Automated Screening for Social Anxiety, Generalized Anxiety, and Depression From Objective Smartphone-Collected Data: Cross-sectional Study

Digital biomarkers in depression: A systematic review and call for standardization and harmonization of feature engineering

BACKGROUND

General physicians misclassify depression in more than half of the cases. Researchers have explored the feasibility of leveraging passively collected data points, also called digital biomarkers, to provide more granular understanding of depression phenotypes as well as a more objective assessment of disease.

METHOD

This paper provides a systematic review following the PRISMA guidelines (Page et al., 2021) to understand which digital biomarkers might be relevant for passive screening of depression. Pubmed and PsycInfo were systematically searched for studies published from 2019 to early 2024, resulting in 161 records assessed for eligibility. Excluded were intervention studies, studies focusing on a different disease or those with a lack of passive data collection. 74 studies remained for a quality assessment, after which 27 studies were included.

RESULTS

The review shows that depressed participants' real-life behavior such as reduced communication with others can be tracked by passive data. Machine learning models for the classification of depression have shown accuracies up to 0.98, surpassing the quality of many standardized assessment methods.

LIMITATIONS

Inconsistency of outcome reporting of current studies does not allow for drawing statistical conclusions regarding effectiveness of individual included features. The Covid-19 pandemic might have impacted the ongoing studies between 2020 and 2022.

CONCLUSION

While digital biomarkers allow real-life tracking of participant's behavior and symptoms, further work is required to align the feature engineering of digital biomarkers. With shown high accuracies of assessments, connecting digital biomarkers with clinical practice can be a promising method of detecting symptoms of depression automatically.

Digital Phenotyping for Stress, Anxiety, and Mild Depression: Systematic Literature Review

BACKGROUND

Unaddressed early-stage mental health issues, including stress, anxiety, and mild depression, can become a burden for individuals in the long term. Digital phenotyping involves capturing continuous behavioral data via digital smartphone devices to monitor human behavior and can potentially identify milder symptoms before they become serious.

OBJECTIVE

This systematic literature review aimed to answer the following questions: (1) what is the evidence of the effectiveness of digital phenotyping using smartphones in identifying behavioral patterns related to stress, anxiety, and mild depression? and (2) in particular, which smartphone sensors are found to be effective, and what are the associated challenges?

METHODS

We used the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) process to identify 36 papers (reporting on 40 studies) to assess the key smartphone sensors related to stress, anxiety, and mild depression. We excluded studies conducted with nonadult participants (eg, teenagers and children) and clinical populations, as well as personality measurement and phobia studies. As we focused on the effectiveness of digital phenotyping using smartphones, results related to wearable devices were excluded.

RESULTS

We categorized the studies into 3 major groups based on the recruited participants: studies with students enrolled in universities, studies with adults who were unaffiliated to any particular organization, and studies with employees employed in an organization. The study length varied from 10 days to 3 years. A range of passive sensors were used in the studies, including GPS, Bluetooth, accelerometer, microphone, illuminance, gyroscope, and Wi-Fi. These were used to assess locations visited; mobility; speech patterns; phone use, such as screen checking; time spent in bed; physical activity; sleep; and aspects of social interactions, such as the number of interactions and response time. Of the 40 included studies, 31 (78%) used machine learning models for prediction; most others (n=8, 20%) used descriptive statistics. Students and adults who experienced stress, anxiety, or depression visited fewer locations, were more sedentary, had irregular sleep, and accrued increased phone use. In contrast to students and adults, less mobility was seen as positive for employees because less mobility in workplaces was associated with higher performance. Overall, travel, physical activity, sleep, social interaction, and phone use were related to stress, anxiety, and mild depression.

CONCLUSIONS

This study focused on understanding whether smartphone sensors can be effectively used to detect behavioral patterns associated with stress, anxiety, and mild depression in nonclinical participants. The reviewed studies provided evidence that smartphone sensors are effective in identifying behavioral patterns associated with stress, anxiety, and mild depression.

Studies of Social Anxiety Using Ambulatory Assessment: Systematic Review

BACKGROUND

There has been an increased interest in understanding social anxiety (SA) and SA disorder (SAD) antecedents and consequences as they occur in real time, resulting in a proliferation of studies using ambulatory assessment (AA). Despite the exponential growth of research in this area, these studies have not been synthesized yet.

OBJECTIVE

This review aimed to identify and describe the latest advances in the understanding of SA and SAD through the use of AA.

METHODS

Following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, a systematic literature search was conducted in Scopus, PubMed, and Web of Science.

RESULTS

A total of 70 articles met the inclusion criteria. The qualitative synthesis of these studies showed that AA permitted the exploration of the emotional, cognitive, and behavioral dynamics associated with the experience of SA and SAD. In line with the available models of SA and SAD, emotion regulation, perseverative cognition, cognitive factors, substance use, and interactional patterns were the principal topics of the included studies. In addition, the incorporation of AA to study psychological interventions, multimodal assessment using sensors and biosensors, and transcultural differences were some of the identified emerging topics.

CONCLUSIONS

AA constitutes a very powerful methodology to grasp SA from a complementary perspective to laboratory experiments and usual self-report measures, shedding light on the cognitive, emotional, and behavioral antecedents and consequences of SA and the development and maintenance of SAD as a mental disorder.

The Use of Passive Smartphone Data to Monitor Anxiety and Depression Among College Students in Real-World Settings: Protocol for a Systematic Review

BACKGROUND

College students are particularly at risk of depression and anxiety. These disorders have a serious impact on public health and affect patients' daily lives. The potential for using smartphones to monitor these mental conditions, providing passively collected physiological and behavioral data, has been reported among the general population. However, research on the use of passive smartphone data to monitor anxiety and depression among specific populations of college students has never been reviewed.

OBJECTIVE

This review's objectives are (1) to provide an overview of the use of passive smartphone data to monitor depression and anxiety among college students, given their specific type of smartphone use and living setting, and (2) to evaluate the different methods used to assess those smartphone data, including their strengths and limitations.

METHODS

This review will follow the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Two independent investigators will review English-language, full-text, peer-reviewed papers extracted from PubMed and Web of Science that measure passive smartphone data and levels of depression or anxiety among college students. A preliminary search was conducted in February 2022 as a proof of concept.

RESULTS

Our preliminary search identified 115 original articles, 8 of which met our eligibility criteria. Our planned full study will include an article selection flowchart, tables, and figures representing the main information extracted on the use of passive smartphone data to monitor anxiety and depression among college students.

CONCLUSIONS

The planned review will summarize the published research on using passive smartphone data to monitor anxiety and depression among college students. The review aims to better understand whether and how passive smartphone data are associated with indicators of depression and anxiety among college students. This could be valuable in order to provide a digital solution for monitoring mental health issues in this specific population by enabling easier identification and follow-up of the patients.

TRIAL REGISTRATION

PROSPERO CRD42022316263; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=316263.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/38785.

Artificial intelligence assisted tools for the detection of anxiety and depression leading to suicidal ideation in adolescents: a review

Epidemiological studies report high levels of anxiety and depression amongst adolescents. These psychiatric conditions and complex interplays of biological, social and environmental factors are important risk factors for suicidal behaviours and suicide, which show a peak in late adolescence and early adulthood. Although deaths by suicide have fallen globally in recent years, suicide deaths are increasing in some countries, such as the US. Suicide prevention is a challenging global public health problem. Currently, there aren't any validated clinical biomarkers for suicidal diagnosis, and traditional methods exhibit limitations. Artificial intelligence (AI) is budding in many fields, including in the diagnosis of medical conditions. This review paper summarizes recent studies (past 8 years) that employed AI tools for the automated detection of depression and/or anxiety disorder and discusses the limitations and effects of some modalities. The studies assert that AI tools produce promising results and could overcome the limitations of traditional diagnostic methods. Although using AI tools for suicidal ideation exhibits limitations, these are outweighed by the advantages. Thus, this review article also proposes extracting a fusion of features such as facial images, speech signals, and visual and clinical history features from deep models for the automated detection of depression and/or anxiety disorder in individuals, for future work. This may pave the way for the identification of individuals with suicidal thoughts.

Predicting Generalized Anxiety Disorder from Impromptu Speech Transcripts Using Context-Aware Transformer-Based Neural Networks: Model Evaluation study (Preprint)

BACKGROUND

The ability to automatically detect anxiety disorders from speech could be useful as a screening tool for an anxiety disorder. Prior studies have shown that individual words in textual transcripts of speech have an association with anxiety severity. Transformer-based neural networks are models that have been recently shown to have powerful predictive capabilities based on the context of more than one input word. Transformers detect linguistic patterns and can be separately trained to make specific predictions based on these patterns.

OBJECTIVE

This study aimed to determine whether a transformer-based language model can be used to screen for generalized anxiety disorder from impromptu speech transcripts.

METHODS

A total of 2000 participants provided an impromptu speech sample in response to a modified version of the Trier Social Stress Test (TSST). They also completed the Generalized Anxiety Disorder 7-item (GAD-7) scale. A transformer-based neural network model (pretrained on large textual corpora) was fine-tuned on the speech transcripts and the GAD-7 to predict whether a participant was above or below a screening threshold of the GAD-7. We reported the area under the receiver operating characteristic curve (AUROC) on the test data and compared the results with a baseline logistic regression model using the Linguistic Inquiry and Word Count (LIWC) features as input. Using the integrated gradient method to determine specific words that strongly affect the predictions, we inferred specific linguistic patterns that influence the predictions.

RESULTS

The baseline LIWC-based logistic regression model had an AUROC value of 0.58. The fine-tuned transformer model achieved an AUROC value of 0.64. Specific words that were often implicated in the predictions were also dependent on the context. For example, the first-person singular pronoun "I" influenced toward an anxious prediction 88% of the time and a nonanxious prediction 12% of the time, depending on the context. Silent pauses in speech, also often implicated in predictions, influenced toward an anxious prediction 20% of the time and a nonanxious prediction 80% of the time.

CONCLUSIONS

There is evidence that a transformer-based neural network model has increased predictive power compared with the single word-based LIWC model. We also showed that the use of specific words in a specific context-a linguistic pattern-is part of the reason for the better prediction. This suggests that such transformer-based models could play a useful role in anxiety screening systems.

A Machine Learning Approach for Continuous Mining of Nonidentifiable Smartphone Data to Create a Novel Digital Biomarker Detecting Generalized Anxiety Disorder: Prospective Cohort Study

BACKGROUND

Anxiety is one of the leading causes of mental health disability around the world. Currently, a majority of the population who experience anxiety go undiagnosed or untreated. New and innovative ways of diagnosing and monitoring anxiety have emerged using smartphone sensor-based monitoring as a metric for the management of anxiety. This is a novel study as it adds to the field of research through the use of nonidentifiable smartphone usage to help detect and monitor anxiety remotely and in a continuous and passive manner.

OBJECTIVE

This study aims to evaluate the accuracy of a novel mental behavioral profiling metric derived from smartphone usage for the identification and tracking of generalized anxiety disorder (GAD).

METHODS

Smartphone data and self-reported 7-item GAD anxiety assessments were collected from 229 participants using an Android operating system smartphone in an observational study over an average of 14 days (SD 29.8). A total of 34 features were mined to be constructed as a potential digital phenotyping marker from continuous smartphone usage data. We further analyzed the correlation of these digital behavioral markers against each item of the 7-item Generalized Anxiety Disorder Scale (GAD-7) and its influence on the predictions of machine learning algorithms.

RESULTS

A total of 229 participants were recruited in this study who had completed the GAD-7 assessment and had at least one set of passive digital data collected within a 24-hour period. The mean GAD-7 score was 11.8 (SD 5.7). Regression modeling was tested against classification modeling and the highest prediction accuracy was achieved from a binary XGBoost classification model (precision of 73%-81%; recall of 68%-87%; F₁-score of 71%-79%; accuracy of 76%; area under the curve of 80%). Nonparametric permutation testing with Pearson correlation results indicated that the proposed metric (Mental Health Similarity Score [MHSS]) had a colinear relationship between GAD-7 Items 1, 3 and 7.

CONCLUSIONS

The proposed MHSS metric demonstrates the feasibility of using passively collected nonintrusive smartphone data and machine learning-based data mining techniques to track an individuals' daily anxiety levels with a 76% accuracy that directly relates to the GAD-7 scale.

Digital Phenotyping in Health Using Machine Learning Approaches: Scoping Review

BACKGROUND

Digital phenotyping is the real-time collection of individual-level active and passive data from users in naturalistic and free-living settings via personal digital devices, such as mobile phones and wearable devices. Given the novelty of research in this field, there is heterogeneity in the clinical use cases, types of data collected, modes of data collection, data analysis methods, and outcomes measured.

OBJECTIVE

The primary aim of this scoping review was to map the published research on digital phenotyping and to outline study characteristics, data collection and analysis methods, machine learning approaches, and future implications.

METHODS

We utilized an a priori approach for the literature search and data extraction and charting process, guided by the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-analyses Extension for Scoping Reviews). We identified relevant studies published in 2020, 2021, and 2022 on PubMed and Google Scholar using search terms related to digital phenotyping. The titles, abstracts, and keywords were screened during the first stage of the screening process, and the second stage involved screening the full texts of the shortlisted articles. We extracted and charted the descriptive characteristics of the final studies, which were countries of origin, study design, clinical areas, active and/or passive data collected, modes of data collection, data analysis approaches, and limitations.

RESULTS

A total of 454 articles on PubMed and Google Scholar were identified through search terms associated with digital phenotyping, and 46 articles were deemed eligible for inclusion in this scoping review. Most studies evaluated wearable data and originated from North America. The most dominant study design was observational, followed by randomized trials, and most studies focused on psychiatric disorders, mental health disorders, and neurological diseases. A total of 7 studies used machine learning approaches for data analysis, with random forest, logistic regression, and support vector machines being the most common.

CONCLUSIONS

Our review provides foundational as well as application-oriented approaches toward digital phenotyping in health. Future work should focus on more prospective, longitudinal studies that include larger data sets from diverse populations, address privacy and ethical concerns around data collection from consumer technologies, and build "digital phenotypes" to personalize digital health interventions and treatment plans.

Acoustic and Linguistic Features of Impromptu Speech and Their Association With Anxiety: Validation Study

BACKGROUND

The measurement and monitoring of generalized anxiety disorder requires frequent interaction with psychiatrists or psychologists. Access to mental health professionals is often difficult because of high costs or insufficient availability. The ability to assess generalized anxiety disorder passively and at frequent intervals could be a useful complement to conventional treatment and help with relapse monitoring. Prior work suggests that higher anxiety levels are associated with features of human speech. As such, monitoring speech using personal smartphones or other wearable devices may be a means to achieve passive anxiety monitoring.

OBJECTIVE

This study aims to validate the association of previously suggested acoustic and linguistic features of speech with anxiety severity.

METHODS

A large number of participants (n=2000) were recruited and participated in a single web-based study session. Participants completed the Generalized Anxiety Disorder 7-item scale assessment and provided an impromptu speech sample in response to a modified version of the Trier Social Stress Test. Acoustic and linguistic speech features were a priori selected based on the existing speech and anxiety literature, along with related features. Associations between speech features and anxiety levels were assessed using age and personal income as covariates.

RESULTS

Word count and speaking duration were negatively correlated with anxiety scores (r=-0.12; P<.001), indicating that participants with higher anxiety scores spoke less. Several acoustic features were also significantly (P<.05) associated with anxiety, including the mel-frequency cepstral coefficients, linear prediction cepstral coefficients, shimmer, fundamental frequency, and first formant. In contrast to previous literature, second and third formant, jitter, and zero crossing rate for the z score of the power spectral density acoustic features were not significantly associated with anxiety. Linguistic features, including negative-emotion words, were also associated with anxiety (r=0.10; P<.001). In addition, some linguistic relationships were sex dependent. For example, the count of words related to power was positively associated with anxiety in women (r=0.07; P=.03), whereas it was negatively associated with anxiety in men (r=-0.09; P=.01).

CONCLUSIONS

Both acoustic and linguistic speech measures are associated with anxiety scores. The amount of speech, acoustic quality of speech, and gender-specific linguistic characteristics of speech may be useful as part of a system to screen for anxiety, detect relapse, or monitor treatment.

Screening for Generalized Anxiety Disorder from Acoustic and Linguistic Features of Impromptu Speech: Prediction Model Evaluation Study (Preprint)

Background

Frequent interaction with mental health professionals is required to screen, diagnose, and track mental health disorders. However, high costs and insufficient access can make frequent interactions difficult. The ability to assess a mental health disorder passively and at frequent intervals could be a useful complement to the conventional treatment. It may be possible to passively assess clinical symptoms with high frequency by characterizing speech alterations collected using personal smartphones or other wearable devices. The association between speech features and mental health disorders can be leveraged as an objective screening tool.

Objective

This study aimed to evaluate the performance of a model that predicts the presence of generalized anxiety disorder (GAD) from acoustic and linguistic features of impromptu speech on a larger and more generalizable scale than prior studies did.

Methods

A total of 2000 participants were recruited, and they participated in a single web-based session. They completed the Generalized Anxiety Disorder-7 item scale assessment and provided an impromptu speech sample in response to a modified version of the Trier Social Stress Test. We used the linguistic and acoustic features that were found to be associated with anxiety disorders in previous studies along with demographic information to predict whether participants fell above or below the screening threshold for GAD based on the Generalized Anxiety Disorder-7 item scale threshold of 10. Separate models for each sex were also evaluated. We reported the mean area under the receiver operating characteristic (AUROC) from a repeated 5-fold cross-validation to evaluate the performance of the models.

Results

A logistic regression model using only acoustic and linguistic speech features achieved a significantly greater prediction accuracy than a random model did (mean AUROC 0.57, SD 0.03; P<.001). When separately assessing samples from female participants, we observed a mean AUROC of 0.55 (SD 0.05; P=.01). The model constructed from the samples from male participants achieved a mean AUROC of 0.57 (SD 0.07; P=.002). The mean AUROC increased to 0.62 (SD 0.03; P<.001) on the all-sample data set when demographic information (age, sex, and income) was included, indicating the importance of demographics when screening for anxiety disorders. The performance also increased for the female sample to a mean of 0.62 (SD 0.04; P<.001) when using demographic information (age and income). An increase in performance was not observed when demographic information was added to the model constructed from the male samples.

Conclusions

A logistic regression model using acoustic and linguistic speech features, which have been suggested to be associated with anxiety disorders in prior studies, can achieve above-random accuracy for predicting GAD. Importantly, the addition of basic demographic variables further improves model performance, suggesting a role for speech and demographic information to be used as automated, objective screeners of GAD.

Opportunities for Smartphone Sensing in E-Health Research: A Narrative Review

Recent years have seen significant advances in the sensing capabilities of smartphones, enabling them to collect rich contextual information such as location, device usage, and human activity at a given point in time. Combined with widespread user adoption and the ability to gather user data remotely, smartphone-based sensing has become an appealing choice for health research. Numerous studies over the years have demonstrated the promise of using smartphone-based sensing to monitor a range of health conditions, particularly mental health conditions. However, as research is progressing to develop the predictive capabilities of smartphones, it becomes even more crucial to fully understand the capabilities and limitations of using this technology, given its potential impact on human health. To this end, this paper presents a narrative review of smartphone-sensing literature from the past 5 years, to highlight the opportunities and challenges of this approach in healthcare. It provides an overview of the type of health conditions studied, the types of data collected, tools used, and the challenges encountered in using smartphones for healthcare studies, which aims to serve as a guide for researchers wishing to embark on similar research in the future. Our findings highlight the predominance of mental health studies, discuss the opportunities of using standardized sensing approaches and machine-learning advancements, and present the trends of smartphone sensing in healthcare over the years.

Digital phenotype of mood disorders: A conceptual and critical review

BACKGROUND

Mood disorders are commonly diagnosed and staged using clinical features that rely merely on subjective data. The concept of digital phenotyping is based on the idea that collecting real-time markers of human behavior allows us to determine the digital signature of a pathology. This strategy assumes that behaviors are quantifiable from data extracted and analyzed through digital sensors, wearable devices, or smartphones. That concept could bring a shift in the diagnosis of mood disorders, introducing for the first time additional examinations on psychiatric routine care.

OBJECTIVE

The main objective of this review was to propose a conceptual and critical review of the literature regarding the theoretical and technical principles of the digital phenotypes applied to mood disorders.

METHODS

We conducted a review of the literature by updating a previous article and querying the PubMed database between February 2017 and November 2021 on titles with relevant keywords regarding digital phenotyping, mood disorders and artificial intelligence.

RESULTS

Out of 884 articles included for evaluation, 45 articles were taken into account and classified by data source (multimodal, actigraphy, ECG, smartphone use, voice analysis, or body temperature). For depressive episodes, the main finding is a decrease in terms of functional and biological parameters [decrease in activities and walking, decrease in the number of calls and SMS messages, decrease in temperature and heart rate variability (HRV)], while the manic phase produces the reverse phenomenon (increase in activities, number of calls and HRV).

CONCLUSION

The various studies presented support the potential interest in digital phenotyping to computerize the clinical characteristics of mood disorders.