Depression Prediction by Using Ecological Momentary Assessment, Actiwatch Data, and Machine Learning: Observational Study on Older Adults Living Alone

Assessing Social Interaction and Loneliness and Their Association With Frailty Among Older Adults With Subjective Cognitive Decline or Mild Cognitive Impairment: Ecological Momentary Assessment Approach

BACKGROUND

Frail older adults are at greater risk of adverse health-related outcomes such as falls, disability, and mortality. Mild behavioral impairment (MBI), which is characterized by neurobehavioral symptoms in individuals without dementia, is a crucial factor in identifying at-risk groups and implementing early interventions for frail older adults. However, the specific role of social functioning, which encompasses social interaction and loneliness levels, in relation to frailty within this group remains unclear.

OBJECTIVE

This study investigated the association between frailty status, social interaction frequency, and loneliness levels among older adults with subjective cognitive decline (SCD) or mild cognitive impairment (MCI) while adjusting for MBI symptoms in 2 contexts: the presence and severity of MBI symptoms.

METHODS

Older adults with SCD or MCI were recruited from an outpatient clinic specializing in the early diagnosis and care management of dementia at a community health center, as well as from a community service center in Seoul, South Korea. Using an ecological momentary assessment approach, participants reported their daily social interaction frequency and loneliness level via a mobile app, 4 times daily for 2 weeks. Frailty status, the outcome variable, was assessed using the Korean version of the frailty phenotype questionnaire. Additionally, MBI symptoms were assessed using the 34-item MBI-Checklist covering 5 domains. Multinomial logistic regression analyses were performed to investigate the association between frailty status (robust, prefrail, and frail), and the independent variables, adjusting for the presence or severity of MBI symptoms.

RESULTS

Among the 101 participants analyzed, 29.7% (n=30) of participants were classified as prefrail, and 12.8% (n=13) of participants were classified as frail. Higher average daily social interaction scores were consistently associated with lower odds of a frail status compared to a robust status. This was evident in the models adjusted for both the global presence (relative risk ratio [RRR] 0.18, P=.02) and global severity (RRR 0.20, P=.02) of MBI symptoms.

CONCLUSIONS

Frequent social interaction was inversely associated with frail status in older adults with SCD or MCI, even after adjusting for the presence and severity of MBI symptoms. These findings highlight the potential of social functioning as a modifiable factor for addressing frailty among older adults at risk of cognitive and functional decline. Future prospective studies using real-time measurements are needed to refine these findings and further investigate additional risk factors and functional outcomes in this group.

Fusing Wearable Biosensors with Artificial Intelligence for Mental Health Monitoring: A Systematic Review

The development of digital instruments for mental health monitoring using biosensor data from wearable devices can enable remote, longitudinal, and objective quantitative benchmarks. To survey developments and trends in this field, we conducted a systematic review of artificial intelligence (AI) models using data from wearable biosensors to predict mental health conditions and symptoms. Following PRISMA guidelines, we identified 48 studies using a variety of wearable and smartphone biosensors including heart rate, heart rate variability (HRV), electrodermal activity/galvanic skin response (EDA/GSR), and digital proxies for biosignals such as accelerometry, location, audio, and usage metadata. We observed several technical and methodological challenges across studies in this field, including lack of ecological validity, data heterogeneity, small sample sizes, and battery drainage issues. We outline several corresponding opportunities for advancement in the field of AI-driven biosensing for mental health.

Applying AI in the Context of the Association Between Device-Based Assessment of Physical Activity and Mental Health: Systematic Review

BACKGROUND

Wearable technology is used by consumers worldwide for continuous activity monitoring in daily life but more recently also for classifying or predicting mental health parameters like stress or depression levels. Previous studies identified, based on traditional approaches, that physical activity is a relevant factor in the prevention or management of mental health. However, upcoming artificial intelligence methods have not yet been fully established in the research field of physical activity and mental health.

OBJECTIVE

This systematic review aims to provide a comprehensive overview of studies that integrated passive monitoring of physical activity data measured via wearable technology in machine learning algorithms for the detection, prediction, or classification of mental health states and traits.

METHODS

We conducted a review of studies processing wearable data to gain insights into mental health parameters. Eligibility criteria were (1) the study uses wearables or smartphones to acquire physical behavior and optionally other sensor measurement data, (2) the study must use machine learning to process the acquired data, and (3) the study had to be published in a peer-reviewed English language journal. Studies were identified via a systematic search in 5 electronic databases.

RESULTS

Of 11,057 unique search results, 49 published papers between 2016 and 2023 were included. Most studies examined the connection between wearable sensor data and stress (n=15, 31%) or depression (n=14, 29%). In total, 71% (n=35) of the studies had less than 100 participants, and 47% (n=23) had less than 14 days of data recording. More than half of the studies (n=27, 55%) used step count as movement measurement, and 44% (n=21) used raw accelerometer values. The quality of the studies was assessed, scoring between 0 and 18 points in 9 categories (maximum 2 points per category). On average, studies were rated 6.47 (SD 3.1) points.

CONCLUSIONS

The use of wearable technology for the detection, prediction, or classification of mental health states and traits is promising and offers a variety of applications across different settings and target groups. However, based on the current state of literature, the application of artificial intelligence cannot realize its full potential mostly due to a lack of methodological shortcomings and data availability. Future research endeavors may focus on the following suggestions to improve the quality of new applications in this context: first, by using raw data instead of already preprocessed data. Second, by using only relevant data based on empirical evidence. In particular, crafting optimal feature sets rather than using many individual detached features and consultation with in-field professionals. Third, by validating and replicating the existing approaches (ie, applying the model to unseen data). Fourth, depending on the research aim (ie, generalization vs personalization) maximizing the sample size or the duration over which data are collected.

App-Based Ecological Momentary Assessment of Problematic Smartphone Use During Examination Weeks in University Students: 6-Week Observational Study

BACKGROUND

The increasing prevalence of problematic smartphone use (PSU) among university students is raising concerns, particularly as excessive smartphone engagement is linked to negative outcomes such as mental health issues, academic underperformance, and sleep disruption. Despite the severity of PSU, its association with behaviors such as physical activity, mobility, and sociability has received limited research attention. Ecological momentary assessment (EMA), including passive data collection through digital phenotyping indicators, offers an objective approach to explore these behavioral patterns.

OBJECTIVE

This study aimed to examine associations between self-reported psychosocial measures; app-based EMA data, including daily behavioral indicators from GPS location tracking; and PSU in university students during the examination period.

METHODS

A 6-week observational study involving 243 university students was conducted using app-based EMA on personal smartphones to collect data on daily behaviors and psychosocial factors related to smartphone overuse. PSU was assessed using the Korean Smartphone Addiction Proneness Scale. Data collected from the Big4+ app, including self-reports on mood, sleep, and appetite, as well as passive sensor data (GPS location, acceleration, and steps) were used to evaluate overall health. Logistic regression analysis was conducted to identify factors that significantly influenced smartphone overuse, providing insights into daily behavior and mental health patterns.

RESULTS

In total, 23% (56/243) of the students exhibited PSU. The regression analysis revealed significant positive associations between PSU and several factors, including depression (Patient Health Questionnaire-9; odds ratio [OR] 8.48, 95% CI 1.95-36.87; P=.004), social interaction anxiety (Social Interaction Anxiety Scale; OR 4.40, 95% CI 1.59-12.15; P=.004), sleep disturbances (General Sleep Disturbance Scale; OR 3.44, 95% CI 1.15-10.30; P=.03), and longer sleep duration (OR 3.11, 95% CI 1.14-8.48; P=.03). Conversely, a significant negative association was found between PSU and time spent at home (OR 0.35, 95% CI 0.13-0.94; P=.04).

CONCLUSIONS

This study suggests that negative self-perceptions of mood and sleep, along with patterns of increased mobility identified through GPS data, increase the risk of PSU, particularly during periods of academic stress. Combining psychosocial assessments with EMA data offers valuable insights for managing PSU during high-stress periods, such as examinations, and provides new directions for future research.

A case for the use of deep learning algorithms for individual and population level assessments of mental health disorders: Predicting depression among China's elderly

BACKGROUND

With the continuous advancement of age in China, attention should be paid to the mental well-being of the elderly population. The present study uses a novel machine learning (ML) method on a large representative elderly database in China as a sample to predict the risk factors of depression in the elderly population from both holistic and individual level.

METHODS

A total of participants met the inclusion criteria from the fourth waves of the China Health and Retirement Longitudinal Study (CHARLS) were analyzed with ML algorithms. The level of depression was assessed by the 10-item Center for Epidemiological Studies Depression Scale (CESD-10).

RESULTS

The current study found top 5 factors that were important for predicting depression in the elderly population in China, including average sleep time, gender, age, social activities and nap time during the day. The results also provide reliable diagnostic likelihood at the individual level to support clinicians identify the most impactful factors contributing to patient depression. Our findings also suggested that activities such as interacting with friends and play ma-Jong, chess or join community clubs may have a positive collaborative effect for elderly's mental health.

CONCLUSIONS

Holistic approaches are an effective method of deriving and interpreting sophisticated models of mental health in elderly populations. More detailed information about a patient's demographics, medical history, sleeping patterns and social/leisure activities can help to inform policy and treatment interventions on a population and individual level. Large scale surveys such as CHARLS are effective methods for testing the most accurate models, however, further research using professional clinical input could further advance the field.

Exploring key factors influencing depressive symptoms among middle-aged and elderly adult population: A machine learning-based method

OBJECTIVE

This paper aims to investigate the key factors, including demographics, socioeconomics, physical well-being, lifestyle, daily activities and loneliness that can impact depressive symptoms in the middle-aged and elderly population using machine learning techniques. By identifying the most important predictors of depressive symptoms through the analysis, the findings can have important implications for early depression detection and intervention.

PARTICIPANTS

For our cross-sectional study, we recruited a total of 976 volunteers, with a specific focus on individuals aged 50 and above. Each participant was requested to provide their demographic, socioeconomic information and undergo several physical health tests. Additionally, they were asked to respond to questionnaires that assessed their mental well-being. Furthermore, participants were requested to maintain an activity log for a continuous 14-day period, starting from the day after they signed up. They had the option to use either a provided mobile application or paper to record their activities.

METHODS

We evaluated multiple machine learning models to find the best-performing one. Subsequently, we conducted post-hoc analysis to extract the variable significance from the selected model to gain deeper insights into the factors influencing depression.

RESULTS

Logistic Regression was chosen as it exhibited superior performance across other models, with AUC of 0.807 ± 0.038, accuracy of 0.798 ± 0.048, specificity of 0.795 ± 0.061, sensitivity of 0.819 ± 0.097, NPV of 0.972 ± 0.013 and PPV of 0.359 ± 0.064. The top influential predictors identified in the model included loneliness, health indicator (i.e. frailty, eyesight, functional mobility), time spent on activities (i.e. staying home, doing exercises and visiting friends) and perceived income adequacy.

CONCLUSION

These findings have the potential to identify individuals at risk of depression and prioritize interventions based on the influential factors. The amount of time dedicated to daily activities emerges as a significant indicator of depression risk among middle-aged and elderly individuals, along with loneliness, physical health indicators and perceived income adequacy.

Use of Machine Learning Algorithms Based on Text, Audio, and Video Data in the Prediction of Anxiety and Posttraumatic Stress in General and Clinical Populations: A Systematic Review

Research in machine learning (ML) algorithms using natural behavior (i.e., text, audio, and video data) suggests that these techniques could contribute to personalization in psychology and psychiatry. However, a systematic review of the current state of the art is missing. Moreover, individual studies often target ML experts who may overlook potential clinical implications of their findings. In a narrative accessible to mental health professionals, we present a systematic review conducted in 5 psychology and 2 computer science databases. We included 128 studies that assessed the predictive power of ML algorithms using text, audio, and/or video data in the prediction of anxiety and posttraumatic stress disorder. Most studies (n = 87) were aimed at predicting anxiety, while the remainder (n = 41) focused on posttraumatic stress disorder. They were mostly published since 2019 in computer science journals and tested algorithms using text (n = 72) as opposed to audio or video. Studies focused mainly on general populations (n = 92) and less on laboratory experiments (n = 23) or clinical populations (n = 13). Methodological quality varied, as did reported metrics of the predictive power, hampering comparison across studies. Two-thirds of studies, which focused on both disorders, reported acceptable to very good predictive power (including high-quality studies only). The results of 33 studies were uninterpretable, mainly due to missing information. Research into ML algorithms using natural behavior is in its infancy but shows potential to contribute to diagnostics of mental disorders, such as anxiety and posttraumatic stress disorder, in the future if standardization of methods, reporting of results, and research in clinical populations are improved.

Digital Phenotyping of Geriatric Depression Using a Community-Based Digital Mental Health Monitoring Platform for Socially Vulnerable Older Adults and Their Community Caregivers: 6-Week Living Lab Single-Arm Pilot Study

BACKGROUND

Despite the increasing need for digital services to support geriatric mental health, the development and implementation of digital mental health care systems for older adults have been hindered by a lack of studies involving socially vulnerable older adult users and their caregivers in natural living environments.

OBJECTIVE

This study aims to determine whether digital sensing data on heart rate variability, sleep quality, and physical activity can predict same-day or next-day depressive symptoms among socially vulnerable older adults in their everyday living environments. In addition, this study tested the feasibility of a digital mental health monitoring platform designed to inform older adult users and their community caregivers about day-to-day changes in the health status of older adults.

METHODS

A single-arm, nonrandomized living lab pilot study was conducted with socially vulnerable older adults (n=25), their community caregivers (n=16), and a managerial social worker over a 6-week period during and after the COVID-19 pandemic. Depressive symptoms were assessed daily using the 9-item Patient Health Questionnaire via scripted verbal conversations with a mobile chatbot. Digital biomarkers for depression, including heart rate variability, sleep, and physical activity, were measured using a wearable sensor (Fitbit Sense) that was worn continuously, except during charging times. Daily individualized feedback, using traffic signal signs, on the health status of older adult users regarding stress, sleep, physical activity, and health emergency status was displayed on a mobile app for the users and on a web application for their community caregivers. Multilevel modeling was used to examine whether the digital biomarkers predicted same-day or next-day depressive symptoms. Study staff conducted pre- and postsurveys in person at the homes of older adult users to monitor changes in depressive symptoms, sleep quality, and system usability.

RESULTS

Among the 31 older adult participants, 25 provided data for the living lab and 24 provided data for the pre-post test analysis. The multilevel modeling results showed that increases in daily sleep fragmentation (P=.003) and sleep efficiency (P=.001) compared with one's average were associated with an increased risk of daily depressive symptoms in older adults. The pre-post test results indicated improvements in depressive symptoms (P=.048) and sleep quality (P=.02), but not in the system usability (P=.18).

CONCLUSIONS

The findings suggest that wearable sensors assessing sleep quality may be utilized to predict daily fluctuations in depressive symptoms among socially vulnerable older adults. The results also imply that receiving individualized health feedback and sharing it with community caregivers may help improve the mental health of older adults. However, additional in-person training may be necessary to enhance usability.

TRIAL REGISTRATION

ClinicalTrials.gov NCT06270121; https://clinicaltrials.gov/study/NCT06270121.

Association of Self-reported Depressed Mood and Alcohol or Tobacco Use Among Older Adults in India: A Study Based on Longitudinal Aging Study India Wave-1

Background

Little information exists about the association between alcohol and tobacco use and self-reported depressed mood, such as feeling sad, blue, or depressed days (SBDD), among older adults in India.

Aim

The aim of this study was to examine the association between alcohol and tobacco use and self-reported depressed mood with SBDD among older adults in India.

Methods

This study uses the Longitudinal Aging Study India (LASI) Wave 1 dataset of 10,487 respondents identified with self-reported mood disorders with SBDD. Descriptive statistics, bivariate, and multivariate models were performed.

Results

In total, 19.7% of persons above 45 years of age experienced SBDD for 2 weeks during the last 12 months. Compared to nonusers, those who used tobacco or alcohol reported higher symptoms of SBDD. Several factors related to alcohol (e.g., illicit alcohol) and tobacco (e.g., smokeless tobacco) indicate a statistically significant association with the prevalence of prolonged sadness or depression.

Conclusion

Analysis of LASI Wave 1 shows that lifestyle choices such as alcohol and tobacco use play a role in the burden and association of negative emotions such as SBDD among older adults in India.

Daily vitality fluctuations in older adults with depressive symptoms: A multilevel location-scale model

BACKGROUND

Examining the daily experiences of older adults with depression facilitates the development and application of personalized effective treatments for them. In previous clinical research on depression, traditional mean-based approaches have mainly been employed. However, the within-person residual variance as a random effect provides greater insight into the heterogeneity of daily experiences among geriatric samples.

OBJECTIVE

This study aimed to examine the relationship between depression and daily vitality in older adults. Specifically, it focused on the mean and residual variance of daily vitality measured by the Ecological Momentary Assessment (EMA).

METHODS

Data from 64 older adults aged 65 years or more, who participated in community welfare centers or retirees' associations, were used. Daily vitality was examined using EMA surveys for seven consecutive days (four random surveys per day). The data were analyzed using a location-scale model.

RESULTS

The intraclass correlation computed from the empty model for the EMA data was 0.488, indicating significant variances in daily vitality across time between individuals. Older adults with higher levels of depressive symptoms showed low mean levels of daily vitality and a large log-residual variance of daily vitality.

CONCLUSIONS

The findings from the current study suggest that individuals experiencing depression not only exhibit low vitality in their daily lives but also struggle to maintain stable levels of vitality in their lives. These insights could contribute to the facilitation and advancement of personalized interventions tailored for older adults.

Digital Literacy and Associated Factors in Older Adults Living in Urban South Korea: A Qualitative Study

This study aimed to explore digital literacy among community-dwelling older adults in urban South Korea. A semistructured interview guide was developed using the Digital Competence ( 2.0 framework, which emphasizes the competencies for full digital participation in five categories: information and data literacy, communication and collaboration, content creation, safety, and problem-solving. The data were analyzed using combined inductive and deductive content analysis. Inductive analysis identified three main categories: perceived ability to use digital technology, responses to digital technology, and contextual factors. In the results of deductive analysis, participants reported varying abilities in using digital technologies for information and data literacy, communication or collaboration, and problem-solving. However, their abilities were limited in handling the safety or security of digital technology and lacked in creating digital content. Responses to digital technology contain subcategories of perception (positive or negative) and behavior (trying or avoidance). Regarding contextual factors, aging-related physical and cognitive changes were identified as barriers to digital literacy. The influence of families or peers was viewed as both a facilitator and a barrier. Our participants recognized the importance of using digital devices to keep up with the trend of digitalization, but their digital literacy was mostly limited to relatively simple levels.

Designing daily-life research combining experience sampling method with parallel data

BACKGROUND

Ambulatory monitoring is gaining popularity in mental and somatic health care to capture an individual's wellbeing or treatment course in daily-life. Experience sampling method collects subjective time-series data of patients' experiences, behavior, and context. At the same time, digital devices allow for less intrusive collection of more objective time-series data with higher sampling frequencies and for prolonged sampling periods. We refer to these data as parallel data. Combining these two data types holds the promise to revolutionize health care. However, existing ambulatory monitoring guidelines are too specific to each data type, and lack overall directions on how to effectively combine them.

METHODS

Literature and expert opinions were integrated to formulate relevant guiding principles.

RESULTS

Experience sampling and parallel data must be approached as one holistic time series right from the start, at the study design stage. The fluctuation pattern and volatility of the different variables of interest must be well understood to ensure that these data are compatible. Data have to be collected and operationalized in a manner that the minimal common denominator is able to answer the research question with regard to temporal and disease severity resolution. Furthermore, recommendations are provided for device selection, data management, and analysis. Open science practices are also highlighted throughout. Finally, we provide a practical checklist with the delineated considerations and an open-source example demonstrating how to apply it.

CONCLUSIONS

The provided considerations aim to structure and support researchers as they undertake the new challenges presented by this exciting multidisciplinary research field.

Depression in Older Adults: Do Current DSM Diagnostic Criteria Really Fit?

OBJECTIVES

The great heterogeneity in symptoms and clinical signs of depression in older adults makes the current diagnostic criteria difficult to apply. This scoping review aims to provide an update on the relevance of each of the diagnostic criteria as defined in the DSM-5.

METHODS

In order to limit the risk of bias inherent in the study selection process, a priori inclusion and exclusion criteria were defined. Articles meeting these criteria were identified using a combination of search terms entered into PubMed, PsycINFO, PsycARTICLES and SocINDEX.

RESULTS

Of the 894 articles identified, 33 articles were selected. This review highlights a different presentation of depression in older adults. Beyond the first two DSM core criteria, some symptoms are more common in older adults: appetite change, sleep disturbance, psychomotor slowing, difficulty concentrating, indecisiveness, and fatigue.

CONCLUSIONS

This review provides an updated description of the clinical expression of depressive symptoms in the older population while highlighting current pending issues.

CLINICAL IMPLICATIONS

Somatic symptoms should be systematically considered in order to improve the diagnosis of depression in older adults, even if, in some cases, they may reflect symptoms of age-related illnesses.

Recent evidence and progress for developing precision nursing in symptomatology: A scoping review

AIM

To summarize the omics results of symptomatic research that can help nurses identify intervention targets and design precision interventions for pain, mental health, cognitive impairment, sleep disorder, fatigue, lymphedema, and quality of life, so as to provide a comprehensive summary of help and inspire to precision nursing.

METHODS

CINAHL, PubMed, Web of Science, and ScienceDirect databases were searched. Retrieval time was from January 2012 to December 2021. Symptomatology research applying omics that can be used to guide nurses in designing targeted interventions was included.

RESULTS

Forty-six studies were included in the final review. Symptomatology research that can be integrated with nursing science to develop precision nursing focused on pain, mental health, cognitive impairment, sleep disorder, fatigue, lymphedema, and quality of life. Most studies were related to cognitive impairment (n = 10; 21.74%), pain (n = 9; 19.57%), and mental health (n = 8; 17.39%). Moreover, the included studies involved various omics technologies, such as whole genome, epigenome, transcriptome, proteome, and metabolome.

CONCLUSION

The rapid development of various omic technologies promotes symptomatology research, which can help nurses fully understand the information of patients. Phenotypic characteristics and biomarkers shown in symptomatology research help nurses identify intervention targets and develop individualization interventions, so as to prevent and reduce symptoms and improve the quality of life.

IMPLICATION FOR NURSING AND HEALTH POLICY

This scoping review is the first synthesis of all peer-reviewed literature to summarize and provide important information and references from the omic results of symptomatology studies to develop precision nursing, highlighting the status and development of precision nursing. Nursing education policies should introduce the development and importance of precision nursing. Further research could consider investing more attention in precision nursing. Nursing researchers can carry out some studies applying omics technology to explore more biomarkers, helping guide the formulation of clinical intervention for symptoms.

Cuproptosis-related genes prediction feature and immune microenvironment in major depressive disorder

Background

Major depressive disorder (MDD) is a severe, unpredictable, ill-cured, relapsing neuropsychiatric disorder. A recently identified type of death called cuproptosis has been linked to a number of illnesses. However, the influence of cuproptosis-related genes in MDD has not been comprehensively assessed in prior study.

Aim

This investigation intends to shed light on the predictive value of cuproptosis-related genes for MDD and the immunological microenvironment.

Methods

GSE38206, GSE76826, GSE9653 databases were used to analyze cuproptosis regulators and immune characteristics. To find the genes that were differently expressed, weighted gene co-expression network analysis was employed. We calculated the effectiveness of the random forest model, generalized linear model, and limit gradient lifting to arrive at the best machine prediction model. Nomogram, calibration curve, and decision curve analysis were used to show the anticipated MDD's accuracy.

Results

This study found that there were activated immune responses and cuproptosis-related genes that were dysregulated in people with MDD compared to healthy controls. Considering the test performance of the learned model and validation on subsequent datasets, the RF model (including OSBPL8, VBP1, MTM1, ELK3, and SLC39A6) was considered to have the best discriminative performance. (AUC = 0.875).

Conclusion

Our study constructed a prediction model to predict MDD risk and clarified the potential connection between cuproptosis and MDD.

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.

Potential of electronic devices for detection of health problems in older adults at home: A systematic review and meta-analysis

OBJECTIVE

The aim of this review was to evaluate the overall diagnostic performance of e-devices for detection of health problems in older adults at home.

METHODS

A systematic review was conducted following the PRISMA-DTA guidelines.

RESULTS

31 studies were included with 24 studies included in meta-analysis. The included studies were divided into four categories according to the signals detected: physical activity (PA), vital signs (VS), electrocardiography (ECG) and other. The meta-analysis showed the pooled estimates of sensitivity and specificity were 0.94 and 0.98 respectively in the 'VS' group. The pooled sensitivity and specificity were 0.97 and 0.98 respectively in the 'ECG' group.

CONCLUSIONS

All kinds of e-devices perform well in diagnosing the common health problems. While ECG-based health problems detection system is more reliable than VS-based ones. For sole signal detection system has limitation in diagnosing specific health problems, more researches should focus on developing new systems combined of multiple signals.

A nurse-led mHealth intervention to alleviate depressive symptoms in older adults living alone in the community: A quasi-experimental study

BACKGROUND

The prevalence of geriatric depression has increased worldwide, becoming a major contributor to the burden of health care costs. Geriatric depression is difficult to detect in daily life because of its atypical presentation for each person. Therefore, there is an emerging need to develop personalised mHealth interventions for older adults with depression based on data from an ecological momentary assessment.

OBJECTIVE

To develop and evaluate the effect of a nurse-led mHealth intervention of geriatric depression in older adults living alone.

DESIGN

A quasi-experimental research design was used, and the study followed the transparent reporting of evaluations with a nonrandomised design statement.

SETTING

The nurse-led mHealth intervention was developed and evaluated in a community senior centre in Seoul, Korea.

PARTICIPANTS

Sixty-four older adults living alone with depressive symptoms were recruited between 1 October 2018 and 1 October 2019.

METHODS

Study participants were randomly assigned to the intervention or control groups by drawing lots. In the intervention group, nurses repeatedly assessed older adults' depressive symptoms using an ecological momentary assessment via a mobile tablet. The intervention consisted of weekly sessions, which included (1) standardised mHealth device training, (2) a nurse-led mHealth programme, and (3) art activities. The control group received care as usual. Intra- and inter-group differences were evaluated using paired t-tests and analysis of covariance was used to assess subjective depression symptoms. A linear mixed-model was used to analyse the relationship between groups and momentary scores over time.

RESULTS

The average age of the final sample was 76.2 years (SD = 6.06), 63.6 % (28/44) of whom were female. Compared with the control group (n = 23), the intervention group (n = 21) showed a decreased depression score (t = 4.041, p = .027). There was no statistical difference between the intervention and control groups based on traditional scales and the ecological momentary assessment. However, our data from the ecological momentary assessment captures clear fluctuating patterns across the days during the study, which traditional scales could not measure.

CONCLUSIONS

Most of the older adults successfully participated in a nurse-led mHealth intervention that included multiple components of a non-pharmacological approach to address depression. Mental health nurses should perform critical roles to personalise mHealth activities considering the older adult's autonomy and supportive decision-making, specifically when using high-technological intervention. Future research should maximise the methodological and clinical advantage of an ecological momentary assessment of geriatric depression.

REGISTRATION

Clinical Research Information Service number KCT0005073.

A Scoping Review of the Use of Machine Learning in Health Economics and Outcomes Research: Part 1-Data From Wearable Devices

OBJECTIVES

With the emerging use of machine learning (ML) techniques, there has been particular interest in using wearable data for health economics and outcomes research (HEOR). We aimed to understand the emerging patterns of how ML has been applied to wearable data in HEOR.

METHODS

We identified studies published in PubMed between January 2016 and March 2021. Studies that included at least 1 HEOR-related Medical Subject Headings term, applied an ML, and used wearable data were eligible for inclusion. Two reviewers abstracted information including ML application types and data on which ML was applied and analyzed them using descriptive analyses.

RESULTS

A total of 148 studies were identified from PubMed, among which 32 studies met the inclusion criteria. There has been an increase over time in the number of ML studies using wearable data. ML has been more frequently used for monitoring events in real time (78%) than to predict future events (22%). There has been a wide range of outcomes examined, ranging from general physical or mental health (24%) to more disease-specific outcomes (eg, disease incidence [19%] and progression [13%]) and treatment-related outcomes (eg, treatment adherence [9%] and outcomes [9%]). Data for ML models were more often derived from wearable devices with specific medical purposes (60%) than those without (40%).

CONCLUSION

There has been a wide range of applications of ML to wearable data. Both medical and nonmedical wearable devices have been used as a data source, showing the potential for providing rich data for ML studies in HEOR.

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.

Assessment and Disruption of Ruminative Episodes to Enhance Mobile Cognitive Behavioral Therapy Just-in-Time Adaptive Interventions in Clinical Depression: Pilot Randomized Controlled Trial

BACKGROUND

A just-in-time adaptive intervention (JITAI) is "designed to address the dynamically changing needs of individuals via the provision of the type or amount of support needed, at the right time when needed." If and how rumination-focused cognitive behavioral therapy (RFCBT), the gold standard, blocks emotional cascades underlying rumination is unclear. Furthermore, cognitive behavioral therapy has been successfully used as a mobile variant, but RFCBT has not been adapted for a mobile variant (mobile RFCBT [MRFCBT]) or for a JITAI variant.

OBJECTIVE

This study aimed to pilot-test a fully automated JITAI leveraging RFCBT and ways to identify and block cascading depressive rumination.

METHODS

Patients in therapy for clinical depression were recruited for a randomized controlled trial (RCT). After consenting to be part of the RCT, they were randomly assigned to either of the 2 mobile versions of the RFCBT conditions personalized to the individual's rumination timing patterns (JITAI-MRFCBT) or a no-treatment control condition through a double-blind procedure. Although the initial design was to have a 3-armed trial with 2 JITAI conditions (a JITAI and a narrative JITAI condition), we later opted to collapse those 2 conditions into 1 JITAI condition because of the low number of participants. All participants were recruited and participated through their smartphones, receiving 5 SMS text message reminders on each of the 35 days to self-report their rumination-related symptoms (eg, rumination episodes and duration). In the JITAI-MRFCBT condition, they also received treatment materials. The first 7 days provided a rumination baseline, and the last 7 days provided a postintervention rumination value. In total, 42% (25/59) of volunteers were eligible and provided their phone numbers, 20% (5/25) of whom never replied to the SMS text message reminding them to start the RCT. A total of 90% (18/20) of volunteers completed it (ie, finishing, as prespecified, 80% of the questionnaires and training tasks) and, therefore, were included in the analysis.

RESULTS

Using independent 2-tailed t tests with bootstrapping, results showed that participants in the JITAI-MRFCBT condition, compared with those in the control condition, reported a greater reduction in counts of rumination episodes (mean -25.28, SD 14.50 vs mean 1.44, SD 4.12, P<.001) and greater reduced average time (minutes) spent in rumination (mean -21.53, SD 17.6 vs mean 1.47, SD 1.5; P=.04). Results also suggest that, compared with those in the control group, those in treatment reduced ruminative carryover from one episode to the next.

CONCLUSIONS

The results suggest that JITAI-MRFCBT may reduce negative rumination by providing RFCBT just in time following rumination, thereby blocking the next rumination episode using the same trigger. This study supports a subsequent, full-scale JITAI and the importance of leveraging mobile smartphone technology with MRFCBT to curb depressive symptoms.

TRIAL REGISTRATION

ClinicalTrials.gov NCT04554706; https://clinicaltrials.gov/ct2/show/NCT04554706.

Combining actigraphy and experience sampling to assess physical activity and sleep in patients with psychosis: A feasibility study

BACKGROUND

Sleep disorders and reduced physical activity are common in patients with psychosis and can be related to health-related outcomes such as symptomatology and functioning. Mobile health technologies and wearable sensor methods enable continuous and simultaneous monitoring of physical activity, sleep, and symptoms in one's day-to-day environment. Only a few studies have applied simultaneous assessment of these parameters. Therefore, we aimed to examine the feasibility of the simultaneous monitoring of physical activity, sleep, and symptoms and functioning in psychosis.

METHODS

Thirty three outpatients diagnosed with a schizophrenia or other psychotic disorder used an actigraphy watch and experience sampling method (ESM) smartphone app for 7 consecutive days to monitor physical activity, sleep, symptoms, and functioning. Participants wore the actigraphy watch during day and night and completed multiple short questionnaires (eight daily, one morning, and one evening) on their phone. Hereafter they completed evaluation questionnaires.

RESULTS

Of the 33 patients (25 male), 32 (97.0%) used the ESM and actigraphy during the instructed timeframe. ESM response was good: 64.0% for the daily, 90.6% for morning, and 82.6% for evening questionnaire(s). Participants were positive about the use of actigraphy and ESM.

CONCLUSION

The combination of wrist-worn actigraphy and smartphone-based ESM is feasible and acceptable in outpatients with psychosis. These novel methods can help both clinical practice and future research to gain more valid insight into physical activity and sleep as biobehavioral markers linked to psychopathological symptoms and functioning in psychosis. This can be used to investigate relationships between these outcomes and thereby improve individualized treatment and prediction.

Prediction models for depression risk among older adults: systematic review and critical appraisal

OBJECTIVE

To provide an overview of prediction models for the risk of major depressive disorder (MDD) among older adults.

METHODS

We conducted a systematic review combined with a meta-analysis and critical appraisal of published studies on existing geriatric depression risk models.

RESULTS

The systematic search screened 23,378 titles and abstracts; 14 studies including 20 prediction models were included. A total of 16 predictors were selected in the final model at least twice. Age, physical health, and cognitive function were the most common predictors. Only one model was externally validated, two models were presented with a complete equation, and five models examined the calibration. We found substantial heterogeneity in predictor and outcome definitions across models; important methodological information was often missing. All models were rated at high or unclear risk of bias, primarily due to methodological limitations. The pooled C-statistics of 12 prediction models was 0.83 (95%CI=0.77-0.89).

CONCLUSION

The usefulness of all models remains unclear due to several methodological limitations. Future studies should focus on methodological quality and external validation of depression risk prediction models.

Late-life depression: Epidemiology, phenotype, pathogenesis and treatment before and during the COVID-19 pandemic

Late-life depression (LLD) is one of the most common mental disorders among the older adults. Population aging, social stress, and the COVID-19 pandemic have significantly affected the emotional health of older adults, resulting in a worldwide prevalence of LLD. The clinical phenotypes between LLD and adult depression differ in terms of symptoms, comorbid physical diseases, and coexisting cognitive impairments. Many pathological factors such as the imbalance of neurotransmitters, a decrease in neurotrophic factors, an increase in β-amyloid production, dysregulation of the hypothalamic-pituitary-adrenal axis, and changes in the gut microbiota, are allegedly associated with the onset of LLD. However, the exact pathogenic mechanism underlying LLD remains unclear. Traditional selective serotonin reuptake inhibitor therapy results in poor responsiveness and side effects during LLD treatment. Neuromodulation therapies and complementary and integrative therapies have been proven safe and effective for the treatment of LLD. Importantly, during the COVID-19 pandemic, modern digital health intervention technologies, including socially assistive robots and app-based interventions, have proven to be advantageous in providing personal services to patients with LLD.

The Case for the Patient-Centric Development of Novel Digital Sleep Assessment Tools in Major Depressive Disorder

Background

Depression imposes a major burden on public health as the leading cause of disability worldwide. Sleep disturbance is a core symptom of depression that affects the vast majority of patients. Nonetheless, it is frequently not resolved by depression treatment and may even be worsened through some pharmaceutical interventions. Disturbed sleep negatively impact patients' quality of life, and persistent sleep disturbance increases the risk of recurrence, relapse, and even suicide. However, the development of novel treatments that might improve sleep problems is hindered by the lack of reliable low-burden objective measures that can adequately assess disturbed sleep in this population.

Summary

Developing improved digital measurement tools that are fit for use in clinical trials for major depressive disorder could promote the inclusion of sleep as a focus for treatment, clinical drug development, and research. This perspective piece explores the path toward the development of novel digital measures, reviews the existing evidence on the meaningfulness of sleep in depression, and summarizes existing methods of sleep assessments, including the use of digital health technologies.

Key Messages

Our objective was to make a clear call to action and path forward for the qualification of new digital outcome measures which would enable assessment of sleep disturbance as an aspect of health that truly matters to patients, promoting sleep as an important outcome for clinical development, and ultimately ensure that disturbed sleep will not remain the forgotten symptom of depression.

Developing a Multimodal Monitoring System for Geriatric Depression: A Feasibility Study

The Internet of Medical Things is promising for monitoring depression symptoms. Therefore, it is necessary to develop multimodal monitoring systems tailored for elderly individuals with high feasibility and usability for further research and practice. This study comprised two phases: (1) methodological development of the system; and (2) system validation to evaluate its feasibility. We developed a system that includes a smartphone for facial and verbal expressions, a smartwatch for activity and heart rate monitoring, and an ecological momentary assessment application. A sample of 21 older Koreans aged 65 years and more was recruited from a community center. The 4-week data were collected for each participant (n = 19) using self-report questionnaires, wearable devices, and interviews and were analyzed using mixed methods. The depressive group (n = 6) indicated lower user acceptance relative to the nondepressive group (n = 13). Both groups experienced positive emotions, had regular life patterns, increased their self-interest, and stated that a system could disturb their daily activities. However, they were interested in learning new technologies and actively monitored their mental health status. Our multimodal monitoring system shows potential as a feasible and useful measure for acquiring mental health information about geriatric depression.

Questionnaire-free machine-learning method to predict depressive symptoms among community-dwelling older adults

The 15-item Geriatric Depression Scale (GDS-15) is widely used to screen for depressive symptoms among older populations. This study aimed to develop and validate a questionnaire-free, machine-learning model as an alternative triage test for the GDS-15 among community-dwelling older adults. The best models were the random forest (RF) and deep-insight visible neural network by internal validation, but both performances were undifferentiated by external validation. The AUROC of the RF model was 0.619 (95% CI 0.610 to 0.627) for the external validation set with a non-local ethnic group. Our triage test can allow healthcare professionals to preliminarily screen for depressive symptoms in older adults without using a questionnaire. If the model shows positive results, then the GDS-15 can be used for follow-up measures. This preliminary screening will save a lot of time and energy for healthcare providers and older adults, especially those persons who are illiterate.

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.

A Multirobot System in an Assisted Home Environment to Support the Elderly in Their Daily Lives

The increasing isolation of the elderly both in their own homes and in care homes has made the problem of caring for elderly people who live alone an urgent priority. This article presents a proposed design for a heterogeneous multirobot system consisting of (i) a small mobile robot to monitor the well-being of elderly people who live alone and suggest activities to keep them positive and active and (ii) a domestic mobile manipulating robot that helps to perform household tasks. The entire system is integrated in an automated home environment (AAL), which also includes a set of low-cost automation sensors, a medical monitoring bracelet and an Android application to propose emotional coaching activities to the person who lives alone. The heterogeneous system uses ROS, IoT technologies, such as Node-RED, and the Home Assistant Platform. Both platforms with the home automation system have been tested over a long period of time and integrated in a real test environment, with good results. The semantic segmentation of the navigation and planning environment in the mobile manipulator for navigation and movement in the manipulation area facilitated the tasks of the later planners. Results about the interactions of users with the applications are presented and the use of artificial intelligence to predict mood is discussed. The experiments support the conclusion that the assistance robot correctly proposes activities, such as calling a relative, exercising, etc., during the day, according to the user's detected emotional state, making this is an innovative proposal aimed at empowering the elderly so that they can be autonomous in their homes and have a good quality of life.

Personalized Prediction of Behaviors and Experiences: An Idiographic Person-Situation Test

A longstanding goal of psychology is to predict the things that people do and feel, but tools to accurately predict future behaviors and experiences remain elusive. In the present study, we used intensive longitudinal data (N = 104 college-age adults at a midwestern university; total assessments = 5,971) and three machine-learning approaches to investigate the degree to which three future behaviors and experiences-loneliness, procrastination, and studying-could be predicted from past psychological (i.e., personality and affective states), situational (i.e., objective situations and psychological situation cues), and time (i.e., trends, diurnal cycles, time of day, and day of the week) phenomena from an idiographic, person-specific perspective. Rather than pitting persons against situations, such an approach allows psychological phenomena, situations, and time to jointly predict future behaviors and experiences. We found (a) a striking degree of prediction accuracy across participants, (b) that a majority of participants' future behaviors are predicted by both person and situation features, and (c) that the most important features vary greatly across people.

Development of an integrated fatigue measurement system for construction workers: a feasibility study

Background

Construction workers working in physically and mentally challenging environments experience high levels of occupational fatigue, which is the primary cause of industrial accidents and illnesses. Therefore, it is very important to measure fatigue in real time to manage the safety and health of construction workers. This study presents a novel approach for simultaneously measuring the subjective and objective fatigue of construction workers using ecological momentary assessment (EMA) and smartwatches. Due to the complexity and diversity of construction site environments, it is necessary to examine whether data collection using smartwatches is suitable in actual construction sites. This study aims to examine the feasibility of the integrated fatigue measurement method.

Methods

This study comprised two phases: (1) development of an integrated fatigue measurement system for construction workers, and (2) a validation study to evaluate the method’s feasibility based on sensor data acquisition, EMA compliance, and feedback from construction workers in the field (N = 80). Three days of biometric data were collected through sensors embedded in the smartwatches for objective fatigue measurement, including heart rate, accelerometer, and gyroscope data. Two types of self-reported data regarding each worker’s fatigue were collected through a researcher-developed EMA application. The acceptability and usability of this system were examined based on the researchers’ observations and unstructured interviews.

Results

Based on the standardized self-report questionnaire scores, participants were classified into high (n = 35, 43.75%) and low (n = 45, 56.25%) fatigue groups for comparison. The quantitative outcomes did not show a statistically significant difference between the two fatigue groups. Both groups experienced positive emotions and were able to recognize their health condition at the time of self-reporting, but stated that responding to this measurement system could be burdensome.

Conclusions

This feasibility study provides a unique understanding of the applications of EMA and smartwatches for safety management in the construction workforce. The developed measurement system shows potential for monitoring fatigue based on the real-time collection of relevant data. It is expected that by expanding this integrated system through further research and onsite application, the health and safety of construction workers can be improved.

Machine Learning on Early Diagnosis of Depression

To review the recent progress of machine learning for the early diagnosis of depression (major depressive disorder). The source of data was 32 original studies in the Web of Science. The search terms were "depression" (title) and "random forest" (abstract). The eligibility criteria were the dependent variable of depression, the interventions of machine learning (the decision tree, the naïve Bayesian, the random forest, the support vector machine and/or the artificial neural network), the outcomes of accuracy and/or the area under the receiver operating characteristic curve (AUC) for the early diagnosis of depression, the publication year of 2000 or later, the publication language of English and the publication journal of SCIE/SSCI. Different machine learning methods would be appropriate for different types of data for the early diagnosis of depression, e.g., logistic regression, the random forest, the support vector machine and/or the artificial neural network in the case of numeric data, the random forest in the case of genomic data. Their performance measures reported varied within 60.1-100.0 for accuracy and 64.0-96.0 for the AUC. Machine learning provides an effective, non-invasive decision support system for early diagnosis of depression.

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.

Exploring the digital footprint of depression: a PRISMA systematic literature review of the empirical evidence

BACKGROUND

This PRISMA systematic literature review examined the use of digital data collection methods (including ecological momentary assessment [EMA], experience sampling method [ESM], digital biomarkers, passive sensing, mobile sensing, ambulatory assessment, and time-series analysis), emphasizing on digital phenotyping (DP) to study depression. DP is defined as the use of digital data to profile health information objectively.

AIMS

Four distinct yet interrelated goals underpin this study: (a) to identify empirical research examining the use of DP to study depression; (b) to describe the different methods and technology employed; (c) to integrate the evidence regarding the efficacy of digital data in the examination, diagnosis, and monitoring of depression and (d) to clarify DP definitions and digital mental health records terminology.

RESULTS

Overall, 118 studies were assessed as eligible. Considering the terms employed, "EMA", "ESM", and "DP" were the most predominant. A variety of DP data sources were reported, including voice, language, keyboard typing kinematics, mobile phone calls and texts, geocoded activity, actigraphy sensor-related recordings (i.e., steps, sleep, circadian rhythm), and self-reported apps' information. Reviewed studies employed subjectively and objectively recorded digital data in combination with interviews and psychometric scales.

CONCLUSIONS

Findings suggest links between a person's digital records and depression. Future research recommendations include (a) deriving consensus regarding the DP definition and (b) expanding the literature to consider a person's broader contextual and developmental circumstances in relation to their digital data/records.

Polysomnographic identification of anxiety and depression using deep learning

Anxiety and depression are common psychiatric conditions associated with significant morbidity and healthcare costs. Sleep is an evolutionarily conserved health state. Anxiety and depression have a bidirectional relationship with sleep. This study reports on the use of analysis of polysomnographic data using deep learning methods to detect the presence of anxiety and depression. Polysomnography data on 940 patients performed at an academic sleep center during the 3-year period from 01/01/2016 to 12/31/2018 were identified for analysis. The data were divided into 3 subgroups: 205 patients with Anxiety/Depression, 349 patients with no Anxiety/Depression, and 386 patients with likely Anxiety/Depression. The first two subgroups were used for training and testing of the deep learning algorithm, and the third subgroup was used for external validation of the resulting model. Hypnograms were constructed via automatic sleep staging, with the 12-channel PSG data being transformed into three-channel RGB (red, green, blue channels) images for analysis. Composite patient images were generated and utilized for training the Xception model, which provided a validation set accuracy of 0.9782 on the ninth training epoch. In the independent test set, the model achieved a high accuracy (0.9688), precision (0.9533), recall (0.9630), and F1-score (0.9581). Classification performance of most other mainstream deep learning models was comparable. These findings suggest that machine learning techniques have the potential to accurately detect the presence of anxiety and depression from analysis of sleep study data. Further studies are needed to explore the utility of these techniques in the field of psychiatry.

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.

App-Based Ecological Momentary Assessment to Enhance Clinical Care for Postpartum Depression: Pilot Acceptability Study

Background

Wearable tracking devices and mobile health technology are increasingly used in an effort to enhance clinical care and the delivery of personalized medical treatment. Postpartum depression is the most frequently diagnosed complication of childbirth; however, significant gaps in screening and treatment remain.

Objective

This study aims to investigate the clinical utility, predictive ability, and acceptability of using ecological momentary assessment to collect daily mood, sleep, and activity data through the use of an Apple Watch and mobile app among women with postpartum depression.

Methods

This was a pilot study consisting of 3 in-person research visits over the course of a 6-week enrollment period. Questionnaires to assess depression, anxiety, and maternal functioning were periodically collected, along with daily self-reported symptoms and passively collected physiological data via an Apple Watch. Feedback was collected from study participants and the study clinician to determine the utility and acceptability of daily tracking. Logistic regression was used to determine whether mood scores in the 2 weeks before a visit predicted scores at follow-up. Compliance with daily assessments was also measured.

Results

Of the 26 women enrolled, 23 (88%) completed the 6-week study period. On average, the participants completed 67% (34.4/51.5 days) of all active daily assessments and 74% (38/51.5 days) of all passive measures. Furthermore, all 23 participants completed the 3 required visits with the research team. Predictive correlations were found between self-reported mood and Edinburgh Postnatal Depression Scale score at follow-up, self-reported anxiety and EDPS, and sleep quality and Edinburgh Postnatal Depression Scale.

Conclusions

Using ecological momentary assessment to track daily symptoms of postpartum depression using a wearable device was largely endorsed as acceptable and clinically useful by participants and the study clinician and could be an innovative solution to increase care access during the COVID-19 pandemic.

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.

Using Momentary Assessment and Machine Learning to Identify Barriers to Self-management in Type 1 Diabetes: Observational Study

BACKGROUND

For adolescents living with type 1 diabetes (T1D), completion of multiple daily self-management tasks, such as monitoring blood glucose and administering insulin, can be challenging because of psychosocial and contextual barriers. These barriers are hard to assess accurately and specifically by using traditional retrospective recall. Ecological momentary assessment (EMA) uses mobile technologies to assess the contexts, subjective experiences, and psychosocial processes that surround self-management decision-making in daily life. However, the rich data generated via EMA have not been frequently examined in T1D or integrated with machine learning analytic approaches.

OBJECTIVE

The goal of this study is to develop a machine learning algorithm to predict the risk of missed self-management in young adults with T1D. To achieve this goal, we train and compare a number of machine learning models through a learned filtering architecture to explore the extent to which EMA data were associated with the completion of two self-management behaviors: mealtime self-monitoring of blood glucose (SMBG) and insulin administration.

METHODS

We analyzed data from a randomized controlled pilot study using machine learning-based filtering architecture to investigate whether novel information related to contextual, psychosocial, and time-related factors (ie, time of day) relate to self-management. We combined EMA-collected contextual and insulin variables via the MyDay mobile app with Bluetooth blood glucose data to construct machine learning classifiers that predicted the 2 self-management behaviors of interest.

RESULTS

With 1231 day-level SMBG frequency counts for 45 participants, demographic variables and time-related variables were able to predict whether daily SMBG was below the clinical threshold of 4 times a day. Using the 1869 data points derived from app-based EMA data of 31 participants, our learned filtering architecture method was able to infer nonadherence events with high accuracy and precision. Although the recall score is low, there is high confidence that the nonadherence events identified by the model are truly nonadherent.

CONCLUSIONS

Combining EMA data with machine learning methods showed promise in the relationship with risk for nonadherence. The next steps include collecting larger data sets that would more effectively power a classifier that can be deployed to infer individual behavior. Improvements in individual self-management insights, behavioral risk predictions, enhanced clinical decision-making, and just-in-time patient support in diabetes could result from this type of approach.

Identifying Predictors of Opioid Overdose Death at a Neighborhood Level With Machine Learning

Predictors of opioid overdose death in neighborhoods are important to identify, both to understand characteristics of high-risk areas and to prioritize limited prevention and intervention resources. Machine learning methods could serve as a valuable tool for identifying neighborhood-level predictors. We examined statewide data on opioid overdose death from Rhode Island (log-transformed rates for 2016-2019) and 203 covariates from the American Community Survey for 742 US Census block groups. The analysis included a least absolute shrinkage and selection operator (LASSO) algorithm followed by variable importance rankings from a random forest algorithm. We employed double cross-validation, with 10 folds in the inner loop to train the model and 4 outer folds to assess predictive performance. The ranked variables included a range of dimensions of socioeconomic status, including education, income and wealth, residential stability, race/ethnicity, social isolation, and occupational status. The R2 value of the model on testing data was 0.17. While many predictors of overdose death were in established domains (education, income, occupation), we also identified novel domains (residential stability, racial/ethnic distribution, and social isolation). Predictive modeling with machine learning can identify new neighborhood-level predictors of overdose in the continually evolving opioid epidemic and anticipate the neighborhoods at high risk of overdose mortality.

Stress research during the COVID-19 pandemic and beyond

The COVID-19 pandemic confronts stress researchers in psychology and neuroscience with unique challenges. Widely used experimental paradigms such as the Trier Social Stress Test feature physical social encounters to induce stress by means of social-evaluative threat. As lockdowns and contact restrictions currently prevent in-person meetings, established stress induction paradigms are often difficult to use. Despite these challenges, stress research is of pivotal importance as the pandemic will likely increase the prevalence of stress-related mental disorders. Therefore, we review recent research trends like virtual reality, pre-recordings and online adaptations regarding their usefulness for established stress induction paradigms. Such approaches are not only crucial for stress research during COVID-19 but will likely stimulate the field far beyond the pandemic. They may facilitate research in new contexts and in homebound or movement-restricted participant groups. Moreover, they allow for new experimental variations that may advance procedures as well as the conceptualization of stress itself. While posing challenges for stress researchers undeniably, the COVID-19 pandemic may evolve into a driving force for progress eventually.

Using Ecological Momentary Assessment to Study the Development of COVID-19 Worries in Sweden: Longitudinal Study

Background

The foray of COVID-19 around the globe has certainly instigated worries in many people, and lockdown measures may well have triggered more specific worries. Sweden, more than other countries, relied on voluntary measures to fight the pandemic. This provides a particularly interesting context to assess people’s reactions to the threat of the pandemic.

Objective

The general aim of this study was to better understand the worried reactions to the virus and the associated lockdown measures. As there have been very few longitudinal studies in this area published to date, development of feelings of worry over time was analyzed over a longer range than in previous research. Affective variables, worry in particular, were included because most of the research in this field has focused on cognitive variables. To employ new methodology, ecological momentary assessment was used for data collection and a multilevel modeling approach was adopted for data analysis.

Methods

Results were based on an unbalanced panel sample of 260 Swedish participants filling in 3226 interview questionnaires by smartphone over a 7-week period in 2020 during the rapid rise of cases in the early phase of the pandemic. Causal factors considered in this study included the perceived severity of an infection, susceptibility of a person to the threat posed by the virus, perceived efficacy of safeguarding measures, and assessment of government action against the spread of COVID-19. The effect of these factors on worries was traced in two analytical steps: the effects at the beginning of the study and the effect on the trend during the study.

Results

The level of general worry related to COVID-19 was modest (mean 6.67, SD 2.54 on an 11-point Likert scale); the increase during the study period was small, but the interindividual variation of both the worry level and its increase over time was large. Findings confirmed that the hypothesized causal factors (severity of infection, susceptibility to the threat of the virus, efficacy of safeguarding, and assessment of government preventive action) did indeed affect the level of worry.

Conclusions

The results confirmed earlier research in a very special case and demonstrated the usefulness of a different study design, which takes a longitudinal perspective, and a new type of data analysis borrowed from multilevel study design.

Robotic-Based Well-Being Monitoring and Coaching System for the Elderly in Their Daily Activities

The increasingly ageing population and the tendency to live alone have led science and engineering researchers to search for health care solutions. In the COVID 19 pandemic, the elderly have been seriously affected in addition to suffering from isolation and its associated and psychological consequences. This paper provides an overview of the RobWell (Robotic-based Well-Being Monitoring and Coaching System for the Elderly in their Daily Activities) system. It is a system focused on the field of artificial intelligence for mood prediction and coaching. This paper presents a general overview of the initially proposed system as well as the preliminary results related to the home automation subsystem, autonomous robot navigation and mood estimation through machine learning prior to the final system integration, which will be discussed in future works. The main goal is to improve their mental well-being during their daily household activities. The system is composed of ambient intelligence with intelligent sensors, actuators and a robotic platform that interacts with the user. A test smart home system was set up in which the sensors, actuators and robotic platform were integrated and tested. For artificial intelligence applied to mood prediction, we used machine learning to classify several physiological signals into different moods. In robotics, it was concluded that the ROS autonomous navigation stack and its autodocking algorithm were not reliable enough for this task, while the robot’s autonomy was sufficient. Semantic navigation, artificial intelligence and computer vision alternatives are being sought.

[The predictable human : Possibilities and risks of AI-based prediction of cognitive abilities, personality traits and mental illnesses]

New approaches to the use of artificial intelligence (AI) to analyze data from neuroimaging but also passively collected data from so-called wearables, such as smartphones or smartwatches, as well as data that can be extracted from social media and other online activities, already make it possible to predict cognitive abilities, personality traits, and mental illnesses, as well as to reveal acute mental states. In this article, we explain the methodological concepts behind these current developments, illuminate the possibilities and limitations, and address ethical and social aspects arising from the use.

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.

An informatics approach to examine decision-making impairments in the daily life of individuals with depression

Mental health informatics studies methods that collect, model, and interpret a wide variety of data to generate useful information with theoretical or clinical relevance to improve mental health and mental health care. This article presents a mental health informatics approach that is based on the decision-making theory of depression, whereby daily life data from a natural sequential decision-making task are collected and modeled using a reinforcement learning method. The model parameters are then estimated to uncover specific aspects of decision-making impairment in individuals with depression. Empirical results from a pilot study conducted to examine decision-making impairments in the daily lives of university students with depression are presented to illustrate this approach. Future research can apply and expand on this approach to investigate a variety of daily life situations and psychiatric conditions and to facilitate new informatics applications. Using this approach in mental health research may generate useful information with both theoretical and clinical relevance and high ecological validity.

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.

Screening for depression in older adults with cognitive impairment in the homecare setting: a systematic review

OBJECTIVE

Previous systematic reviews have examined depression screening in older adults with cognitive impairment (CI) in outpatient and inpatient clinics, nursing homes, and residential care. Despite an increasing number of older adults with CI receiving care in their homes, less is known about best depression screening practices in homecare. The objective of this review is to identify evidence-based practices for depression screening for individuals with CI receiving homecare by assessing tool performance and establishing the current evidence for screening practices in this setting.

METHODS

This review is registered under PROSPERO (ID: CRD42018110243). A systematic search was conducted using MEDLINE, EMBASE, Health and Psychosocial Abstracts, PsycINFO and CINAHL. The following criteria were used: assessment of depression at home in older adults (>55 years) with CI, where performance outcomes of the depression screening tool were reported.

RESULTS

Of 5,453 studies, only three met eligibility criteria. These studies evaluated the Patient Health Questionnaire (n = 236), the Geriatric Depression Scale (n = 79) and the Mental Health Index (n = 1,444) in older adults at home with and without CI. Psychometric evaluation demonstrated moderate performance in the subsamples of people with CI.

CONCLUSION

At present, there is insufficient evidence to support best practices in screening for depression in people with CI in homecare.