Evaluating depression with multimodal wristband-type wearable device: screening and assessing patient severity utilizing machine-learning

Automated mood disorder symptoms monitoring from multivariate time-series sensory data: getting the full picture beyond a single number

Mood disorders (MDs) are among the leading causes of disease burden worldwide. Limited specialized care availability remains a major bottleneck thus hindering pre-emptive interventions. MDs manifest with changes in mood, sleep, and motor activity, observable in ecological physiological recordings thanks to recent advances in wearable technology. Therefore, near-continuous and passive collection of physiological data from wearables in daily life, analyzable with machine learning (ML), could mitigate this problem, bringing MDs monitoring outside the clinician's office. Previous works predict a single label, either the disease state or a psychometric scale total score. However, clinical practice suggests that the same label may underlie different symptom profiles, requiring specific treatments. Here we bridge this gap by proposing a new task: inferring all items in HDRS and YMRS, the two most widely used standardized scales for assessing MDs symptoms, using physiological data from wearables. To that end, we develop a deep learning pipeline to score the symptoms of a large cohort of MD patients and show that agreement between predictions and assessments by an expert clinician is clinically significant (quadratic Cohen's κ and macro-average F1 score both of 0.609). While doing so, we investigate several solutions to the ML challenges associated with this task, including multi-task learning, class imbalance, ordinal target variables, and subject-invariant representations. Lastly, we illustrate the importance of testing on out-of-distribution samples.

The Role of Artificial Intelligence in Identifying Depression and Anxiety: A Comprehensive Literature Review

This narrative literature review undertakes a comprehensive examination of the burgeoning field, tracing the development of artificial intelligence (AI)-powered tools for depression and anxiety detection from the level of intricate algorithms to practical applications. Delivering essential mental health care services is now a significant public health priority. In recent years, AI has become a game-changer in the early identification and intervention of these pervasive mental health disorders. AI tools can potentially empower behavioral healthcare services by helping psychiatrists collect objective data on patients' progress and tasks. This study emphasizes the current understanding of AI, the different types of AI, its current use in multiple mental health disorders, advantages, disadvantages, and future potentials. As technology develops and the digitalization of the modern era increases, there will be a rise in the application of artificial intelligence in psychiatry; therefore, a comprehensive understanding will be needed. We searched PubMed, Google Scholar, and Science Direct using keywords for this. In a recent review of studies using electronic health records (EHR) with AI and machine learning techniques for diagnosing all clinical conditions, roughly 99 publications have been found. Out of these, 35 studies were identified for mental health disorders in all age groups, and among them, six studies utilized EHR data sources. By critically analyzing prominent scholarly works, we aim to illuminate the current state of this technology, exploring its successes, limitations, and future directions. In doing so, we hope to contribute to a nuanced understanding of AI's potential to revolutionize mental health diagnostics and pave the way for further research and development in this critically important domain.

Towards Personalised Mood Prediction and Explanation for Depression from Biophysical Data

Digital health applications using Artificial Intelligence (AI) are a promising opportunity to address the widening gap between available resources and mental health needs globally. Increasingly, passively acquired data from wearables are augmented with carefully selected active data from depressed individuals to develop Machine Learning (ML) models of depression based on mood scores. However, most ML models are black box in nature, and hence the outputs are not explainable. Depression is also multimodal, and the reasons for depression may vary significantly between individuals. Explainable and personalised models will thus be beneficial to clinicians to determine the main features that lead to a decline in the mood state of a depressed individual, thus enabling suitable personalised therapy. This is currently lacking. Therefore, this study presents a methodology for developing personalised and accurate Deep Learning (DL)-based predictive mood models for depression, along with novel methods for identifying the key facets that lead to the exacerbation of depressive symptoms. We illustrate our approach by using an existing multimodal dataset containing longitudinal Ecological Momentary Assessments of depression, lifestyle data from wearables and neurocognitive assessments for 14 mild to moderately depressed participants over one month. We develop classification- and regression-based DL models to predict participants' current mood scores-a discrete score given to a participant based on the severity of their depressive symptoms. The models are trained inside eight different evolutionary-algorithm-based optimisation schemes that optimise the model parameters for a maximum predictive performance. A five-fold cross-validation scheme is used to verify the DL model's predictive performance against 10 classical ML-based models, with a model error as low as 6% for some participants. We use the best model from the optimisation process to extract indicators, using SHAP, ALE and Anchors from explainable AI literature to explain why certain predictions are made and how they affect mood. These feature insights can assist health professionals in incorporating personalised interventions into a depressed individual's treatment regimen.

Prediction of Diagnosis and Treatment Response in Adolescents With Depression by Using a Smartphone App and Deep Learning Approaches: Usability Study

BACKGROUND

Lack of quantifiable biomarkers is a major obstacle in diagnosing and treating depression. In adolescents, increasing suicidality during antidepressant treatment further complicates the problem.

OBJECTIVE

We sought to evaluate digital biomarkers for the diagnosis and treatment response of depression in adolescents through a newly developed smartphone app.

METHODS

We developed the Smart Healthcare System for Teens At Risk for Depression and Suicide app for Android-based smartphones. This app passively collected data reflecting the social and behavioral activities of adolescents, such as their smartphone usage time, physical movement distance, and the number of phone calls and text messages during the study period. Our study consisted of 24 adolescents (mean age 15.4 [SD 1.4] years, 17 girls) with major depressive disorder (MDD) diagnosed with Kiddie Schedule for Affective Disorders and Schizophrenia for School-Age Children-Present and Lifetime Version and 10 healthy controls (mean age 13.8 [SD 0.6] years, 5 girls). After 1 week's baseline data collection, adolescents with MDD were treated with escitalopram in an 8-week, open-label trial. Participants were monitored for 5 weeks, including the baseline data collection period. Their psychiatric status was measured every week. Depression severity was measured using the Children's Depression Rating Scale-Revised and Clinical Global Impressions-Severity. The Columbia Suicide Severity Rating Scale was administered in order to assess suicide severity. We applied the deep learning approach for the analysis of the data. Deep neural network was employed for diagnosis classification, and neural network with weighted fuzzy membership functions was used for feature selection.

RESULTS

We could predict the diagnosis of depression with training accuracy of 96.3% and 3-fold validation accuracy of 77%. Of the 24 adolescents with MDD, 10 responded to antidepressant treatments. We predicted the treatment response of adolescents with MDD with training accuracy of 94.2% and 3-fold validation accuracy of 76%. Adolescents with MDD tended to move longer distances and use smartphones for longer periods of time compared to controls. The deep learning analysis showed that smartphone usage time was the most important feature in distinguishing adolescents with MDD from controls. Prominent differences were not observed in the pattern of each feature between the treatment responders and nonresponders. The deep learning analysis revealed that the total length of calls received as the most important feature predicting antidepressant response in adolescents with MDD.

CONCLUSIONS

Our smartphone app demonstrated preliminary evidence of predicting diagnosis and treatment response in depressed adolescents. This is the first study to predict the treatment response of adolescents with MDD by examining smartphone-based objective data with deep learning approaches.

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

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

Screening for Major Depressive Disorder Using a Wearable Ultra-Short-Term HRV Monitor and Signal Quality Indices

To encourage potential major depressive disorder (MDD) patients to attend diagnostic sessions, we developed a novel MDD screening system based on sleep-induced autonomic nervous responses. The proposed method only requires a wristwatch device to be worn for 24 h. We evaluated heart rate variability (HRV) via wrist photoplethysmography (PPG). However, previous studies have indicated that HRV measurements obtained using wearable devices are susceptible to motion artifacts. We propose a novel method to improve screening accuracy by removing unreliable HRV data (identified on the basis of signal quality indices (SQIs) obtained by PPG sensors). The proposed algorithm enables real-time calculation of signal quality indices in the frequency domain (SQI-FD). A clinical study conducted at Maynds Tower Mental Clinic enrolled 40 MDD patients (mean age, 37.5 ± 8.8 years) diagnosed on the basis of the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, and 29 healthy volunteers (mean age, 31.9 ± 13.0 years). Acceleration data were used to identify sleep states, and a linear classification model was trained and tested using HRV and pulse rate data. Ten-fold cross-validation showed a sensitivity of 87.3% (80.3% without SQI-FD data) and specificity of 84.0% (73.3% without SQI-FD data). Thus, SQI-FD drastically improved sensitivity and specificity.

Predicting depressive symptoms in middle-aged and elderly adults using sleep data and clinical health markers: A machine learning approach

OBJECTIVES

Comorbid depression is a highly prevalent and debilitating condition in middle-aged and elderly adults, particularly when associated with obesity, diabetes, and sleep disturbances. In this context, there is a growing need to develop efficient screening methods for cases based on clinical health markers for these comorbidities and sleep data. Thus, our objective was to detect depressive symptoms in these subjects, considering general biomarkers of obesity and diabetes and variables related to sleep and physical exercise through a machine learning approach.

METHODS

We used the National Health and Nutrition Examination Survey (NHANES) 2015-2016 data. Eighteen variables on self-reported physical activity, self-reported sleep habits, sleep disturbance indicative, anthropometric measurements, sociodemographic characteristics and plasma biomarkers of obesity and diabetes were selected as predictors. A total of 2907 middle-aged and elderly subjects were eligible for the study. Supervised learning algorithms such as Lasso penalized Logistic Regression (LR), Random Forest (RF) and Extreme Gradient Boosting (XGBoost) were implemented.

RESULTS

XGBoost provided greater accuracy and precision (87%), with a proportion of hits in cases with depressive symptoms above 80%. In addition, daytime sleepiness was the most significant predictor variable for predicting depressive symptoms.

CONCLUSIONS

Sleep and physical activity variables, in addition to obesity and diabetes biomarkers, together assume significant importance to predict, with accuracy and precision of 87%, the occurrence of depressive symptoms in middle-aged and elderly individuals.

Wearable devices for anxiety & depression: A scoping review

Background

The rates of mental health disorders such as anxiety and depression are at an all-time high especially since the onset of COVID-19, and the need for readily available digital health care solutions has never been greater. Wearable devices have increasingly incorporated sensors that were previously reserved for hospital settings. The availability of wearable device features that address anxiety and depression is still in its infancy, but consumers will soon have the potential to self-monitor moods and behaviors using everyday commercially-available devices.

Objective

This study aims to explore the features of wearable devices that can be used for monitoring anxiety and depression.

Methods

Six bibliographic databases, including MEDLINE, EMBASE, PsycINFO, IEEE Xplore, ACM Digital Library, and Google Scholar were used as search engines for this review. Two independent reviewers performed study selection and data extraction, while two other reviewers justified the cross-checking of extracted data. A narrative approach for synthesizing the data was utilized.

Results

From 2408 initial results, 58 studies were assessed and highlighted according to our inclusion criteria. Wrist-worn devices were identified in the bulk of our studies (n = 42 or 71%). For the identification of anxiety and depression, we reported 26 methods for assessing mood, with the State-Trait Anxiety Inventory being the joint most common along with the Diagnostic and Statistical Manual of Mental Disorders (n = 8 or 14%). Finally, n = 26 or 46% of studies highlighted the smartphone as a wearable device host device.

Conclusion

The emergence of affordable, consumer-grade biosensors offers the potential for new approaches to support mental health therapies for illnesses such as anxiety and depression. We believe that purposefully-designed wearable devices that combine the expertise of technologists and clinical experts can play a key role in self-care monitoring and diagnosis.

Wearable Artificial Intelligence for Anxiety and Depression: Scoping Review

BACKGROUND

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

OBJECTIVE

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Development and validation of the Chinese Geriatric Depression Risk calculator (CGD-risk): A screening tool to identify elderly Chinese with depression

BACKGROUND

The prevalence of depression among China's elderly is high, but stigma surrounding mental illness and a shortage of psychiatrists limit widespread screening and diagnosis of geriatric depression. We sought to develop a screening tool using easy-to-obtain and minimally sensitive predictors to identify elderly Chinese with depressive symptoms (depression hereafter) for referral to mental health services and determine the most important factors for effective screening.

METHODS

Using nationally representative survey data, we developed and externally validated the Chinese Geriatric Depression Risk calculator (CGD-Risk). CGD-Risk, a gradient boosting machine learning model, was evaluated based on discrimination (Concordance (C) statistic), calibration, and through a decision curve analysis. We conducted a sensitivity analysis on a cohort of middle-aged Chinese, a sub-group analysis using three data sets, and created predictor importance and partial dependence plots to enhance interpretability.

RESULTS

A total of 5681 elderly Chinese were included in the development data and 12,373 in the external validation data. CGD-Risk showed good discrimination during internal validation (C: 0.81, 95 % CI 0.79 to 0.84) and external validation (C: 0.77, 95 % CI: 0.76, 0.78). Compared to an alternative screening strategy CGD-Risk would correctly identify 17.8 more elderly with depression per 100 people screened.

LIMITATIONS

We were only able to externally validate a partial version of CGD-Risk due to differences between the internal and external validation data.

CONCLUSIONS

CGD-Risk is a clinically viable, minimally sensitive screening tool that could identify elderly Chinese at high risk of depression while circumventing issues of response bias from stigma surrounding emotional openness.

Extended reality for mental health: Current trends and future challenges

Virtual and augmented reality have been used to diagnose and treat several mental health disorders for decades. Technological advances in these fields have facilitated the availability of commercial solutions for end customers and practitioners. However, there are still some barriers and limitations that prevent these technologies from being widely used by professionals on a daily basis. In addition, the COVID-19 pandemic has exposed a variety of new scenarios in which these technologies could play an essential role, like providing remote treatment. Disorders that traditionally had received less attention are also getting in the spotlight, such as depression or obsessive-compulsive disorder. Improvements in equipment and hardware, like Mixed Reality Head Mounted Displays, could help open new opportunities in the mental health field. Extended reality (XR) is an umbrella term meant to comprise Virtual reality (VR), mixed reality (MR), and augmented reality (AR). While XR applications are eminently visual, other senses are being explored in literature around multisensory interactions, such as auditory, olfactory, or haptic feedback. Applying such stimuli within XR experiences around mental disorders is still under-explored and could greatly enrich the therapeutic experience. This manuscript reviews recent research regarding the use of XR for mental health scenarios, highlighting trends, and potential applications as well as areas for improvement. It also discusses future challenges and research areas in upcoming topics such as the use of wearables, multisensory, and multimodal interaction. The main goal of this paper is to unpack how these technologies could be applied to XR scenarios for mental health to exploit their full potential and follow the path of other health technologies by promoting personalized medicine.

Lifestyle, Demographic and Socio-Economic Determinants of Mental Health Disorders of Employees in the European Countries

Ensuring the health and well-being of workers should be a top priority for employers and governments. The aim of the article is to evaluate and rank the importance of mental health determinants: lifestyle, demographic factors and socio-economic status. The research study is based on EHIS 2013-2015 data for a sample of N = 140,791 employees from 30 European countries. The results obtained using machine learning techniques such as gradient-boosted trees and SHAPley values show that the mental health of European employees is strongly determined by the BMI, age and social support from close people. The next vital features are alcohol consumption, an unmet need for health care and sports activity, followed by the affordability of medicine or treatment, income and occupation. The wide range of variables clearly indicates that there is an important role for governments to play in order to minimize the risk of mental disorders across various socio-economic groups. It is also a signal for businesses to help boost the mental health of their employees by creating holistic, mentally friendly working conditions, such as offering time-management training, implementing morning briefings, offering quiet areas, making employees feel valued, educating them about depression and burnout symptoms, and promoting a healthy lifestyle.

Utilizing daily mood diaries and wearable sensor data to predict depression and suicidal ideation among medical interns

BACKGROUND

Intensive longitudinal methods (ILMs) for collecting self-report (e.g., daily diaries, ecological momentary assessment) and passive data from smartphones and wearable sensors provide promising avenues for improved prediction of depression and suicidal ideation (SI). However, few studies have utilized ILMs to predict outcomes for at-risk, non-clinical populations in real-world settings.

METHODS

Medical interns (N = 2881; 57 % female; 58 % White) were recruited from over 300 US residency programs. Interns completed a pre-internship assessment of depression, were given Fitbit wearable devices, and provided daily mood ratings (scale: 1-10) via mobile application during the study period. Three-step hierarchical logistic regressions were used to predict depression and SI at the end of the first quarter utilizing pre-internship predictors in step 1, Fitbit sleep/step features in step 2, and daily diary mood features in step 3.

RESULTS

Passively collected Fitbit features related to sleep and steps had negligible predictive validity for depression, and no incremental predictive validity for SI. However, mean-level and variability in mood scores derived from daily diaries were significant independent predictors of depression and SI, and significantly improved model accuracy.

LIMITATIONS

Work schedules for interns may result in sleep and activity patterns that differ from typical associations with depression or SI. The SI measure did not capture intent or severity.

CONCLUSIONS

Mobile self-reporting of daily mood improved the prediction of depression and SI during a meaningful at-risk period under naturalistic conditions. Additional research is needed to guide the development of adaptive interventions among vulnerable populations.

Technology-Based Approaches for Supporting Perinatal Mental Health

PURPOSE OF REVIEW

This review explores advances in the utilization of technology to address perinatal mood and anxiety disorders (PMADs). Specifically, we sought to assess the range of technologies available, their application to PMADs, and evidence supporting use.

RECENT FINDINGS

We identified a variety of technologies with promising capacity for direct intervention, prevention, and augmentation of clinical care for PMADs. These included wearable technology, electronic consultation, virtual and augmented reality, internet-based cognitive behavioral therapy, and predictive analytics using machine learning. Available evidence for these technologies in PMADs was almost uniformly positive. However, evidence for use in PMADs was limited compared to that in general mental health populations. Proper attention to PMADs has been severely limited by issues of accessibility, affordability, and patient acceptance. Increased use of technology has the potential to address all three of these barriers by facilitating modes of communication, data collection, and patient experience.

IMU-Based Monitoring for Assistive Diagnosis and Management of IoHT: A Review

With the rapid development of Internet of Things (IoT) technologies, traditional disease diagnoses carried out in medical institutions can now be performed remotely at home or even ambient environments, yielding the concept of the Internet of Health Things (IoHT). Among the diverse IoHT applications, inertial measurement unit (IMU)-based systems play a significant role in the detection of diseases in many fields, such as neurological, musculoskeletal, and mental. However, traditional numerical interpretation methods have proven to be challenging to provide satisfying detection accuracies owing to the low quality of raw data, especially under strong electromagnetic interference (EMI). To address this issue, in recent years, machine learning (ML)-based techniques have been proposed to smartly map IMU-captured data on disease detection and progress. After a decade of development, the combination of IMUs and ML algorithms for assistive disease diagnosis has become a hot topic, with an increasing number of studies reported yearly. A systematic search was conducted in four databases covering the aforementioned topic for articles published in the past six years. Eighty-one articles were included and discussed concerning two aspects: different ML techniques and application scenarios. This review yielded the conclusion that, with the help of ML technology, IMUs can serve as a crucial element in disease diagnosis, severity assessment, characteristic estimation, and monitoring during the rehabilitation process. Furthermore, it summarizes the state-of-the-art, analyzes challenges, and provides foreseeable future trends for developing IMU-ML systems for IoHT.

Depressed Mood Prediction of Elderly People with a Wearable Band

Depression in the elderly is an important social issue considering the population aging of the world. In particular, elderly living alone who has narrowed social relationship due to bereavement and retirement are more prone to be depressed. Long-term depressed mood can be a precursor to eventual depression as a disease. Our goal is how to predict the depressed mood of single household elderly from unobtrusive monitoring of their daily life. We have selected a wearable band with multiple sensors for monitoring elderly people. Depression questionnaire has been surveyed periodically to be used as the labels. Instead of working with depression patients, we recruited 14 single household elderly people from a nearby community. The wearable band provided daily activity and biometric data for 71 days. From the data, we generate a depressed mood prediction model. Multiple features from the collected sensor data are exploited for model generation. One general model is generated to be used as the baseline for the initial model deployment. Personal models are also generated for model refinement. The general model has a high recall of 80% in an MLP model. Individual models achieved an average recall of 82.7%. In this study, we have demonstrated that we can generate depressed mood prediction models with data collected from real daily living. Our work has shown the feasibility of using a wearable band as an unobtrusive depression monitoring sensor even for elderly people.

Development of medical device software for the screening and assessment of depression severity using data collected from a wristband-type wearable device: SWIFT study protocol

INTRODUCTION

Few biomarkers can be used clinically to diagnose and assess the severity of depression. However, a decrease in activity and sleep efficiency can be observed in depressed patients, and recent technological developments have made it possible to measure these changes. In addition, physiological changes, such as heart rate variability, can be used to distinguish depressed patients from normal persons; these parameters can be used to improve diagnostic accuracy. The proposed research will explore and construct machine learning models capable of detecting depressive episodes and assessing their severity using data collected from wristband-type wearable devices.

METHODS AND ANALYSIS

Patients with depressive symptoms and healthy subjects will wear a wristband-type wearable device for 7 days; data on triaxial acceleration, pulse rate, skin temperature, and ultraviolet light will be collected. On the seventh day of wearing, the severity of depressive episodes will be assessed using Structured Clinical Interview for DSM-5 (SCID-5), Hamilton Depression Rating Scale (HAMD), and other scales. Data for up to five 7-day periods of device wearing will be collected from each subject. Using wearable device data associated with clinical symptoms as supervisory data, we will explore and build a machine learning model capable of identifying the presence or absence of depressive episodes and predicting the HAMD scores for an unknown data set.

DISCUSSION

Our machine learning model could improve the clinical diagnosis and management of depression through the use of a wearable medical device.

CLINICAL TRIAL REGISTRATION

[https://jrct.niph.go.jp/latest-detail/jRCT1031210478], identifier [jRCT1031210478].

Digital Biomarkers for Depression Screening With Wearable Devices: Cross-sectional Study With Machine Learning Modeling

Background

Depression is a prevalent mental disorder that is undiagnosed and untreated in half of all cases. Wearable activity trackers collect fine-grained sensor data characterizing the behavior and physiology of users (ie, digital biomarkers), which could be used for timely, unobtrusive, and scalable depression screening.

Objective

The aim of this study was to examine the predictive ability of digital biomarkers, based on sensor data from consumer-grade wearables, to detect risk of depression in a working population.

Methods

This was a cross-sectional study of 290 healthy working adults. Participants wore Fitbit Charge 2 devices for 14 consecutive days and completed a health survey, including screening for depressive symptoms using the 9-item Patient Health Questionnaire (PHQ-9), at baseline and 2 weeks later. We extracted a range of known and novel digital biomarkers characterizing physical activity, sleep patterns, and circadian rhythms from wearables using steps, heart rate, energy expenditure, and sleep data. Associations between severity of depressive symptoms and digital biomarkers were examined with Spearman correlation and multiple regression analyses adjusted for potential confounders, including sociodemographic characteristics, alcohol consumption, smoking, self-rated health, subjective sleep characteristics, and loneliness. Supervised machine learning with statistically selected digital biomarkers was used to predict risk of depression (ie, symptom severity and screening status). We used varying cutoff scores from an acceptable PHQ-9 score range to define the depression group and different subsamples for classification, while the set of statistically selected digital biomarkers remained the same. For the performance evaluation, we used k-fold cross-validation and obtained accuracy measures from the holdout folds.

Results

A total of 267 participants were included in the analysis. The mean age of the participants was 33 (SD 8.6, range 21-64) years. Out of 267 participants, there was a mild female bias displayed (n=170, 63.7%). The majority of the participants were Chinese (n=211, 79.0%), single (n=163, 61.0%), and had a university degree (n=238, 89.1%). We found that a greater severity of depressive symptoms was robustly associated with greater variation of nighttime heart rate between 2 AM and 4 AM and between 4 AM and 6 AM; it was also associated with lower regularity of weekday circadian rhythms based on steps and estimated with nonparametric measures of interdaily stability and autocorrelation as well as fewer steps-based daily peaks. Despite several reliable associations, our evidence showed limited ability of digital biomarkers to detect depression in the whole sample of working adults. However, in balanced and contrasted subsamples comprised of depressed and healthy participants with no risk of depression (ie, no or minimal depressive symptoms), the model achieved an accuracy of 80%, a sensitivity of 82%, and a specificity of 78% in detecting subjects at high risk of depression.

Conclusions

Digital biomarkers that have been discovered and are based on behavioral and physiological data from consumer wearables could detect increased risk of depression and have the potential to assist in depression screening, yet current evidence shows limited predictive ability. Machine learning models combining these digital biomarkers could discriminate between individuals with a high risk of depression and individuals with no risk.

Machine Learning-Based Behavioral Diagnostic Tools for Depression: Advances, Challenges, and Future Directions

The psychiatric diagnostic procedure is currently based on self-reports that are subject to personal biases. Therefore, the diagnostic process would benefit greatly from data-driven tools that can enhance accuracy and specificity. In recent years, many studies have achieved promising results in detecting and diagnosing depression based on machine learning (ML) analysis. Despite these favorable results in depression diagnosis, which are primarily based on ML analysis of neuroimaging data, most patients do not have access to neuroimaging tools. Hence, objective assessment tools are needed that can be easily integrated into the routine psychiatric diagnostic process. One solution is to use behavioral data, which can be easily collected while still maintaining objectivity. The current paper summarizes the main ML-based approaches that use behavioral data in diagnosing depression and other psychiatric disorders. We classified these studies into two main categories: (a) laboratory-based assessments and (b) data mining, the latter of which we further divided into two sub-groups: (i) social media usage and movement sensors data and (ii) demographic and clinical information. The paper discusses the advantages and challenges in this field and suggests future research directions and implementations. The paper's overarching aim is to serve as a first step in synthetizing existing knowledge about ML-based behavioral diagnosis studies in order to develop interventions and individually tailored treatments in the future.

Features of wearable devices used for Anxiety & Depression: A scoping review (Preprint).. [DOI: 10.2196/preprints.33287] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

BACKGROUND

The rates of mental health disorders such as anxiety and depression are at an all time high and the need for readily available digital health care solutions has never been greater. Wearable devices (WD) have seen a steady rise in the usage of sensors previously reserved for hospital settings. The availibity of features that make use of WDs for anxiety and depression is in its infancy, but we are seeing the potential for consumers to self monitor moods and behaviours with everyday commercially available devices and the ability to self-regulate their health needs.

OBJECTIVE

This study aims to explore features of wearable devices (WDs) used for anxiety and depression

METHODS

We have searched the following six bibliographic databases while conducting this review: MEDLINE, EMBASE, PsycINFO, IEEE Xplore, ACM Digital Library, and Google Scholar. Two reviewers independently performed study selection and data extraction; two other individual reviewers justified cross-checking of extracted data. We utilized a narrative approach for synthesizing the data.

RESULTS

From an initial 2,408 studies we assess and report the features in 58 studies that were highlighted according to our inclusion criteria. Wrist worn devices were identified in the bulk of our studies (n=42 or 71%). Depression was assessed in most of the studies (n=27 or 47%), whereas anxiety was assessed in n=15 or 25% of studies. More than a quarter (n=16 or 27%) of the included studies assessed both mental disorders. Finally n=26 or 46% of studies highlighted the wearable device host device as a smartphone.

CONCLUSIONS

The emergence of affordable, consumer-grade biosensors offers the potential for new approaches to support mental health therapies such as anxiety and depression. We see WDs having real potential in aiding with self-care and with purposefully designed WDs that combine the expertise of technologists and clinical experts WDs could play a key role in self-care monitoring and diagnosis.

Moderating effect of people-oriented public health services on depression among people under mandatory social isolation during the COVID-19 pandemic: a cross-sectional study in China

BACKGROUND

Public health measures, such as social isolation, are vital to control the spread of the coronavirus disease 2019 (COVID-19), but such measures may increase the risk of depression. Thus, this study examines the influencing and moderating factors of depressive symptoms among individuals subjected to mandatory social isolation.

METHODS

An online cross-sectional survey was conducted to collect data from people under mandatory home or centralized social isolation in Shenzhen, China, from February 28 to March 6, 2020. The perceived risk of infection with COVID-19, perceived tone of media coverage, perceived quality of people-oriented public health services, and their depressive symptoms were assessed. Three rounds of stepwise multiple regression were performed to examine the moderating effects after controlling various variables, such as demographics, duration and venue of mandatory social isolation, infection and isolation status of family, time spent on COVID-related news, and online social support.

RESULTS

Among the 340 participants, 57.6% were men, the average age was 35.5 years old (SD = 8.37), and 55.6% held a bachelor's degree or above. Individuals subjected to mandatory social isolation generally reported low levels of depressive symptoms. Perceived susceptibility to infection was relatively low, whereas perceived tone of media coverage was mainly positive. In terms of perceived quality of public health services, 12 (3.5%), 103 (30.3%), and 225 (66.2%) participants reported low, medium, and high quality of people-oriented services, respectively. Perceived susceptibility was positively associated with depression, whereas perceived tone of media coverage was negatively associated. The quality of people-centered public health services moderated the association between perceived risk and depressive symptoms and between perceived tone of media coverage and depressive symptoms.

CONCLUSIONS

This study revealed the depressive symptoms among individuals subjected to mandatory social isolation during the COVID-19 pandemic and highlighted that frontline public health workers play a critical role in protecting public mental health.

Machine Learning Analysis to Identify Digital Behavioral Phenotypes for Engagement and Health Outcome Efficacy of an mHealth Intervention for Obesity: Randomized Controlled Trial

BACKGROUND

The digital health care community has been urged to enhance engagement and clinical outcomes by analyzing multidimensional digital phenotypes.

OBJECTIVE

This study aims to use a machine learning approach to investigate the performance of multivariate phenotypes in predicting the engagement rate and health outcomes of digital cognitive behavioral therapy.

METHODS

We leveraged both conventional phenotypes assessed by validated psychological questionnaires and multidimensional digital phenotypes within time-series data from a mobile app of 45 participants undergoing digital cognitive behavioral therapy for 8 weeks. We conducted a machine learning analysis to discriminate the important characteristics.

RESULTS

A higher engagement rate was associated with higher weight loss at 8 weeks (r=-0.59; P<.001) and 24 weeks (r=-0.52; P=.001). Applying the machine learning approach, lower self-esteem on the conventional phenotype and higher in-app motivational measures on digital phenotypes commonly accounted for both engagement and health outcomes. In addition, 16 types of digital phenotypes (ie, lower intake of high-calorie food and evening snacks and higher interaction frequency with mentors) predicted engagement rates (mean R² 0.416, SD 0.006). The prediction of short-term weight change (mean R² 0.382, SD 0.015) was associated with 13 different digital phenotypes (ie, lower intake of high-calorie food and carbohydrate and higher intake of low-calorie food). Finally, 8 measures of digital phenotypes (ie, lower intake of carbohydrate and evening snacks and higher motivation) were associated with a long-term weight change (mean R² 0.590, SD 0.011).

CONCLUSIONS

Our findings successfully demonstrated how multiple psychological constructs, such as emotional, cognitive, behavioral, and motivational phenotypes, elucidate the mechanisms and clinical efficacy of a digital intervention using the machine learning method. Accordingly, our study designed an interpretable digital phenotype model, including multiple aspects of motivation before and during the intervention, predicting both engagement and clinical efficacy. This line of research may shed light on the development of advanced prevention and personalized digital therapeutics.

TRIAL REGISTRATION

ClinicalTrials.gov NCT03465306; https://clinicaltrials.gov/ct2/show/NCT03465306.

Ensuring patient and public involvement in the transition to AI-assisted mental health care: A systematic scoping review and agenda for design justice

Background

Machine‐learning algorithms and big data analytics, popularly known as ‘artificial intelligence’ (AI), are being developed and taken up globally. Patient and public involvement (PPI) in the transition to AI‐assisted health care is essential for design justice based on diverse patient needs.

Objective

To inform the future development of PPI in AI‐assisted health care by exploring public engagement in the conceptualization, design, development, testing, implementation, use and evaluation of AI technologies for mental health.

Methods

Systematic scoping review drawing on design justice principles, and (i) structured searches of Web of Science (all databases) and Ovid (MEDLINE, PsycINFO, Global Health and Embase); (ii) handsearching (reference and citation tracking); (iii) grey literature; and (iv) inductive thematic analysis, tested at a workshop with health researchers.

Results

The review identified 144 articles that met inclusion criteria. Three main themes reflect the challenges and opportunities associated with PPI in AI‐assisted mental health care: (a) applications of AI technologies in mental health care; (b) ethics of public engagement in AI‐assisted care; and (c) public engagement in the planning, development, implementation, evaluation and diffusion of AI technologies.

Conclusion

The new data‐rich health landscape creates multiple ethical issues and opportunities for the development of PPI in relation to AI technologies. Further research is needed to understand effective modes of public engagement in the context of AI technologies, to examine pressing ethical and safety issues and to develop new methods of PPI at every stage, from concept design to the final review of technology in practice. Principles of design justice can guide this agenda.

Unobtrusive Sensing Technology for Quantifying Stress and Well-Being Using Pulse, Speech, Body Motion, and Electrodermal Data in a Workplace Setting: Study Concept and Design

Introduction: Mental disorders are a leading cause of disability worldwide. Depression has a significant impact in the field of occupational health because it is particularly prevalent during working age. On the other hand, there are a growing number of studies on the relationship between "well-being" and employee productivity. To promote healthy and productive workplaces, this study aims to develop a technique to quantify stress and well-being in a way that does not disturb the workplace. Methods and analysis: This is a single-arm prospective observational study. The target population is adult (>20 years old) workers at companies that often engage in desk work; specifically, a person who sits in front of a computer for at least half their work hours. The following data will be collected: (a) participants' background characteristics; (b) participants' biological data during the 4-week observation period using sensing devices such as a camera built into the computer (pulse wave data extracted from the facial video images), a microphone built into their work computer (voice data), and a wristband-type wearable device (electrodermal activity data, body motion data, and body temperature); (c) stress, well-being, and depression rating scale assessment data. The analysis workflow is as follows: (1) primary analysis, comprised of using software to digitalize participants' vital information; (2) secondary analysis, comprised of examining the relationship between the quantified vital data from (1), stress, well-being, and depression; (3) tertiary analysis, comprised of generating machine learning algorithms to estimate stress, well-being, and degree of depression in relation to each set of vital data as well as multimodal vital data. Discussion: This study will evaluate digital phenotype regarding stress and well-being of white-collar workers over a 4-week period using persistently obtainable biomarkers such as heart rate, acoustic characteristics, body motion, and electrodermal activity. Eventually, this study will lead to the development of a machine learning algorithm to determine people's optimal levels of stress and well-being. Ethics and dissemination: Collected data and study results will be disseminated widely through conference presentations, journal publications, and/or mass media. The summarized results of our overall analysis will be supplied to participants. Registration: UMIN000036814.

Current Advances in Wearable Devices and Their Sensors in Patients With Depression

In this study, a literature survey was conducted of research into the development and use of wearable devices and sensors in patients with depression. We collected 18 studies that had investigated wearable devices for assessment, monitoring, or prediction of depression. In this report, we examine the sensors of the various types of wearable devices (e.g., actigraphy units, wristbands, fitness trackers, and smartwatches) and parameters measured through sensors in people with depression. In addition, we discuss future trends, referring to research in other areas employing wearable devices, and suggest the challenges of using wearable devices in the field of depression. Real-time objective monitoring of symptoms and novel approaches for diagnosis and treatment using wearable devices will lead to changes in management of patients with depression. During the process, it is necessary to overcome several issues, including limited types of collected data, reliability, user adherence, and privacy concerns.