight that passive sensing data can indeed digitally phenotype stress in university students.

Clinical trial registration

Australia New Zealand Clinical Trials Registry (ANZCTR), identifier ACTRN12621001223820.

Identifying Person-Specific Drivers of Depression in Adolescents: Protocol for a Smartphone-Based Ecological Momentary Assessment and Passive Sensing Study

BACKGROUND

Adolescence is marked by an increasing risk of depression and is an optimal window for prevention and early intervention. Personalizing interventions may be one way to maximize therapeutic benefit, especially given the marked heterogeneity in depressive presentations. However, empirical evidence that can guide personalized intervention for youth is lacking. Identifying person-specific symptom drivers during adolescence could improve outcomes by accounting for both developmental and individual differences.

OBJECTIVE

This study leverages adolescents' everyday smartphone use to investigate person-specific drivers of depression and validate smartphone-based mobile sensing data against established ambulatory methods. We describe the methods of this study and provide an update on its status. After data collection is completed, we will address three specific aims: (1) identify idiographic drivers of dynamic variability in depressive symptoms, (2) test the validity of mobile sensing against ecological momentary assessment (EMA) and actigraphy for identifying these drivers, and (3) explore adolescent baseline characteristics as predictors of these drivers.

METHODS

A total of 50 adolescents with elevated symptoms of depression will participate in 28 days of (1) smartphone-based EMA assessing depressive symptoms, processes, affect, and sleep; (2) mobile sensing of mobility, physical activity, sleep, natural language use in typed interpersonal communication, screen-on time, and call frequency and duration using the Effortless Assessment of Risk States smartphone app; and (3) wrist actigraphy of physical activity and sleep. Adolescents and caregivers will complete developmental and clinical measures at baseline, as well as user feedback interviews at follow-up. Idiographic, within-subject networks of EMA symptoms will be modeled to identify each adolescent's person-specific drivers of depression. Correlations among EMA, mobile sensor, and actigraph measures of sleep, physical, and social activity will be used to assess the validity of mobile sensing for identifying person-specific drivers. Data-driven analyses of mobile sensor variables predicting core depressive symptoms (self-reported mood and anhedonia) will also be used to assess the validity of mobile sensing for identifying drivers. Finally, between-subject baseline characteristics will be explored as predictors of person-specific drivers.

RESULTS

As of October 2023, 84 families were screened as eligible, of whom 70% (n=59) provided informed consent and 46% (n=39) met all inclusion criteria after completing baseline assessment. Of the 39 included families, 85% (n=33) completed the 28-day smartphone and actigraph data collection period and follow-up study visit.

CONCLUSIONS

This study leverages depressed adolescents' everyday smartphone use to identify person-specific drivers of adolescent depression and to assess the validity of mobile sensing for identifying these drivers. The findings are expected to offer novel insights into the structure and dynamics of depressive symptomatology during a sensitive period of development and to inform future development of a scalable, low-burden smartphone-based tool that can guide personalized treatment decisions for depressed adolescents.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/43931.

Why do adolescents attempt suicide? Insights from leading ideation-to-action suicide theories: a systematic review

Suicide is a leading cause of death among adolescents, and recent suicide theories have sought to clarify the factors that facilitate the transition from suicide ideation to action. Specifically, the Interpersonal Theory of Suicide (IPTS), Integrated Motivational-Volitional Model (IMV), and Three Step Theory (3ST) have highlighted risk factors central to the formation of suicidal ideation and suicidal behaviors, which is necessary for suicide death. However, these models were initially developed and tested among adults, and given core socioemotional and neurodevelopmental differences in adolescents, the applicability of these models remains unclear. Directly addressing this gap in knowledge, this systematic review aimed to (1) describe the evidence of leading ideation-to-action theories (i.e., IPTS, IMV, 3ST) as they relate to suicide risk among adolescents, (2) integrate ideation-to-action theories within prevailing biological frameworks of adolescent suicide, and (3) provide recommendations for future adolescent suicide research. Overall, few studies provided a complete test of models in adolescent samples, and empirical research testing components of these theories provided mixed support. Future research would benefit from integrating neurodevelopmental and developmentally sensitive psychosocial frameworks to increase the applicability of ideation-to-action theories to adolescents. Further, utilizing real-time monitoring approaches may serve to further clarify the temporal association among risk factors and suicide.

Prospective Follow-Up of Adolescents With and at Risk for Depression: Protocol and Methods of the Identifying Depression Early in Adolescence Risk Stratified Cohort Longitudinal Assessments

Objective

To present the protocol and methods for the prospective longitudinal assessments-including clinical and digital phenotyping approaches-of the Identifying Depression Early in Adolescence Risk Stratified Cohort (IDEA-RiSCo) study, which comprises Brazilian adolescents stratified at baseline by risk of developing depression or presence of depression.

Method

Of 7,720 screened adolescents aged 14 to 16 years, we recruited 150 participants (75 boys, 75 girls) based on a composite risk score: 50 with low risk for developing depression (LR), 50 with high risk for developing depression (HR), and 50 with an active untreated major depressive episode (MDD). Three annual follow-up assessments were conducted, involving clinical measures (parent- and adolescent-reported questionnaires and psychiatrist assessments), active and passive data sensing via smartphones, and neurobiological measures (neuroimaging and biological material samples). Retention rates were 96% (Wave 1), 94% (Wave 2), and 88% (Wave 3), with no significant differences by sex or group (p > .05). Participants highlighted their familiarity with the research team and assessment process as a motivator for sustained engagement.

Discussion

This protocol relied on novel aspects, such as the use of a WhatsApp bot, which is particularly pertinent for low- to-middle-income countries, and the collection of information from diverse sources in a longitudinal design, encompassing clinical data, self-reports, parental reports, Global Positioning System (GPS) data, and ecological momentary assessments. The study engaged adolescents over an extensive period and demonstrated the feasibility of conducting a prospective follow-up study with a risk-enriched cohort of adolescents in a middle-income country, integrating mobile technology with traditional methodologies to enhance longitudinal data collection.

Investigating Rhythmicity in App Usage to Predict Depressive Symptoms: Protocol for Personalized Framework Development and Validation Through a Countrywide Study

BACKGROUND

Understanding a student's depressive symptoms could facilitate significantly more precise diagnosis and treatment. However, few studies have focused on depressive symptom prediction through unobtrusive systems, and these studies are limited by small sample sizes, low performance, and the requirement for higher resources. In addition, research has not explored whether statistically significant rhythms based on different app usage behavioral markers (eg, app usage sessions) exist that could be useful in finding subtle differences to predict with higher accuracy like the models based on rhythms of physiological data.

OBJECTIVE

The main objective of this study is to explore whether there exist statistically significant rhythms in resource-insensitive app usage behavioral markers and predict depressive symptoms through these marker-based rhythmic features. Another objective of this study is to understand whether there is a potential link between rhythmic features and depressive symptoms.

METHODS

Through a countrywide study, we collected 2952 students' raw app usage behavioral data and responses to the 9 depressive symptoms in the 9-item Patient Health Questionnaire (PHQ-9). The behavioral data were retrieved through our developed app, which was previously used in our pilot studies in Bangladesh on different research problems. To explore whether there is a rhythm based on app usage data, we will conduct a zero-amplitude test. In addition, we will develop a cosinor model for each participant to extract rhythmic parameters (eg, acrophase). In addition, to obtain a comprehensive picture of the rhythms, we will explore nonparametric rhythmic features (eg, interdaily stability). Furthermore, we will conduct regression analysis to understand the association of rhythmic features with depressive symptoms. Finally, we will develop a personalized multitask learning (MTL) framework to predict symptoms through rhythmic features.

RESULTS

After applying inclusion criteria (eg, having app usage data of at least 2 days to explore rhythmicity), we kept the data of 2902 (98.31%) students for analysis, with 24.48 million app usage events, and 7 days' app usage of 2849 (98.17%) students. The students are from all 8 divisions of Bangladesh, both public and private universities (19 different universities and 52 different departments). We are analyzing the data and will publish the findings in a peer-reviewed publication.

CONCLUSIONS

Having an in-depth understanding of app usage rhythms and their connection with depressive symptoms through a countrywide study can significantly help health care professionals and researchers better understand depressed students and may create possibilities for using app usage-based rhythms for intervention. In addition, the MTL framework based on app usage rhythmic features may more accurately predict depressive symptoms due to the rhythms' capability to find subtle differences.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/51540.

Multi-modal analysis of inflammation as a potential mediator of depressive symptoms in young people with HIV: The GOLD depression study

People living with HIV are at three times greater risk for depressive symptoms. Inflammation is a notable predictor of depression, and people with HIV exhibit chronic inflammation despite antiretroviral therapy. We hypothesised that inflammatory biomarkers may mediate the association between HIV status and depressive symptoms. Participants (N = 60, 53% girls, median [interquartile range (IQR)] age 15.5 [15.0, 16.0] years, 70% living with HIV, of whom 90.5% were virally-suppressed) completed the nine-item Patient Health Questionnaire (PHQ-9). We measured choline and myo-inositol in basal ganglia, midfrontal gray matter, and peritrigonal white matter using magnetic resonance spectroscopy, and 16 inflammatory proteins in blood serum using ELISA and Luminex™ multiplex immunoassays. Using structural equation mediation modelling, we calculated standardised indirect effect estimates with 95% confidence intervals. Median [IQR] total PHQ-9 score was 3 [0, 7]. HIV status was significantly associated with total PHQ-9 score (B = 3.32, p = 0.022). Participants with HIV showed a higher choline-to-creatine ratio in the basal ganglia than those without HIV (β = 0.86, pFDR = 0.035). In blood serum, participants with HIV showed higher monocyte chemoattractant protein-1 (MCP-1, β = 0.59, pFDR = 0.040), higher chitinase-3 like-1 (YKL-40, β = 0.73, pFDR = 0.032), and lower interleukin-1beta (IL-1β, β = -0.67, pFDR = 0.047) than those without HIV. There were no significant associations of any biomarkers with total PHQ-9 score. None of the indirect effects were significant, mediating <13.1% of the association. Findings remained consistent when accounting for age, gender, and time between neuroimaging and PHQ-9 administration. Using a robust analytical approach in a community-based sample, we have shown that participants living with HIV reported greater depressive symptoms than those without HIV, but we did not find that neuroimaging and blood biomarkers of inflammation significantly mediated this association. Further studies with participants experiencing severe depression may help to elucidate the links between HIV, inflammation, and depression.

Machine Learning for Multimodal Mental Health Detection: A Systematic Review of Passive Sensing Approaches

As mental health (MH) disorders become increasingly prevalent, their multifaceted symptoms and comorbidities with other conditions introduce complexity to diagnosis, posing a risk of underdiagnosis. While machine learning (ML) has been explored to mitigate these challenges, we hypothesized that multiple data modalities support more comprehensive detection and that non-intrusive collection approaches better capture natural behaviors. To understand the current trends, we systematically reviewed 184 studies to assess feature extraction, feature fusion, and ML methodologies applied to detect MH disorders from passively sensed multimodal data, including audio and video recordings, social media, smartphones, and wearable devices. Our findings revealed varying correlations of modality-specific features in individualized contexts, potentially influenced by demographics and personalities. We also observed the growing adoption of neural network architectures for model-level fusion and as ML algorithms, which have demonstrated promising efficacy in handling high-dimensional features while modeling within and cross-modality relationships. This work provides future researchers with a clear taxonomy of methodological approaches to multimodal detection of MH disorders to inspire future methodological advancements. The comprehensive analysis also guides and supports future researchers in making informed decisions to select an optimal data source that aligns with specific use cases based on the MH disorder of interest.

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 β = 0.219, p = 0.012) and continued to relate to PHQ-8 at medial (β = 0.198, p = 0.022) and proximal (β = 0.183, p = 0.045) windows. In contrast, circadian movement was proximally related to (β = -0.131, p = 0.035) but did not predict (distal β = 0.034, p = 0.577; medial β = -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.

Modeling Suicidality with Multimodal Impulsivity Characterization in Participants with Mental Health Disorder

Introduction

Suicide is one of the leading causes of death across different age groups. The persistence of suicidal ideation and the progression of suicidal ideations to action could be related to impulsivity, the tendency to act on urges with low temporal latency, and little forethought. Quantifying impulsivity could thus help suicidality estimation and risk assessments in ideation-to-action suicidality frameworks.

Methods

To model suicidality with impulsivity quantification, we obtained questionnaires, behavioral tests, heart rate variability (HRV), and resting state functional magnetic resonance imaging measurements from 34 participants with mood disorders. The participants were categorized into three suicidality groups based on their Mini-International Neuropsychiatric Interview: none, low, and moderate to severe.

Results

Questionnaire and HRV-based impulsivity measures were significantly different between the suicidality groups with higher subscales of impulsivity associated with higher suicidality. A multimodal system to characterize impulsivity objectively resulted in a classification accuracy of 96.77% in the three-class suicidality group prediction task.

Conclusions

This study elucidates the relative sensitivity of various impulsivity measures in differentiating participants with suicidality and demonstrates suicidality prediction with high accuracy using a multimodal objective impulsivity characterization in participants with mood disorders.

Acceptability and feasibility of ecological momentary assessment with augmentation of passive sensor data in young adults at high risk for suicide

Ecological Momentary Assessment (EMA) and wearable sensor data have the potential to enhance prediction of suicide risk in real-world conditions. However, the feasibility of this methodology with high-risk populations, including over extended periods, warrants closer attention. This study examined the feasibility and acceptability of concurrent EMA and wearable sensor monitoring in young adults after emergency department (ED) care for suicide risk-related concerns. For 2 months after ED discharge, 106 participants (ages 18-25; 81.1% female) took part in EMA surveys (4x per day) and passive sensor (Fitbit) monitoring and completed an end-of-study phone interview. Overall adherence to EMA (62.1%) and wearable sensor (53.6%) was moderate and comparable to briefer protocols. Relative to EMAs (81%), fewer participants completed the full 8 weeks of Fitbit (63%). While lower initial hopelessness was linked to reduced EMA adherence, previous-day suicidal ideation predicted lower Fitbit adherence on the next day. Self-endorsed barriers to EMA and wearable sensor adherence were also examined. Participants tended to report positive experience with the protocol, with majority indicating EMAs were minimally burdensome, reporting that the Fitbit was generally comfortable, and expressing interest in participating in a similar study again. Findings provide support for the feasibility and acceptability of concurrent intensive self-report and wearable sensor data during a high-risk period. Implications and future directions are discussed.

A Systematic Review of Location Data for Depression Prediction

Depression contributes to a wide range of maladjustment problems. With the development of technology, objective measurement for behavior and functional indicators of depression has become possible through the passive sensing technology of digital devices. Focusing on location data, we systematically reviewed the relationship between depression and location data. We searched Scopus, PubMed, and Web of Science databases by combining terms related to passive sensing and location data with depression. Thirty-one studies were included in this review. Location data demonstrated promising predictive power for depression. Studies examining the relationship between individual location data variables and depression, homestay, entropy, and the normalized entropy variable of entropy dimension showed the most consistent and significant correlations. Furthermore, variables of distance, irregularity, and location showed significant associations in some studies. However, semantic location showed inconsistent results. This suggests that the process of geographical movement is more related to mood changes than to semantic location. Future research must converge across studies on location-data measurement methods.

Systematic review and meta-analysis of performance of wearable artificial intelligence in detecting and predicting depression

Given the limitations of traditional approaches, wearable artificial intelligence (AI) is one of the technologies that have been exploited to detect or predict depression. The current review aimed at examining the performance of wearable AI in detecting and predicting depression. The search sources in this systematic review were 8 electronic databases. Study selection, data extraction, and risk of bias assessment were carried out by two reviewers independently. The extracted results were synthesized narratively and statistically. Of the 1314 citations retrieved from the databases, 54 studies were included in this review. The pooled mean of the highest accuracy, sensitivity, specificity, and root mean square error (RMSE) was 0.89, 0.87, 0.93, and 4.55, respectively. The pooled mean of lowest accuracy, sensitivity, specificity, and RMSE was 0.70, 0.61, 0.73, and 3.76, respectively. Subgroup analyses revealed that there is a statistically significant difference in the highest accuracy, lowest accuracy, highest sensitivity, highest specificity, and lowest specificity between algorithms, and there is a statistically significant difference in the lowest sensitivity and lowest specificity between wearable devices. Wearable AI is a promising tool for depression detection and prediction although it is in its infancy and not ready for use in clinical practice. Until further research improve its performance, wearable AI should be used in conjunction with other methods for diagnosing and predicting depression. Further studies are needed to examine the performance of wearable AI based on a combination of wearable device data and neuroimaging data and to distinguish patients with depression from those with other diseases.

Wearable Artificial Intelligence for Anxiety and Depression: Scoping Review

BACKGROUND

Anxiety and depression are the most common mental disorders worldwide. Owing to the lack of psychiatrists around the world, the incorporation of artificial intelligence (AI) into wearable devices (wearable AI) has been exploited to provide mental health services.

OBJECTIVE

This review aimed to explore the features of wearable AI used for anxiety and depression to identify application areas and open research issues.

METHODS

We searched 8 electronic databases (MEDLINE, PsycINFO, Embase, CINAHL, IEEE Xplore, ACM Digital Library, Scopus, and Google Scholar) and included studies that met the inclusion criteria. Then, we checked the studies that cited the included studies and screened studies that were cited by the included studies. The study selection and data extraction were carried out by 2 reviewers independently. The extracted data were aggregated and summarized using narrative synthesis.

RESULTS

Of the 1203 studies identified, 69 (5.74%) were included in this review. Approximately, two-thirds of the studies used wearable AI for depression, whereas the remaining studies used it for anxiety. The most frequent application of wearable AI was in diagnosing anxiety and depression; however, none of the studies used it for treatment purposes. Most studies targeted individuals aged between 18 and 65 years. The most common wearable device used in the studies was Actiwatch AW4 (Cambridge Neurotechnology Ltd). Wrist-worn devices were the most common type of wearable device in the studies. The most commonly used category of data for model development was physical activity data, followed by sleep data and heart rate data. The most frequently used data set from open sources was Depresjon. The most commonly used algorithm was random forest, followed by support vector machine.

CONCLUSIONS

Wearable AI can offer great promise in providing mental health services related to anxiety and depression. Wearable AI can be used by individuals for the prescreening assessment of anxiety and depression. Further reviews are needed to statistically synthesize the studies' results related to the performance and effectiveness of wearable AI. Given its potential, technology companies should invest more in wearable AI for the treatment of anxiety and depression.