Detecting Bipolar Depression From Geographic Location Data

Digital biomarkers for non-motor symptoms in Parkinson's disease: the state of the art

Digital biomarkers that remotely monitor symptoms have the potential to revolutionize outcome assessments in future disease-modifying trials in Parkinson's disease (PD), by allowing objective and recurrent measurement of symptoms and signs collected in the participant's own living environment. This biomarker field is developing rapidly for assessing the motor features of PD, but the non-motor domain lags behind. Here, we systematically review and assess digital biomarkers under development for measuring non-motor symptoms of PD. We also consider relevant developments outside the PD field. We focus on technological readiness level and evaluate whether the identified digital non-motor biomarkers have potential for measuring disease progression, covering the spectrum from prodromal to advanced disease stages. Furthermore, we provide perspectives for future deployment of these biomarkers in trials. We found that various wearables show high promise for measuring autonomic function, constipation and sleep characteristics, including REM sleep behavior disorder. Biomarkers for neuropsychiatric symptoms are less well-developed, but show increasing accuracy in non-PD populations. Most biomarkers have not been validated for specific use in PD, and their sensitivity to capture disease progression remains untested for prodromal PD where the need for digital progression biomarkers is greatest. External validation in real-world environments and large longitudinal cohorts remains necessary for integrating non-motor biomarkers into research, and ultimately also into daily clinical practice.

Depressive symptom screening in elderly by passive sensing data of smartphones or smartwatches: A systematic review

BACKGROUND

The elderly is commonly susceptible to depression, the symptoms for which may overlap with natural aging or other illnesses, and therefore miss being captured by routine screening questionnaires. Passive sensing data have been promoted as a tool for depressive symptoms detection though there is still limited evidence on its usage in the elderly. Therefore, this study aims to review current knowledge on the use of passive sensing data via smartphones and smartwatches in depressive symptom screening for the elderly.

METHOD

The search of literature was performed in PubMed, IEEE Xplore digital library, and PsycINFO. Literature investigating the use of passive sensing data to screen, monitor, and/or predict depressive symptoms in the elderly (aged 60 and above) via smartphones and/or wrist-worn wearables was included for initial screening. Studies in English from international journals published between January 2012 to September 2022 were included. The reviewed studies were further analyzed by a narrative analysis.

RESULTS

The majority of 21 included studies were conducted in Western countries with a few in Asia and Australia. Most studies adopted a cohort study design (n = 12), followed by cross-sectional design (n = 7) and a case-control design (n = 2). The most popular passive sensing data was related to sleep and physical activity using an actigraphy. Sleep characteristics, such as prolonged wakefulness after sleep onset, along with lower levels of physical activity, exhibited a significant association with depression. However, cohort studies expressed concerns regarding data quality stemming from incomplete follow-up and potential confounding effects.

CONCLUSION

Passive sensing data, such as sleep, and physical activity parameters should be promoted for depressive symptoms detection. However, the validity, reliability, feasibility, and privacy concerns still need further exploration.

MoodSensing: A smartphone app for digital phenotyping and assessment of bipolar disorder

BACKGROUND

Daily life tracking has proven to be of great help in the assessment of patients with bipolar disorder. Although there are many smartphone apps for tracking bipolar disorder, most of them lack academic verification, privacy policy and long-term maintenance.

METHODS

Our developed app, MoodSensing, aims to collect users' digital phenotyping for assessment of bipolar disorder. The data collection was approved by the Institutional Review Board. This study collaborated with professional clinicians to ensure that the app meets both clinical needs and user experience requirements. Based on the collected digital phenotyping, deep learning techniques were applied to forecast participants' weekly HAM-D and YMRS scale scores.

RESULTS

In experiments, the data collected by our app can effectively predict the scale scores, reaching the mean absolute error of 0.84 and 0.22 on the scales. The statistical data also demonstrate the increase in user engagement.

CONCLUSIONS

Our analysis reveals that the developed MoodSensing app can not only provide a good user experience, but also the recorded data have certain discriminability for clinical assessment. Our app also provides relevant policies to protect user privacy, and has been launched in the Apple Store and Google Play Store.

Smartphone and Wearable Device-Based Digital Phenotyping to Understand Substance use and its Syndemics

Digital phenotyping is a process that allows researchers to leverage smartphone and wearable data to explore how technology use relates to behavioral health outcomes. In this Research Concepts article, we provide background on prior research that has employed digital phenotyping; the fundamentals of how digital phenotyping works, using examples from participant data; the application of digital phenotyping in the context of substance use and its syndemics; and the ethical, legal and social implications of digital phenotyping. We discuss applications for digital phenotyping in medical toxicology, as well as potential uses for digital phenotyping in future research. We also highlight the importance of obtaining ground truth annotation in order to identify and establish digital phenotypes of key behaviors of interest. Finally, there are many potential roles for medical toxicologists to leverage digital phenotyping both in research and in the future as a clinical tool to better understand the contextual features associated with drug poisoning and overdose. This article demonstrates how medical toxicologists and researchers can progress through phases of a research trajectory using digital phenotyping to better understand behavior and its association with smartphone usage.

Multimodal Mental Health Digital Biomarker Analysis From Remote Interviews Using Facial, Vocal, Linguistic, and Cardiovascular Patterns

OBJECTIVE

Psychiatric evaluation suffers from subjectivity and bias, and is hard to scale due to intensive professional training requirements. In this work, we investigated whether behavioral and physiological signals, extracted from tele-video interviews, differ in individuals with psychiatric disorders.

METHODS

Temporal variations in facial expression, vocal expression, linguistic expression, and cardiovascular modulation were extracted from simultaneously recorded audio and video of remote interviews. Averages, standard deviations, and Markovian process-derived statistics of these features were computed from 73 subjects. Four binary classification tasks were defined: detecting 1) any clinically-diagnosed psychiatric disorder, 2) major depressive disorder, 3) self-rated depression, and 4) self-rated anxiety. Each modality was evaluated individually and in combination.

RESULTS

Statistically significant feature differences were found between psychiatric and control subjects. Correlations were found between features and self-rated depression and anxiety scores. Heart rate dynamics provided the best unimodal performance with areas under the receiver-operator curve (AUROCs) of 0.68-0.75 (depending on the classification task). Combining multiple modalities provided AUROCs of 0.72-0.82.

CONCLUSION

Multimodal features extracted from remote interviews revealed informative characteristics of clinically diagnosed and self-rated mental health status.

SIGNIFICANCE

The proposed multimodal approach has the potential to facilitate scalable, remote, and low-cost assessment for low-burden automated mental health services.

Video-based evaluation system for tic action in Tourette syndrome: modeling, detection, and evaluation

Behavioral ratings based on clinical observations are still the gold standard for screening, diagnosing, and assessing outcomes in Tourette syndrome. Detecting tic symptoms plays an important role in patient treatment and evaluation; accurate tic identification is the key to clinical diagnosis and evaluation. In this study, we proposed a tic action detection method using face video feature recognition for tic and control groups. Through facial ROI extraction, a 3D convolutional neural network was used to learn video feature representations, and multi-instance learning anomaly detection strategy was integrated to construct the tic action analysis and discrimination framework. We applied this tic recognition framework in our video dataset. The model evaluation results achieved average tic detection accuracy of 91.02%, precision of 77.07% and recall of 78.78%. And the tic score curve with postprocessing provided information of how the patient's twitches change over time. The detection results at the individual level indicated that our method can effectively detect tic actions in videos of Tourette patients without the need for fine labeling, which is significant for the long-term evaluation of patients with Tourette syndrome.

Human-centred artificial intelligence for mobile health sensing: challenges and opportunities

Advances in wearable sensing and mobile computing have enabled the collection of health and well-being data outside of traditional laboratory and hospital settings, paving the way for a new era of mobile health. Meanwhile, artificial intelligence (AI) has made significant strides in various domains, demonstrating its potential to revolutionize healthcare. Devices can now diagnose diseases, predict heart irregularities and unlock the full potential of human cognition. However, the application of machine learning (ML) to mobile health sensing poses unique challenges due to noisy sensor measurements, high-dimensional data, sparse and irregular time series, heterogeneity in data, privacy concerns and resource constraints. Despite the recognition of the value of mobile sensing, leveraging these datasets has lagged behind other areas of ML. Furthermore, obtaining quality annotations and ground truth for such data is often expensive or impractical. While recent large-scale longitudinal studies have shown promise in leveraging wearable sensor data for health monitoring and prediction, they also introduce new challenges for data modelling. This paper explores the challenges and opportunities of human-centred AI for mobile health, focusing on key sensing modalities such as audio, location and activity tracking. We discuss the limitations of current approaches and propose potential solutions.

Clinician and Patient Perspectives on the Use of Passive Mobile Monitoring and Self-Tracking for Patients With Serious Mental Illness: User-Centered Approach

BACKGROUND

Early intervention in mental health crises can prevent negative outcomes. A promising new direction is remote mental health monitoring using smartphone technology to passively collect data from individuals to rapidly detect the worsening of serious mental illness (SMI). This technology may benefit patients with SMI, but little is known about health IT acceptability among this population or their mental health clinicians.

OBJECTIVE

We used the Health Information Technology Acceptability Model to analyze the acceptability and usability of passive mobile monitoring and self-tracking among patients with serious mental illness and their mental health clinicians.

METHODS

Data collection took place between December 2020 and June 2021 in 1 Veterans Administration health care system. Interviews with mental health clinicians (n=16) assessed the acceptability of mobile sensing, its usefulness as a tool to improve clinical assessment and care, and recommendations for program refinements. Focus groups with patients with SMI (n=3 groups) and individual usability tests (n=8) elucidated patient attitudes about engaging in health IT and perceptions of its usefulness as a tool for self-tracking and improving mental health assessments.

RESULTS

Clinicians discussed the utility of web-based data dashboards to monitor patients with SMI health behaviors and receiving alerts about their worsening health. Potential benefits included improving clinical care, capturing behaviors patients do not self-report, watching trends, and receiving alerts. Clinicians' concerns included increased workloads tied to dashboard data review, lack of experience using health IT in clinical care, and how SMI patients' associated paranoia and financial instability would impact patient uptake. Despite concerns, all mental health clinicians stated that they would recommend it. Almost all patients with SMI were receptive to using smartphone dashboards for self-monitoring and having behavioral change alerts sent to their mental health clinicians. They found the mobile app easy to navigate and dashboards easy to find and understand. Patient concerns centered on privacy and "government tracking," and their phone's battery life and data plans. Despite concerns, most reported that they would use it.

CONCLUSIONS

Many people with SMI would like to have mobile informatics tools that can support their illness and recovery. Similar to other populations (eg, older adults, people experiencing homelessness) this population presents challenges to adoption and implementation. Health care organizations will need to provide resources to address these and support successful illness management. Clinicians are supportive of technological approaches, with adapting informatics data into their workflow as the primary challenge. Despite clear challenges, technological developments are increasingly designed to be acceptable to patients. The research development-clinical deployment gap must be addressed by health care systems, similar to computerized cognitive training. It will ensure clinicians operate at the top of their skill set and are not overwhelmed by administrative tasks, data summarization, or reviewing data that do not indicate a need for intervention.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.2196/39010.

Symptom tracking in endometriosis using digital technologies: Knowns, unknowns, and future prospects

Endometriosis is a common chronic pain condition with no known cure and limited treatment options. Digital technologies, ranging from smartphone apps to wearable sensors, have shown potential toward facilitating chronic pain assessment and management; however, to date, many of these tools have not been specifically deployed or evaluated in patients with endometriosis-associated pain. Informed by previous studies in related chronic pain conditions, we discuss how digital technologies may be used in endometriosis to facilitate objective, continuous, and holistic symptom tracking. We postulate that these pervasive and increasingly affordable technologies present promising opportunities toward developing decision-support tools assisting healthcare professionals and empowering patients with endometriosis to make better-informed choices about symptom management.

A Digital System (YouXin) to Facilitate Self-Management by People With Psychosis in China: Protocol for a Nonrandomized Validity and Feasibility Study With a Mixed Methods Design

BACKGROUND

Psychosis is one of the most disabling mental health conditions and causes significant personal, social, and economic burden. Accurate and timely symptom monitoring is critical to offering prompt and time-sensitive clinical services. Digital health is a promising solution for the barriers encountered by conventional symptom monitoring approaches, including accessibility, the ecological validity of assessments, and recall bias. However, to date, there has been no digital health technology developed to support self-management for people with psychosis in China.

OBJECTIVE

We report the study protocol to evaluate the validity, feasibility, acceptability, usability, and safety of a symptom self-monitoring smartphone app (YouXin; Chinese name ) for people with psychosis in China.

METHODS

This is a nonrandomized validity and feasibility study with a mixed methods design. The study was approved by the University of Manchester and Beijing Anding Hospital Research Ethics Committee. YouXin is a smartphone app designed to facilitate symptom self-monitoring for people with psychosis. YouXin has 2 core functions: active monitoring of symptoms (ie, smartphone survey) and passive monitoring of behavioral activity (ie, passive data collection via embedded smartphone sensors). The development process of YouXin utilized a systematic coproduction approach. A series of coproduction consultation meetings was conducted by the principal researcher with service users and clinicians to maximize the usability and acceptability of the app for end users. Participants with psychosis aged 16 years to 65 years were recruited from Beijing Anding Hospital, Beijing, China. All participants were invited to use the YouXin app to self-monitor symptoms for 4 weeks. At the end of the 4-week follow-up, we invited participants to take part in a qualitative interview to explore the acceptability of the app and trial procedures postintervention.

RESULTS

Recruitment to the study was initiated in August 2022. Of the 47 participants who were approached for the study from August 2022 to October 2022, 41 participants agreed to take part in the study. We excluded 1 of the 41 participants for not meeting the inclusion criteria, leaving a total of 40 participants who began the study. As of December 2022, 40 participants had completed the study, and the recruitment was complete.

CONCLUSIONS

This study is the first to develop and test a symptom self-monitoring app specifically designed for people with psychosis in China. If the study shows the feasibility of YouXin, a potential future direction is to integrate the app into clinical workflows to facilitate digital mental health care for people with psychosis in China. This study will inform improvements to the app, trial procedures, and implementation strategies with this population. Moreover, the findings of this trial could lead to optimization of digital health technologies designed for people with psychosis in China.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/45170.

The Effects of Adopting Mobile Health and Fitness Apps on Hospital Visits: Quasi-Experimental Study

BACKGROUND

Overcrowding in public hospitals, a common issue in many countries, leads to a range of negative outcomes, such as insufficient access to medical services and patient dissatisfaction. Prior literature regarding solutions to reducing hospital overcrowding primarily focuses on organizational-level operational efficiency. However, few studies have investigated the strategies from the individual patient perspective. Specifically, we considered using mobile health and fitness apps to promote users' health behaviors and produce health benefits, thereby reducing hospital visits.

OBJECTIVE

This study estimated the causal effect of health and fitness app adoption on hospital visits by exploiting the staggered timing of adoption. We also investigated how the effect varied with users' socioeconomic status and digital literacy. This study provides causal evidence for the effects of health apps, extends the digital health literature, and sheds light on mobile health policies.

METHODS

This study used a data set containing health and fitness app use and hospital-related geolocation data of 267,651 Chinese mobile phone users from January to December 2019. We used the difference-in-differences and difference-in-difference-in-differences designs to estimate the causal effect. We performed a sensitivity analysis to establish the robustness of the findings. We also conducted heterogeneity analyses based on the interactions of postadoption indicators with users' consumption levels, city tiers, and digital literacy.

RESULTS

The preferred model (difference-in-difference-in-differences) showed a significant decrease in hospital visits after the adoption of health and fitness apps. App adoption led to a 5.8% (P<.001), 13.1% (P<.001), and 18.4% reduction (P<.001) in hospital visits 1, 2, and 3 months after adoption, respectively. In addition, the moderation analysis shows that the effect is greater for users with high consumption levels, in high-tier cities, or with high digital literacy.

CONCLUSIONS

This study estimated the causal effect of health and fitness app adoption on hospital visits. The results and sensitivity analysis showed that app adoption can reduce users' hospital visits. The effect varies with users' consumption levels, city tiers, and digital literacy. These findings provide useful insights for multiple stakeholders in the Chinese health care context.

Wearable and Mobile Technologies for the Evaluation and Treatment of Obsessive-Compulsive Disorder: Scoping Review

BACKGROUND

Smartphones and wearable biosensors can continuously and passively measure aspects of behavior and physiology while also collecting data that require user input. These devices can potentially be used to monitor symptom burden; estimate diagnosis and risk for relapse; predict treatment response; and deliver digital interventions in patients with obsessive-compulsive disorder (OCD), a prevalent and disabling psychiatric condition that often follows a chronic and fluctuating course and may uniquely benefit from these technologies.

OBJECTIVE

Given the speed at which mobile and wearable technologies are being developed and implemented in clinical settings, a continual reappraisal of this field is needed. In this scoping review, we map the literature on the use of wearable devices and smartphone-based devices or apps in the assessment, monitoring, or treatment of OCD.

METHODS

In July 2022 and April 2023, we conducted an initial search and an updated search, respectively, of multiple databases, including PubMed, Embase, APA PsycINFO, and Web of Science, with no restriction on publication period, using the following search strategy: ("OCD" OR "obsessive" OR "obsessive-compulsive") AND ("smartphone" OR "phone" OR "wearable" OR "sensing" OR "biofeedback" OR "neurofeedback" OR "neuro feedback" OR "digital" OR "phenotyping" OR "mobile" OR "heart rate variability" OR "actigraphy" OR "actimetry" OR "biosignals" OR "biomarker" OR "signals" OR "mobile health").

RESULTS

We analyzed 2748 articles, reviewed the full text of 77 articles, and extracted data from the 25 articles included in this review. We divided our review into the following three parts: studies without digital or mobile intervention and with passive data collection, studies without digital or mobile intervention and with active or mixed data collection, and studies with a digital or mobile intervention.

CONCLUSIONS

Use of mobile and wearable technologies for OCD has developed primarily in the past 15 years, with an increasing pace of related publications. Passive measures from actigraphy generally match subjective reports. Ecological momentary assessment is well tolerated for the naturalistic assessment of symptoms, may capture novel OCD symptoms, and may also document lower symptom burden than retrospective recall. Digital or mobile treatments are diverse; however, they generally provide some improvement in OCD symptom burden. Finally, ongoing work is needed for a safe and trusted uptake of technology by patients and providers.

Machine Learning Techniques for Developing Remotely Monitored Central Nervous System Biomarkers Using Wearable Sensors: A Narrative Literature Review

BACKGROUND

Central nervous system (CNS) disorders benefit from ongoing monitoring to assess disease progression and treatment efficacy. Mobile health (mHealth) technologies offer a means for the remote and continuous symptom monitoring of patients. Machine Learning (ML) techniques can process and engineer mHealth data into a precise and multidimensional biomarker of disease activity.

OBJECTIVE

This narrative literature review aims to provide an overview of the current landscape of biomarker development using mHealth technologies and ML. Additionally, it proposes recommendations to ensure the accuracy, reliability, and interpretability of these biomarkers.

METHODS

This review extracted relevant publications from databases such as PubMed, IEEE, and CTTI. The ML methods employed across the selected publications were then extracted, aggregated, and reviewed.

RESULTS

This review synthesized and presented the diverse approaches of 66 publications that address creating mHealth-based biomarkers using ML. The reviewed publications provide a foundation for effective biomarker development and offer recommendations for creating representative, reproducible, and interpretable biomarkers for future clinical trials.

CONCLUSION

mHealth-based and ML-derived biomarkers have great potential for the remote monitoring of CNS disorders. However, further research and standardization of study designs are needed to advance this field. With continued innovation, mHealth-based biomarkers hold promise for improving the monitoring of CNS disorders.

Predictors of adherence to electronic self-monitoring in patients with bipolar disorder: a contactless study using Growth Mixture Models

BACKGROUND

Several studies have reported on the feasibility of electronic (e-)monitoring using computers or smartphones in patients with mental disorders, including bipolar disorder (BD). While studies on e-monitoring have examined the role of demographic factors, such as age, gender, or socioeconomic status and use of health apps, to our knowledge, no study has examined clinical characteristics that might impact adherence with e-monitoring in patients with BD. We analyzed adherence to e-monitoring in patients with BD who participated in an ongoing e-monitoring study and evaluated whether demographic and clinical factors would predict adherence.

METHODS

Eighty-seven participants with BD in different phases of the illness were included. Patterns of adherence for wearable use, daily and weekly self-rating scales over 15 months were analyzed to identify adherence trajectories using growth mixture models (GMM). Multinomial logistic regression models were fitted to compute the effects of predictors on GMM classes.

RESULTS

Overall adherence rates were 79.5% for the wearable; 78.5% for weekly self-ratings; and 74.6% for daily self-ratings. GMM identified three latent class subgroups: participants with (i) perfect; (ii) good; and (iii) poor adherence. On average, 34.4% of participants showed "perfect" adherence; 37.1% showed "good" adherence; and 28.2% showed poor adherence to all three measures. Women, participants with a history of suicide attempt, and those with a history of inpatient admission were more likely to belong to the group with perfect adherence.

CONCLUSIONS

Participants with higher illness burden (e.g., history of admission to hospital, history of suicide attempts) have higher adherence rates to e-monitoring. They might see e-monitoring as a tool for better documenting symptom change and better managing their illness, thus motivating their engagement.

Patient preferences for key drivers and facilitators of adoption of mHealth technology to manage depression: A discrete choice experiment

BACKGROUND

In time, we may be able to detect the early onset of symptoms of depression and even predict relapse using behavioural data gathered through mobile technologies. However, barriers to adoption exist and understanding the importance of these factors to users is vital to ensure maximum adoption.

METHOD

In a discrete choice experiment, people with a history of depression (N = 171) were asked to select their preferred technology from a series of vignettes containing four characteristics: privacy, clinical support, established benefit and device accuracy (i.e., ability to detect symptoms), with different levels. Mixed logit models were used to establish what was most likely to affect adoption. Sub-group analyses explored effects of age, gender, education, technology acceptance and familiarity, and nationality.

RESULTS

Higher level of privacy, greater clinical support, increased perceived benefit and better device accuracy were important. Accuracy was the most important, with only modest compromises willing to be made to increase other factors such as privacy. Established benefit was the least valued of the attributes with participants happy with technology that had possible but unknown benefits. Preferences were moderated by technology acceptance, age, nationality, and educational background.

CONCLUSION

For people with a history of depression, adoption of technology may be driven by the desire for accurate detection of symptoms. However, people with lower technology acceptance and educational attainment, those who were younger, and specific nationalities may be willing to compromise on some accuracy for more privacy and clinical support. These preferences should help shape design of mHealth tools.

Smartwatch digital phenotypes predict positive and negative symptom variation in a longitudinal monitoring study of patients with psychotic disorders

Introduction

Monitoring biometric data using smartwatches (digital phenotypes) provides a novel approach for quantifying behavior in patients with psychiatric disorders. We tested whether such digital phenotypes predict changes in psychopathology of patients with psychotic disorders.

Methods

We continuously monitored digital phenotypes from 35 patients (20 with schizophrenia and 15 with bipolar spectrum disorders) using a commercial smartwatch for a period of up to 14 months. These included 5-min measures of total motor activity from an accelerometer (TMA), average Heart Rate (HRA) and heart rate variability (HRV) from a plethysmography-based sensor, walking activity (WA) measured as number of total steps per day and sleep/wake ratio (SWR). A self-reporting questionnaire (IPAQ) assessed weekly physical activity. After pooling phenotype data, their monthly mean and variance was correlated within each patient with psychopathology scores (PANSS) assessed monthly.

Results

Our results indicate that increased HRA during wakefulness and sleep correlated with increases in positive psychopathology. Besides, decreased HRV and increase in its monthly variance correlated with increases in negative psychopathology. Self-reported physical activity did not correlate with changes in psychopathology. These effects were independent from demographic and clinical variables as well as changes in antipsychotic medication dose.

Discussion

Our findings suggest that distinct digital phenotypes derived passively from a smartwatch can predict variations in positive and negative dimensions of psychopathology of patients with psychotic disorders, over time, providing ground evidence for their potential clinical use.

A novel multi-modal depression detection approach based on mobile crowd sensing and task-based mechanisms

Depression has become a global concern, and COVID-19 also has caused a big surge in its incidence. Broadly, there are two primary methods of detecting depression: Task-based and Mobile Crowd Sensing (MCS) based methods. These two approaches, when integrated, can complement each other. This paper proposes a novel approach for depression detection that combines real-time MCS and task-based mechanisms. We aim to design an end-to-end machine learning pipeline, which involves multimodal data collection, feature extraction, feature selection, fusion, and classification to distinguish between depressed and non-depressed subjects. For this purpose, we created a real-world dataset of depressed and non-depressed subjects. We experimented with: various features from multi-modalities, feature selection techniques, fused features, and machine learning classifiers such as Logistic Regression, Support Vector Machines (SVM), etc. for classification. Our findings suggest that combining features from multiple modalities perform better than any single data modality, and the best classification accuracy is achieved when features from all three data modalities are fused. Feature selection method based on Pearson's correlation coefficients improved the accuracy in comparison with other methods. Also, SVM yielded the best accuracy of 86%. Our proposed approach was also applied on benchmarking dataset, and results demonstrated that the multimodal approach is advantageous in performance with state-of-the-art depression recognition techniques.

An Extended Review Concerning the Relevance of Deep Learning and Privacy Techniques for Data-Driven Soft Sensors

The continuously increasing number of mobile devices actively being used in the world amounted to approximately 6.8 billion by 2022. Consequently, this implies a substantial increase in the amount of personal data collected, transported, processed, and stored. The authors of this paper designed and implemented an integrated personal health data management system, which considers data-driven software and hardware sensors, comprehensive data privacy techniques, and machine-learning-based algorithmic models. It was determined that there are very few relevant and complete surveys concerning this specific problem. Therefore, the current scientific research was considered, and this paper comprehensively analyzes the importance of deep learning techniques that are applied to the overall management of data collected by data-driven soft sensors. This survey considers aspects that are related to demographics, health and body parameters, and human activity and behaviour pattern detection. Additionally, the relatively complex problem of designing and implementing data privacy mechanisms, while ensuring efficient data access, is also discussed, and the relevant metrics are presented. The paper concludes by presenting the most important open research questions and challenges. The paper provides a comprehensive and thorough scientific literature survey, which is useful for any researcher or practitioner in the scope of data-driven soft sensors and privacy techniques, in relation to the relevant machine-learning-based models.

Modern views of machine learning for precision psychiatry

In light of the National Institute of Mental Health (NIMH)'s Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and diagnosis of mental disorders. Machine learning (ML) and artificial intelligence (AI) technologies are playing an increasingly critical role in the new era of precision psychiatry. Combining ML/AI with neuromodulation technologies can potentially provide explainable solutions in clinical practice and effective therapeutic treatment. Advanced wearable and mobile technologies also call for the new role of ML/AI for digital phenotyping in mobile mental health. In this review, we provide a comprehensive review of ML methodologies and applications by combining neuroimaging, neuromodulation, and advanced mobile technologies in psychiatry practice. We further review the role of ML in molecular phenotyping and cross-species biomarker identification in precision psychiatry. We also discuss explainable AI (XAI) and neuromodulation in a closed human-in-the-loop manner and highlight the ML potential in multi-media information extraction and multi-modal data fusion. Finally, we discuss conceptual and practical challenges in precision psychiatry and highlight ML opportunities in future research.

Passive Mobile Self-tracking of Mental Health by Veterans With Serious Mental Illness: Protocol for a User-Centered Design and Prospective Cohort Study

BACKGROUND

Serious mental illnesses (SMI) are common, disabling, and challenging to treat, requiring years of monitoring and treatment adjustments. Stress or reduced medication adherence can lead to rapid worsening of symptoms and behaviors. Illness exacerbations and relapses generally occur with little or no clinician awareness in real time, leaving limited opportunity to modify treatments. Previous research suggests that passive mobile sensing may be beneficial for individuals with SMI by helping them monitor mental health status and behaviors, and quickly detect worsening mental health for prompt assessment and intervention. However, there is too little research on its feasibility and acceptability and the extent to which passive data can predict changes in behaviors or symptoms.

OBJECTIVE

The aim of this research is to study the feasibility, acceptability, and safety of passive mobile sensing for tracking behaviors and symptoms of patients in treatment for SMI, as well as developing analytics that use passive data to predict changes in behaviors and symptoms.

METHODS

A mobile app monitors and transmits passive mobile sensor and phone utilization data, which is used to track activity, sociability, and sleep in patients with SMI. The study consists of a user-centered design phase and a mobile sensing phase. In the design phase, focus groups, interviews, and usability testing inform further app development. In the mobile sensing phase, passive mobile sensing occurs with participants engaging in weekly assessments for 9 months. Three- and nine-month interviews study the perceptions of passive mobile sensing and ease of app use. Clinician interviews before and after the mobile sensing phase study the usefulness and feasibility of app utilization in clinical care. Predictive analytic models are built, trained, and selected, and make use of machine learning methods. Models use sensor and phone utilization data to predict behavioral changes and symptoms.

RESULTS

The study started in October 2020. It has received institutional review board approval. The user-centered design phase, consisting of focus groups, usability testing, and preintervention clinician interviews, was completed in June 2021. Recruitment and enrollment for the mobile sensing phase began in October 2021.

CONCLUSIONS

Findings may inform the development of passive sensing apps and self-tracking in patients with SMI, and integration into care to improve assessment, treatment, and patient outcomes.

TRIAL REGISTRATION

ClinicalTrials.gov NCT05023252; https://clinicaltrials.gov/ct2/show/NCT05023252.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/39010.

Detecting and Responding to Information Overload With an Adaptive User Interface

OBJECTIVE

The objective of this study was to develop and evaluate an adaptive user interface that could detect states of operator information overload and calibrate the amount of information on the screen.

BACKGROUND

Machine learning can detect changes in operating context and trigger adaptive user interfaces (AUIs) to accommodate those changes. Operator attentional state represents a promising aspect of operating context for triggering AUIs. Behavioral rather than physiological indices can be used to infer operator attentional state.

METHOD

In Experiment 1, a network analysis task sought to induce states of information overload relative to a baseline. Streams of interaction data were taken from these two states and used to train machine learning classifiers. We implemented these classifiers in Experiment 2 to drive an AUI that automatically calibrated the amount of information displayed to operators.

RESULTS

Experiment 1 successfully induced information overload in participants, resulting in lower accuracy, slower completion time, and higher workload. A series of machine learning classifiers detected states of information overload significantly above chance level. Experiment 2 identified four clusters of users who responded significantly differently to the AUIs. The AUIs benefited performance, completion time, and workload in three clusters.

CONCLUSION

Behavioral indices can successfully detect states of information overload and be used to effectively drive an AUI for some user groups. The success of AUIs may be contingent on characteristics of the user group.

APPLICATION

This research applies to domains seeking real-time assessments of user attentional or psychological state.

Digital phenotyping in psychiatry: A scoping review

BACKGROUND

Digital phenotyping has been defined as the moment-by-moment assessment of an illness state through digital means, promising objective, quantifiable data on psychiatric patients' conditions, and could potentially improve diagnosis and management of mental illness. As it is a rapidly growing field, it is to be expected that new literature is being published frequently.

OBJECTIVE

We conducted this scoping review to assess the current state of literature on digital phenotyping and offer some discussion on the current trends and future direction of this area of research.

METHODS

We searched four databases, PubMed, Ovid MEDLINE, PsycINFO and Web of Science, from inception to August 25th, 2021. We included studies written in English that 1) investigated or applied their findings to diagnose psychiatric disorders and 2) utilized passive sensing for management or diagnosis. Protocols were excluded. A narrative synthesis approach was used, due to the heterogeneity and variability in outcomes and outcome types reported.

RESULTS

Of 10506 unique records identified, we included a total of 107 articles. The number of published studies has increased over tenfold from 2 in 2014 to 28 in 2020, illustrating the field's rapid growth. However, a significant proportion of these (49% of all studies and 87% of primary studies) were proof of concept, pilot or correlational studies examining digital phenotyping's potential. Most (62%) of the primary studies published evaluated individuals with depression (21%), BD (18%) and SZ (23%) (Appendix 1).

CONCLUSION

There is promise shown in certain domains of data and their clinical relevance, which have yet to be fully elucidated. A consensus has yet to be reached on the best methods of data collection and processing, and more multidisciplinary collaboration between physicians and other fields is needed to unlock the full potential of digital phenotyping and allow for statistically powerful clinical trials to prove clinical utility.

Associations among smartphone app-based measurements of mood, sleep and activity in bipolar disorder

The recent popularization of smart technology presents new opportunities for continual, digital-monitoring of patient status. In this project, we used a smartphone app to track the mood, sleep, and activity levels of 159 outpatients with bipolar disorder (BD). The participants were asked to report their daily wake/sleep time and emotional status in the app, while daily activity data were automatically collected via GPS. We performed repeated-measures correlation analysis to examine possible correlations between the readouts. Mood, sleep and activity levels all showed intra-variable correlations with readings on the next day, in the next week, and in the next month. Furthermore, mood and sleep at the reference time were positively correlated with activity in subsequent weeks or months, and activity was positively correlated with mood and sleep in the same time ranges. Thus, our results were in line with previous studies, showing that mood, sleep, and activity levels are interdependent in patients with BD. With the association between mood on future activity level was most significant, and the correlations between each readout and the others were dependent on time frame. Our findings suggest our smartphone app has potential to provide an informative and reliable means for real-time tracking of BD status.

Digital phenotyping in depression diagnostics: Integrating psychiatric and engineering perspectives

Depression is a serious medical condition and is a leading cause of disability worldwide. Current depression diagnostics and assessment has significant limitations due to heterogeneity of clinical presentations, lack of objective assessments, and assessments that rely on patients' perceptions, memory, and recall. Digital phenotyping (DP), especially assessments conducted using mobile health technologies, has the potential to greatly improve accuracy of depression diagnostics by generating objectively measurable endophenotypes. DP includes two primary sources of digital data generated using ecological momentary assessments (EMA), assessments conducted in real-time, in subjects' natural environment. This includes active EMA, data that require active input by the subject, and passive EMA or passive sensing, data passively and automatically collected from subjects' personal digital devices. The raw data is then analyzed using machine learning algorithms to identify behavioral patterns that correlate with patients' clinical status. Preliminary investigations have also shown that linguistic and behavioral clues from social media data and data extracted from the electronic medical records can be used to predict depression status. These other sources of data and recent advances in telepsychiatry can further enhance DP of the depressed patients. Success of DP endeavors depends on critical contributions from both psychiatric and engineering disciplines. The current review integrates important perspectives from both disciplines and discusses parameters for successful interdisciplinary collaborations. A clinically-relevant model for incorporating DP in clinical setting is presented. This model, based on investigations conducted by our group, delineates development of a depression prediction system and its integration in clinical setting to enhance depression diagnostics and inform the clinical decision making process. Benefits, challenges, and opportunities pertaining to clinical integration of DP of depression diagnostics are discussed from interdisciplinary perspectives.

Financial technologies (FinTech) for mental health: The potential of objective financial data to better understand the relationships between financial behavior and mental health

Financial stability is a key challenge for individuals with mental illnesses. Symptomatic periods often manifest in poor financial decision-making including compulsive spending and risky behaviors. This article explores research opportunities and challenges in developing financial technologies (FinTech) to support individuals with mental health. Specifically, we focus on how objective financial data might lead to novel mental health assessment and intervention methods. We have used data from one individual with bipolar disorder (BD) (i.e., an N = 1 case study) to illustrate feasibility of collecting and analyzing objective financial data alongside mental health factors. While we have not found statistically significant trends nor our findings are generalizable beyond this case, our approach provides an insight into the potential of using objective financial data to identify early warning signs and thereby, enable preemptive care for individuals with serious mental illnesses. We have also identified challenges of accessing objective financial data. The paper outlines what data is currently available, what can be done with it, and what factors to consider when working with financial data. We have also explored future directions for developing interventions to support financial well-being and stability. Furthermore, we have described the technical, ethical, and equity challenges for financial data-driven assessments and intervention methods, as well as provided a broad research agenda to address these challenges.

The Extent of User Involvement in the Design of Self-tracking Technology for Bipolar Disorder: Literature Review

BACKGROUND

The number of self-monitoring apps for bipolar disorder (BD) is increasing. The involvement of users in human-computer interaction (HCI) research has a long history and is becoming a core concern for designers working in this space. The application of models of involvement, such as user-centered design, is becoming standardized to optimize the reach, adoption, and sustained use of this type of technology.

OBJECTIVE

This paper aims to examine the current ways in which users are involved in the design and evaluation of self-monitoring apps for BD by investigating 3 specific questions: are users involved in the design and evaluation of technology? If so, how does this happen? And what are the best practice ingredients regarding the design of mental health technology?

METHODS

We reviewed the available literature on self-tracking technology for BD and make an overall assessment of the level of user involvement in design. The findings were reviewed by an expert panel, including an individual with lived experience of BD, to form best practice ingredients for the design of mental health technology. This combines the existing practices of patient and public involvement and HCI to evolve from the generic guidelines of user-centered design and to those that are tailored toward mental health technology.

RESULTS

For the first question, it was found that out of the 11 novel smartphone apps included in this review, 4 (36%) self-monitoring apps were classified as having no mention of user involvement in design, 1 (9%) self-monitoring app was classified as having low user involvement, 4 (36%) self-monitoring apps were classified as having medium user involvement, and 2 (18%) self-monitoring apps were classified as having high user involvement. For the second question, it was found that despite the presence of extant approaches for the involvement of the user in the process of design and evaluation, there is large variability in whether the user is involved, how they are involved, and to what extent there is a reported emphasis on the voice of the user, which is the ultimate aim of such design approaches. For the third question, it is recommended that users are involved in all stages of design with the ultimate goal of empowering and creating empathy for the user.

CONCLUSIONS

Users should be involved early in the design process, and this should not just be limited to the design itself, but also to associated research ensuring end-to-end involvement. Communities in health care-based design and HCI design need to work together to increase awareness of the different methods available and to encourage the use and mixing of the methods as well as establish better mechanisms to reach the target user group. Future research using systematic literature search methods should explore this further.

Apps and gaps in bipolar disorder: A systematic review on electronic monitoring for episode prediction

BACKGROUND

Long-term clinical monitoring in bipolar disorder (BD) is an important therapeutic tool. The availability of smartphones and wearables has sparked the development of automated applications to remotely monitor patients. This systematic review focus on the current state of electronic (e-) monitoring for episode prediction in BD.

METHODS

We systematically reviewed the literature on e-monitoring for episode prediction in adult BD patients. The systematic review was done according to the guidelines for reporting of systematic reviews and meta-analyses (PRISMA) and was registered in PROSPERO on April 29, 2020 (CRD42020155795). We conducted a search of Web of Science, MEDLINE, EMBASE, and PsycINFO (all 2000-2020) databases. We identified and extracted data from 17 published reports on 15 relevant studies.

RESULTS

Studies were heterogeneous and most had substantial methodological and technical limitations. Models varied widely in their performance. Published metrics were too heterogeneous to lend themselves to a meta-analysis. Four studies reported sensitivity (range: 0.21 - 0.95); and two reported specificity for prediction of mood episodes (range: 0.36 - 0.99). Two studies reported accuracy (range: 0.64 - 0.88) and four reported area under the curve (AUC; range: 0.52-0.95). Overall, models were better in predicting manic or hypomanic episodes, but their performance depended on feature type.

LIMITATIONS

Our conclusions are tempered by the lack of appropriate information impeding our ability to synthesize the available evidence.

CONCLUSIONS

Given the clinical variability in BD, predicting mood episodes remains a challenging task. Emerging e-monitoring technology for episode prediction in BD requires more development before it can be adopted clinically.

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.

[Symptom Monitoring and Detection of Early Warning Signs in Bipolar Episodes Via App - Views of Patients and Relatives on e-Health Need]

BACKGROUND

The onset and early warning signs of episodes of bipolar disorder are often realized late by those affected. The earlier an incipient episode is treated, the more prognostically favorable the course will be. Symptom monitoring via smartphone application (app) could be an innovative way to recognize and react to early warning signs more swiftly. The aim of this study was to find out whether patients and their relatives consider technical support through an app to be useful and practical in the early warning sign detection and treatment.

METHODS

In the present study, 51 patients with bipolar disorder and 28 relatives were interviewed. We gathered information on whether participants were able to perceive early warning signs in form of behavioral changes sufficiently and in a timely fashion and also whether they would use an app as treatment support tool.

RESULTS

Although 94.1% of the surveyed patients and 78.6% of their relatives felt that they were well informed about the disease, 13.7% and 35.7%, respectively were not fully satisfied with the current treatment options. Early warning signs of every depressive development were noticed by 25.5% of the patients (relatives 10.7%). Every (hypo)manic development was only noticed by 11.8% of the patients (relatives 7.1%); 88.2% of the patients and 85.7% of the relatives noticed the same symptoms recurrently at the beginning of a depression and 70.6% and 67.9%, respectively, at the beginning of a (hypo)manic episode (in particular changes in physical activity, communication behavior and the sleep-wake rhythm). 84.3% of the patients and 89.3% of the relatives stated that they considered technical support that draws attention to mood and activity changes as useful and that they would use such an app for the treatment.

DISCUSSION

The current options for perceiving early warning signs of a depressive or (hypo)manic episode in bipolar disorder are clinically inadequate. Those affected and their relatives desire innovative, technical support. Early detection of symptoms, which often manifest themselves in changes in behavior or activity patterns, is essentiell for managing the course of bipolar disorder. In the future, smartphone apps could be used for clinical treatment and research through objective, continuous and.

Fusing Location Data for Depression Prediction

Recent studies have demonstrated that geographic location features collected using smartphones can be a powerful predictor for depression. While location information can be conveniently gathered by GPS, typical datasets suffer from significant periods of missing data due to various factors (e.g., phone power dynamics, limitations of GPS). A common approach is to remove the time periods with significant missing data before data analysis. In this paper, we develop an approach that fuses location data collected from two sources: GPS and WiFi association records, on smartphones, and evaluate its performance using a dataset collected from 79 college students. Our evaluation demonstrates that our data fusion approach leads to significantly more complete data. In addition, the features extracted from the more complete data present stronger correlation with self-report depression scores, and lead to depression prediction with much higher F ₁ scores (up to 0.76 compared to 0.5 before data fusion). We further investigate the scenerio when including an additional data source, i.e., the data collected from a WiFi network infrastructure. Our results show that, while the additional data source leads to even more complete data, the resultant F ₁ scores are similar to those when only using the location data (i.e., GPS and WiFi association records) from the phones.

"Psyosphere": A GPS Data-Analysing Tool for the Behavioural Sciences

Positioning technologies, such as GPS are widespread in society but are used only sparingly in behavioural science research, e.g., because processing positioning technology data can be cumbersome. The current work attempts to unlock positioning technology potential for behavioural science studies by developing and testing a research tool to analyse GPS tracks. This tool—psyosphere—is published as open-source software, and aims to extract behaviours from GPSs data that are more germane to behavioural research. Two field experiments were conducted to test application of the research tool. During these experiments, participants played a smuggling game, thereby either smuggling tokens representing illicit material past border guards or not. Results suggested that participants varied widely in variables, such as course and speed variability and distance from team members in response to the presence of border guards. Subsequent analyses showed that some of these GPS-derived behavioural variables could be linked to self-reported mental states, such as fear. Although more work needs to be done, the current study demonstrates that psyosphere may enable researchers to conduct behavioural experiments with positioning technology, outside of a laboratory setting.

Potential Applications of Mobile and Wearable Devices for Psychological Support During the COVID-19 Pandemic: A Review

The coronavirus disease 19 (COVID-19) pandemic that has been raging in 2020 does affect not only the physical state but also the mental health of the general population, particularly, that of the healthcare workers. Given the unprecedented large-scale impacts of the COVID-19 pandemic, digital technology has gained momentum as invaluable social interaction and health tracking tools in this time of great turmoil, in part due to the imposed state-wide mobilization limitations to mitigate the risk of infection that might arise from in-person socialization or hospitalization. Over the last five years, there has been a notable increase in the demand and usage of mobile and wearable devices as well as their adoption in studies of mental fitness. The purposes of this scoping review are to summarize evidence on the sweeping impact of COVID-19 on mental health as well as to evaluate the merits of the devices for remote psychological support. We conclude that the COVID-19 pandemic has inflicted a significant toll on the mental health of the population, leading to an upsurge in reports of pathological stress, depression, anxiety, and insomnia. It is also clear that mobile and wearable devices (e.g., smartwatches and fitness trackers) are well placed for identifying and targeting individuals with these psychological burdens in need of intervention. However, we found that most of the previous studies used research-grade wearable devices that are difficult to afford for the normal consumer due to their high cost. Thus, the possibility of replacing the research-grade wearable devices with the current smartwatch is also discussed.

Digital biomarkers from geolocation data in bipolar disorder and schizophrenia: a systematic review

OBJECTIVE

The study sought to explore to what extent geolocation data has been used to study serious mental illness (SMI). SMIs such as bipolar disorder and schizophrenia are characterized by fluctuating symptoms and sudden relapse. Currently, monitoring of people with an SMI is largely done through face-to-face visits. Smartphone-based geolocation sensors create opportunities for continuous monitoring and early intervention.

MATERIALS AND METHODS

We searched MEDLINE, PsycINFO, and Scopus by combining terms related to geolocation and smartphones with SMI concepts. Study selection and data extraction were done in duplicate.

RESULTS

Eighteen publications describing 16 studies were included in our review. Eleven studies focused on bipolar disorder. Common geolocation-derived digital biomarkers were number of locations visited (n = 8), distance traveled (n = 8), time spent at prespecified locations (n = 7), and number of changes in GSM (Global System for Mobile communications) cell (n = 4). Twelve of 14 publications evaluating clinical aspects found an association between geolocation-derived digital biomarker and SMI concepts, especially mood. Geolocation-derived digital biomarkers were more strongly associated with SMI concepts than other information (eg, accelerometer data, smartphone activity, self-reported symptoms). However, small sample sizes and short follow-up warrant cautious interpretation of these findings: of all included studies, 7 had a sample of fewer than 10 patients and 11 had a duration shorter than 12 weeks.

CONCLUSIONS

The growing body of evidence for the association between SMI concepts and geolocation-derived digital biomarkers shows potential for this instrument to be used for continuous monitoring of patients in their everyday lives, but there is a need for larger studies with longer follow-up times.

Automatically Generated Smartphone Data in Young Patients With Newly Diagnosed Bipolar Disorder and Healthy Controls

Background: Smartphones may facilitate continuous and fine-grained monitoring of behavioral activities via automatically generated data and could prove to be especially valuable in monitoring illness activity in young patients with bipolar disorder (BD), who often present with rapid changes in mood and related symptoms. The present pilot study in young patients with newly diagnosed BD and healthy controls (HC) aimed to (1) validate automatically generated smartphone data reflecting physical and social activity and phone usage against validated clinical rating scales and questionnaires; (2) investigate differences in automatically generated smartphone data between young patients with newly diagnosed BD and HC; and (3) investigate associations between automatically generated smartphone data and smartphone-based self-monitored mood and activity in young patients with newly diagnosed BD. Methods: A total of 40 young patients with newly diagnosed BD and 21 HC aged 15-25 years provided daily automatically generated smartphone data for 3-779 days [median (IQR) = 140 (11.5-268.5)], in addition to daily smartphone-based self-monitoring of activity and mood. All participants were assessed with clinical rating scales. Results: (1) The number of outgoing phone calls was positively associated with scores on the Young Mania Rating Scale and subitems concerning activity and speech. The number of missed calls (p = 0.015) and the number of outgoing text messages (p = 0.017) were positively associated with the level of psychomotor agitation according to the Hamilton Depression Rating scale subitem 9. (2) Young patients with newly diagnosed BD had a higher number of incoming calls compared with HC (BD: mean = 1.419, 95% CI: 1.162, 1.677; HC: mean = 0.972, 95% CI: 0.637, 1.308; p = 0.043) and lower self-monitored mood and activity (p's < 0.001). (3) Smartphone-based self-monitored mood and activity were positively associated with step counts and the number of outgoing calls, respectively (p's < 0.001). Conclusion: Automatically generated data on physical and social activity and phone usage seem to reflect symptoms. These data differ between young patients with newly diagnosed BD and HC and reflect changes in illness activity in young patients with BD. Automatically generated smartphone-based data could be a useful clinical tool in diagnosing and monitoring illness activity in young patients with BD.

Digital Communication Biomarkers of Mood and Diagnosis in Borderline Personality Disorder, Bipolar Disorder, and Healthy Control Populations

Background: Remote monitoring and digital phenotyping harbor potential to aid clinical diagnosis, predict episode course and recognize early signs of mental health crises. Digital communication metrics, such as phone call and short message service (SMS) use may represent novel biomarkers of mood and diagnosis in Bipolar Disorder (BD) and Borderline Personality Disorder (BPD). Materials and Methods: BD (n = 17), BPD (n = 17) and Healthy Control (HC, n = 21) participants used a smartphone application which monitored phone calls and SMS messaging, alongside self-reported mood. Linear mixed-effects regression models were used to assess the association between digital communications and mood symptoms, mood state, trait-impulsivity, diagnosis and the interaction effect between mood and diagnosis. Results: Transdiagnostically, self-rated manic symptoms and manic state were positively associated with total and outgoing call frequency and cumulative total, incoming and outgoing call duration. Manic symptoms were also associated with total and outgoing SMS frequency. Transdiagnostic depressive symptoms were associated with increased mean incoming call duration. For the different diagnostic groups, BD was associated with increased total call frequency and BPD with increased total and outgoing SMS frequency and length compared to HC. Depression in BD, but not BPD, was associated with decreased total and outgoing call frequency, mean total and outgoing call duration and total and outgoing SMS frequency. Finally, trait-impulsivity was positively associated with total call frequency, total and outgoing SMS frequency and cumulative total and outgoing SMS length. Conclusion: These results identify a general increase in phone call and SMS communications associated with self-reported manic symptoms and a diagnosis-moderated decrease in communications associated with depression in BD, but not BPD, participants. These findings may inform the development of clinical tools to aid diagnosis and remote symptom monitoring, as well as informing understanding of differential psychopathologies in BD and BPD.

Screening for Depression in Mobile Devices Using Patient Health Questionnaire-9 (PHQ-9) Data: A Diagnostic Meta-Analysis via Machine Learning Methods

PURPOSE

Depression is a symptom commonly encountered in primary care; however, it is often not detected by doctors. Recently, disease diagnosis and treatment approaches have been attempted using smart devices. In this study, instrumental effectiveness was confirmed with the diagnostic meta-analysis of studies that demonstrated the diagnostic effectiveness of PHQ-9 for depression using mobile devices.

PATIENTS AND METHODS

We found all published and unpublished studies through EMBASE, MEDLINE, MEDLINE In-Process, and PsychINFO up to March 26, 2021. We performed a meta-analysis by including 1099 subjects in four studies. We performed a diagnostic meta-analysis according to the PHQ-9 cut-off score and machine learning algorithm techniques. Quality assessment was conducted using the QUADAS-2 tool. Data on the sensitivity and specificity of the studies included in the meta-analysis were extracted in a standardized format. Bivariate and summary receiver operating characteristic (SROC) curve were constructed using the metandi, midas, metabias, and metareg functions of the Stata algorithm meta-analysis words.

RESULTS

Using four studies out of the 5476 papers searched, a diagnostic meta-analysis of the PHQ-9 scores of 1099 people diagnosed with depression was performed. The pooled sensitivity and specificity were 0.797 (95% CI = 0.642-0.895) and 0.85 (95% CI = 0.780-0.900), respectively. The diagnostic odds ratio was 22.16 (95% CI = 7.273-67.499). Overall, a good balance was maintained, and no heterogeneity or publication bias was presented.

CONCLUSION

Through various machine learning algorithm techniques, it was possible to confirm that PHQ-9 depression screening in mobiles is an effective diagnostic tool when integrated into a diagnostic meta-analysis.

Digital phenotyping: towards replicable findings with comprehensive assessments and integrative models in bipolar disorders

Background

Digital phenotyping promises to unobtrusively obtaining a continuous and objective input of symptomatology from patients’ daily lives. The prime example are bipolar disorders, as smartphone parameters directly reflect bipolar symptomatology. Empirical studies, however, have yielded inconsistent findings. We believe that three main shortcomings have to be addressed to fully leverage the potential of digital phenotyping: short assessment periods, rare outcome assessments, and an extreme fragmentation of parameters without an integrative analytical strategy.

Methods

To demonstrate how to overcome these shortcomings, we conducted frequent (biweekly) dimensional and categorical expert ratings and daily self-ratings over an extensive assessment period (12 months) in 29 patients with bipolar disorder. Digital phenotypes were monitored continuously. As an integrative analytical strategy, we used structural equation modelling to build latent psychopathological outcomes (mania, depression) and latent digital phenotype predictors (sleep, activity, communicativeness).

Outcomes

Combining gold-standard categorical expert ratings with dimensional self and expert ratings resulted in two latent outcomes (mania and depression) with statistically meaningful factor loadings that dynamically varied over 299 days. Latent digital phenotypes of sleep and activity were associated with same-day latent manic psychopathology, suggesting that psychopathological alterations in bipolar disorders relate to domains (latent variables of sleep and activity) and not only to specific behaviors (such as the number of declined incoming calls). The identification of latent psychopathological outcomes that dimensionally vary on a daily basis will enable to empirically determine which combination of digital phenotypes at which days prior to an upcoming episode are viable as digital prodromal predictors.

Smartphone-based activity measurements in patients with newly diagnosed bipolar disorder, unaffected relatives and control individuals

BACKGROUND

In DSM-5 activity is a core criterion for diagnosing hypomania and mania. However, there are no guidelines for quantifying changes in activity. The objectives of the study were (1) to investigate daily smartphone-based self-reported and automatically-generated activity, respectively, against validated measurements of activity; (2) to validate daily smartphone-based self-reported activity and automatically-generated activity against each other; (3) to investigate differences in daily self-reported and automatically-generated smartphone-based activity between patients with bipolar disorder (BD), unaffected relatives (UR) and healthy control individuals (HC).

METHODS

A total of 203 patients with BD, 54 UR, and 109 HC were included. On a smartphone-based app, the participants daily reported their activity level on a scale from -3 to + 3. Additionally, participants owning an android smartphone provided automatically-generated data, including step counts, screen on/off logs, and call- and text-logs. Smartphone-based activity was validated against an activity questionnaire the International Physical Activity Questionnaire (IPAQ) and activity items on observer-based rating scales of depression using the Hamilton Depression Rating scale (HAMD), mania using Young Mania Rating scale (YMRS) and functioning using the Functional Assessment Short Test (FAST). In these analyses, we calculated averages of smartphone-based activity measurements reported in the period corresponding to the days assessed by the questionnaires and rating scales.

RESULTS

(1) Smartphone-based self-reported activity was a valid measure according to scores on the IPAQ and activity items on the HAMD and YMRS, and was associated with FAST scores, whereas the majority of automatically-generated smartphone-based activity measurements were not. (2) Daily smartphone-based self-reported and automatically-generated activity correlated with each other with nearly all measurements. (3) Patients with BD had decreased daily self-reported activity compared with HC. Patients with BD had decreased physical (number of steps) and social activity (more missed calls) but a longer call duration compared with HC. UR also had decreased physical activity compared with HC but did not differ on daily self-reported activity or social activity.

CONCLUSION

Daily self-reported activity measured via smartphone represents overall activity and correlates with measurements of automatically generated smartphone-based activity. Detecting activity levels using smartphones may be clinically helpful in diagnosis and illness monitoring in patients with bipolar disorder. Trial registration clinicaltrials.gov NCT02888262.

Automatic Depression Prediction Using Internet Traffic Characteristics on Smartphones

Depression is a serious mental health problem. Recently, researchers have proposed novel approaches that use sensing data collected passively on smartphones for automatic depression screening. While these studies have explored several types of sensing data (e.g., location, activity, conversation), none of them has leveraged Internet traffic of smartphones, which can be collected with little energy consumption and the data is insensitive to phone hardware. In this paper, we explore using coarse-grained meta-data of Internet traffic on smartphones for depression screening. We develop techniques to identify Internet usage sessions (i.e., time periods when a user is online) and extract a novel set of features based on usage sessions from the Internet traffic meta-data. Our results demonstrate that Internet usage features can reflect the different behavioral characteristics between depressed and non-depressed participants, confirming findings in psychological sciences, which have relied on surveys or questionnaires instead of real Internet traffic as in our study. Furthermore, we develop machine learning based prediction models that use these features to predict depression. Our evaluation shows that Internet usage features can be used for effective depression prediction, leading to F 1 score as high as 0.80.

Digital Phenotyping in Bipolar Disorder: Which Integration with Clinical Endophenotypes and Biomarkers?

Bipolar disorder (BD) is a complex neurobiological disorder characterized by a pathologic mood swing. Digital phenotyping, defined as the 'moment-by-moment quantification of the individual-level human phenotype in its own environment', represents a new approach aimed at measuring the human behavior and may theoretically enhance clinicians' capability in early identification, diagnosis, and management of any mental health conditions, including BD. Moreover, a digital phenotyping approach may easily introduce and allow clinicians to perform a more personalized and patient-tailored diagnostic and therapeutic approach, in line with the framework of precision psychiatry. The aim of the present paper is to investigate the role of digital phenotyping in BD. Despite scarce literature published so far, extremely heterogeneous methodological strategies, and limitations, digital phenotyping may represent a grounding research and clinical field in BD, by owning the potentialities to quickly identify, diagnose, longitudinally monitor, and evaluating clinical response and remission to psychotropic drugs. Finally, digital phenotyping might potentially constitute a possible predictive marker for mood disorders.

Classification of Attentional Tunneling Through Behavioral Indices

OBJECTIVE

The objective of this study was to develop a machine learning classifier to infer attentional tunneling through behavioral indices. This research serves as a proof of concept for a method for inferring operator state to trigger adaptations to user interfaces.

BACKGROUND

Adaptive user interfaces adapt their information content or configuration to changes in operating context. Operator attentional states represent a promising class of triggers for these adaptations. Behavioral indices may be a viable alternative to physiological correlates for triggering interface adaptations based on attentional state.

METHOD

A visual search task sought to induce attentional tunneling in participants. We analyzed user interaction under tunnel and non-tunnel conditions to determine whether the paradigm was successful. We then examined the performance trade-offs stemming from attentional tunnels. Finally, we developed a machine learning classifier to identify patterns of interaction characteristics associated with attentional tunnels.

RESULTS

The experimental paradigm successfully induced attentional tunnels. Attentional tunnels were shown to improve performance when information appeared within them, but to hinder performance when it appeared outside. Participants were found to be more tunneled in their second tunnel trial relative to their first. Our classifier achieved a classification accuracy similar to comparable studies (area under curve = 0.74).

CONCLUSION

Behavioral indices can be used to infer attentional tunneling. There is a performance trade-off from attentional tunneling, suggesting the opportunity for adaptive systems.

APPLICATION

This research applies to adaptive automation aimed at managing operator attention in information-dense work domains.

Ethical and Safety Concerns Regarding the Use of Mental Health-Related Apps in Counseling: Considerations for Counselors

Mental health-related smartphone apps (MHapps) have the potential to greatly enhance and enrich the counseling relationship, and dramatically improve the lives of clients. However, a large portion of MHapps have not been empirically researched and found to be effective. An average of 2 million apps are available in the Apple and Android stores, and users average more than 80 apps on their phones. Many of the apps lack disclaimers about the collection of user information, and there is no governing body to oversee and regulate app development and availability. This is particularly problematic with mental health-related smartphone apps, because many developers are not affiliated with mental health professionals, and many apps do not provide emergency information should a mental health emergency occur while using the app. Moreover, users are left to haphazardly make decisions about health-related apps usage without assistance. Counselors who supplement counseling with mental health-related smartphone apps could unknowingly violate their Code of Ethics by integrating apps that may jeopardize their clients' safety. The authors review literature related to mental health-related app efficacy, safety, and ethics and provide a compilation of items to consider that can be used before supplementing counseling with mental health-related apps.

Geolocation as a Digital Phenotyping Measure of Negative Symptoms and Functional Outcome

OBJECTIVE

Negative symptoms and functional outcome have traditionally been assessed using clinical rating scales, which rely on retrospective self-reports and have several inherent limitations that impact validity. These issues may be addressed with more objective digital phenotyping measures. In the current study, we evaluated the psychometric properties of a novel "passive" digital phenotyping method: geolocation.

METHOD

Participants included outpatients with schizophrenia or schizoaffective disorder (SZ: n = 44), outpatients with bipolar disorder (BD: n =19), and demographically matched healthy controls (CN: n = 42) who completed 6 days of "active" digital phenotyping assessments (eg, surveys) while geolocation was recorded.

RESULTS

Results indicated that SZ patients show less activity than CN and BD, particularly, in their travel from home. Geolocation variables demonstrated convergent validity by small to medium correlations with negative symptoms and functional outcome measured via clinical rating scales, as well as active digital phenotyping behavioral indices of avolition, asociality, and anhedonia. Discriminant validity was supported by low correlations with positive symptoms, depression, and anxiety. Reliability was supported by good internal consistency and moderate stability across days.

CONCLUSIONS

These findings provide preliminary support for the reliability and validity of geolocation as an objective measure of negative symptoms and functional outcome. Geolocation offers enhanced precision and the ability to take a "big data" approach that facilitates sophisticated computational models. Near-continuous recordings and large numbers of samples may make geolocation a novel outcome measure for clinical trials due to enhanced power to detect treatment effects.

A framework for assessing neuropsychiatric phenotypes by using smartphone-based location data

The use of smartphone-based location data to quantify behavior longitudinally and passively is rapidly gaining traction in neuropsychiatric research. However, a standardized and validated preprocessing framework for deriving behavioral phenotypes from smartphone-based location data is currently lacking. Here, we present a preprocessing framework consisting of methods that are validated in the context of geospatial data. This framework aims to generate context-enriched location data by identifying stationary, non-stationary, and recurrent stationary states in movement patterns. Subsequently, this context-enriched data is used to derive a series of behavioral phenotypes that are related to movement. By using smartphone-based location data collected from 245 subjects, including patients with schizophrenia, we show that the proposed framework is effective and accurate in generating context-enriched location data. This data was subsequently used to derive behavioral readouts that were sensitive in detecting behavioral nuances related to schizophrenia and aging, such as the time spent at home and the number of unique places visited. Overall, our results indicate that the proposed framework reliably preprocesses raw smartphone-based location data in such a manner that relevant behavioral phenotypes of interest can be derived.

Passive Sensing of Prediction of Moment-To-Moment Depressed Mood among Undergraduates with Clinical Levels of Depression Sample Using Smartphones

Prior research has recently shown that passively collected sensor data collected within the contexts of persons daily lives via smartphones and wearable sensors can distinguish those with major depressive disorder (MDD) from controls, predict MDD severity, and predict changes in MDD severity across days and weeks. Nevertheless, very little research has examined predicting depressed mood within a day, which is essential given the large amount of variation occurring within days. The current study utilized passively collected sensor data collected from a smartphone application to future depressed mood from hour-to-hour in an ecological momentary assessment study in a sample reporting clinical levels of depression (N = 31). Using a combination of nomothetic and idiographically-weighted machine learning models, the results suggest that depressed mood can be accurately predicted from hour to hour with an average correlation between out of sample predicted depressed mood levels and observed depressed mood of 0.587, CI [0.552, 0.621]. This suggests that passively collected smartphone data can accurately predict future depressed mood among a sample reporting clinical levels of depression. If replicated in other samples, this modeling framework may allow just-in-time adaptive interventions to treat depression as it changes in the context of daily life.

Why Loneliness Interventions Are Unsuccessful: A Call for Precision Health

Background

Loneliness has drawn increasing attention over the past few decades due to rising recognition of its close connection with serious health issues, like dementia. Yet, researchers are failing to find solutions to alleviate the globally experienced burden of loneliness.

Purpose

This review aims to shed light on possible reasons for why interventions have been ineffective. We suggest new directions for research on loneliness as it relates to precision health, emerging technologies, digital phenotyping, and machine learning.

Results

Current loneliness interventions are unsuccessful due to (i) their inconsideration of loneliness as a heterogeneous construct and (ii) not being targeted at individuals' needs and contexts. We propose a model for how loneliness interventions can move towards finding the right solution for the right person at the right time. Taking a precision health approach, we explore how transdisciplinary research can contribute to creating a more holistic picture of loneliness and shift interventions from treatment to prevention.

Conclusions

We urge the field to rethink metrics to account for diverse intra-individual experiences and trajectories of loneliness. Big data sharing and evolving technologies that emphasize human connection raise hope for realizing our model of precision health applied to loneliness. There is an urgent need for precise, integrated, and theory-driven interventions that focus on individuals' needs and the subjective burden of loneliness in the ageing context.

Objective Characterization of Activity, Sleep, and Circadian Rhythm Patterns Using a Wrist-Worn Actigraphy Sensor: Insights Into Posttraumatic Stress Disorder

BACKGROUND

Wearables have been gaining increasing momentum and have enormous potential to provide insights into daily life behaviors and longitudinal health monitoring. However, to date, there is still a lack of principled algorithmic framework to facilitate the analysis of actigraphy and objectively characterize day-by-day data patterns, particularly in cohorts with sleep problems.

OBJECTIVE

This study aimed to propose a principled algorithmic framework for the assessment of activity, sleep, and circadian rhythm patterns in people with posttraumatic stress disorder (PTSD), a mental disorder with long-lasting distressing symptoms such as intrusive memories, avoidance behaviors, and sleep disturbance. In clinical practice, these symptoms are typically assessed using retrospective self-reports that are prone to recall bias. The aim of this study was to develop objective measures from patients' everyday lives, which could potentially considerably enhance the understanding of symptoms, behaviors, and treatment effects.

METHODS

Using a wrist-worn sensor, we recorded actigraphy, light, and temperature data over 7 consecutive days from three groups: 42 people diagnosed with PTSD, 43 traumatized controls, and 30 nontraumatized controls. The participants also completed a daily sleep diary over 7 days and the standardized Pittsburgh Sleep Quality Index questionnaire. We developed a novel approach to automatically determine sleep onset and offset, which can also capture awakenings that are crucial for assessing sleep quality. Moreover, we introduced a new intuitive methodology facilitating actigraphy exploration and characterize day-by-day data across 49 activity, sleep, and circadian rhythm patterns.

RESULTS

We demonstrate that the new sleep detection algorithm closely matches the sleep onset and offset against the participants' sleep diaries consistently outperforming an existing open-access widely used approach. Participants with PTSD exhibited considerably more fragmented sleep patterns (as indicated by greater nocturnal activity, including awakenings) and greater intraday variability compared with traumatized and nontraumatized control groups, showing statistically significant (P<.05) and strong associations (|R|>0.3).

CONCLUSIONS

This study lays the foundation for objective assessment of activity, sleep, and circadian rhythm patterns using passively collected data from a wrist-worn sensor, facilitating large community studies to monitor longitudinally healthy and pathological cohorts under free-living conditions. These findings may be useful in clinical PTSD assessment and could inform therapy and monitoring of treatment effects.

Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data

Just-in-time adaptive interventions (JITAIs), typically smartphone apps, learn to deliver therapeutic content when users need it. The challenge is to "push" content at algorithmically chosen moments without making users trigger it with effortful input. We trained a randomForest algorithm to predict heroin craving, cocaine craving, or stress (reported via smartphone app 3x/day) 90 min into the future, using 16 weeks of field data from 189 outpatients being treated for opioid-use disorder. We used only one form of continuous input (along with person-level demographic data), collected passively: an indicator of environmental exposures along the past 5 h of movement, as assessed by GPS. Our models achieved excellent overall accuracy-as high as 0.93 by the end of 16 weeks of tailoring-but this was driven mostly by correct predictions of absence. For predictions of presence, "believability" (positive predictive value, PPV) usually peaked in the high 0.70s toward the end of the 16 weeks. When the prediction target was more rare, PPV was lower. Our findings complement those of other investigators who use machine learning with more broadly based "digital phenotyping" inputs to predict or detect mental and behavioral events. When target events are comparatively subtle, like stress or drug craving, accurate detection or prediction probably needs effortful input from users, not passive monitoring alone. We discuss ways in which accuracy is difficult to achieve or even assess, and warn that high overall accuracy (including high specificity) can mask the abundance of false alarms that low PPV reveals.