Predicting the severity of mood and neuropsychiatric symptoms from digital biomarkers using wearable physiological data and deep learning.

Neuropsychiatric symptoms (NPS) and mood disorders are common in individuals with mild cognitive impairment (MCI) and increase the risk of progression to dementia. Wearable devices collecting physiological and behavioral data can help in remote, passive, and continuous monitoring of moods and NPS, overcoming limitations and inconveniences of current assessment methods. In this longitudinal study, we examined the predictive ability of digital biomarkers based on sensor data from a wrist-worn wearable to determine the severity of NPS and mood disorders on a daily basis in older adults with predominant MCI. In addition to conventional physiological biomarkers, such as heart rate variability and skin conductance levels, we leveraged deep-learning features derived from physiological data using a self-supervised convolutional autoencoder. Models combining common digital biomarkers and deep features predicted depression severity scores with a correlation of r = 0.73 on average, total severity of mood disorder symptoms with r = 0.67, and mild behavioral impairment scores with r = 0.69 in the study population. Our findings demonstrated the potential of physiological biomarkers collected from wearables and deep learning methods to be used for the continuous and unobtrusive assessments of mental health symptoms in older adults, including those with MCI. TRIAL REGISTRATION: This trial was registered with ClinicalTrials.gov (NCT05059353) on September 28, 2021, titled "Effectiveness and Safety of a Digitally Based Multidomain Intervention for Mild Cognitive Impairment".

Predicting cognitive scores from wearable-based digital physiological features using machine learning: data from a clinical trial in mild cognitive impairment.

BACKGROUND: Continuous assessment and remote monitoring of cognitive function in individuals with mild cognitive impairment (MCI) enables tracking therapeutic effects and modifying treatment to achieve better clinical outcomes. While standardized neuropsychological tests are inconvenient for this purpose, wearable sensor technology collecting physiological and behavioral data looks promising to provide proxy measures of cognitive function. The objective of this study was to evaluate the predictive ability of digital physiological features, based on sensor data from wrist-worn wearables, in determining neuropsychological test scores in individuals with MCI. METHODS: We used the dataset collected from a 10-week single-arm clinical trial in older adults (50-70 years old) diagnosed with amnestic MCI (N = 30) who received a digitally delivered multidomain therapeutic intervention. Cognitive performance was assessed before and after the intervention using the Neuropsychological Test Battery (NTB) from which composite scores were calculated (executive function, processing speed, immediate memory, delayed memory and global cognition). The Empatica E4, a wrist-wearable medical-grade device, was used to collect physiological data including blood volume pulse, electrodermal activity, and skin temperature. We processed sensors' data and extracted a range of physiological features. We used interpolated NTB scores for 10-day intervals to test predictability of scores over short periods and to leverage the maximum of wearable data available. In addition, we used individually centered data which represents deviations from personal baselines. Supervised machine learning was used to train models predicting NTB scores from digital physiological features and demographics. Performance was evaluated using "leave-one-subject-out" and "leave-one-interval-out" cross-validation. RESULTS: The final sample included 96 aggregated data intervals from 17 individuals. In total, 106 digital physiological features were extracted. We found that physiological features, especially measures of heart rate variability, correlated most strongly to the executive function compared to other cognitive composites. The model predicted the actual executive function scores with correlation r = 0.69 and intra-individual changes in executive function scores with r = 0.61. CONCLUSIONS: Our findings demonstrated that wearable-based physiological measures, primarily HRV, have potential to be used for the continuous assessments of cognitive function in individuals with MCI.

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

BACKGROUND: Depression is a prevalent mental disorder that is undiagnosed and untreated in half of all cases. Wearable activity trackers collect fine-grained sensor data characterizing the behavior and physiology of users (ie, digital biomarkers), which could be used for timely, unobtrusive, and scalable depression screening. OBJECTIVE: The aim of this study was to examine the predictive ability of digital biomarkers, based on sensor data from consumer-grade wearables, to detect risk of depression in a working population. METHODS: This was a cross-sectional study of 290 healthy working adults. Participants wore Fitbit Charge 2 devices for 14 consecutive days and completed a health survey, including screening for depressive symptoms using the 9-item Patient Health Questionnaire (PHQ-9), at baseline and 2 weeks later. We extracted a range of known and novel digital biomarkers characterizing physical activity, sleep patterns, and circadian rhythms from wearables using steps, heart rate, energy expenditure, and sleep data. Associations between severity of depressive symptoms and digital biomarkers were examined with Spearman correlation and multiple regression analyses adjusted for potential confounders, including sociodemographic characteristics, alcohol consumption, smoking, self-rated health, subjective sleep characteristics, and loneliness. Supervised machine learning with statistically selected digital biomarkers was used to predict risk of depression (ie, symptom severity and screening status). We used varying cutoff scores from an acceptable PHQ-9 score range to define the depression group and different subsamples for classification, while the set of statistically selected digital biomarkers remained the same. For the performance evaluation, we used k-fold cross-validation and obtained accuracy measures from the holdout folds. RESULTS: A total of 267 participants were included in the analysis. The mean age of the participants was 33 (SD 8.6, range 21-64) years. Out of 267 participants, there was a mild female bias displayed (n=170, 63.7%). The majority of the participants were Chinese (n=211, 79.0%), single (n=163, 61.0%), and had a university degree (n=238, 89.1%). We found that a greater severity of depressive symptoms was robustly associated with greater variation of nighttime heart rate between 2 AM and 4 AM and between 4 AM and 6 AM; it was also associated with lower regularity of weekday circadian rhythms based on steps and estimated with nonparametric measures of interdaily stability and autocorrelation as well as fewer steps-based daily peaks. Despite several reliable associations, our evidence showed limited ability of digital biomarkers to detect depression in the whole sample of working adults. However, in balanced and contrasted subsamples comprised of depressed and healthy participants with no risk of depression (ie, no or minimal depressive symptoms), the model achieved an accuracy of 80%, a sensitivity of 82%, and a specificity of 78% in detecting subjects at high risk of depression. CONCLUSIONS: Digital biomarkers that have been discovered and are based on behavioral and physiological data from consumer wearables could detect increased risk of depression and have the potential to assist in depression screening, yet current evidence shows limited predictive ability. Machine learning models combining these digital biomarkers could discriminate between individuals with a high risk of depression and individuals with no risk.

Site-Dependent Peculiarities of Calcium Bonds in Bone Tissue.

The relationship of the hierarchical organization of the skeleton with the local electronic and atomic structure of bone is investigated. The Ca 2p photoemission from intact and various arthritis-damaged areas was measured and examined to study site-dependent peculiarities of calcium bonds in subchondral femoral bone. The medial and lateral condyles of the femur resected during total knee arthroplasty were used as samples. The Ca 2p3/2,1/2-1 photoelectron spectra demonstrate the distinct hierarchy-induced deviations of calcium bonds on the proximal side of the samples. It is shown that the apatite calcium bonds dominate in intact area, whereas non-apatite bonds dominate in OA-damaged areas, especially near sclerotic area but not inside it. The site dependence is associated with the interaction of broken collagen molecules with hydroxyapatite nanocrystallites at the cartilage-bone interface. The interplay of biomechanical and biochemical processes is examined, and the restoration of calcium bonds in sclerotic bone is discussed.

Associations of perceived indoor environmental quality with stress in the workplace.

Indoor environmental quality (IEQ) is a general indicator of the quality of conditions inside a building. We investigated associations of perceived IEQ including air quality, thermal comfort, noise, and light quality with stress at work and the extent to which workplace location modifies these associations. We recruited 464 full-time workers from four companies in Singapore. Data on socio-demographic characteristics, lifestyle/health-related factors, and workplace factors were collected through self-administered questionnaires. Perceived IEQ satisfaction scores of all four factors were collected using the validated OFFICAIR questionnaire. We fitted a logistic regression model to assess associations between each perceived IEQ score and stress at work, adjusting for potential confounders. The odds ratio for stress at work associated with a 1-unit increase in perceived air quality score was 0.88 (0.82-0.94), 0.89 (0.82-0.97) for thermal comfort, 0.93 (0.87-0.98) for noise, and 0.88 (0.82-0.94) for light quality. Significant associations were found in office and control rooms for all four perceived IEQ, except for thermal comfort in office rooms. Higher satisfaction levels of perceived air quality, thermal comfort, noise, and lighting, were significantly associated with a reduction in stress at work. Our findings could potentially provide a useful tool for environmental health impact assessment for buildings.

Effects of user behaviors on accumulation of social capital in an online social network.

The use of social network sites helps people to make and maintain social ties accumulating social capital, which is increasingly important for individual success. There is a wide variation in the amount and structure of online ties, and to some extent this variation is contingent on specific online user behaviors which are to date under-researched. In this work, we examine an entire city-bounded friendship network (N = 194,601) extracted from VK social network site to explore how specific online user behaviors are related to structural social capital in a network of geographically proximate ties. Social network analysis was used to evaluate individual social capital as a network asset, and multiple regression analysis-to determine and estimate the effects of online user behaviors on social capital. The analysis reveals that the graph is both clustered and highly centralized which suggests the presence of a hierarchical structure: a set of sub-communities united by city-level hubs. Against this background, membership in more online groups is positively associated with user's brokerage in the location-bounded network. Additionally, the share of local friends, the number of received likes and the duration of SNS use are associated with social capital indicators. This contributes to the literature on the formation of online social capital, examined at the level of a large and geographically localized population.

Association between shift work and poor sleep quality in an Asian multi-ethnic working population: A cross-sectional study.

BACKGROUND: We aimed to examine the association between shift work and sleep quality in a diverse occupational type. METHODS: This was a cross-sectional study of self-reported sleep quality in 424 workers aged ≥21 using the Pittsburgh Sleep Quality Index (PSQI). We divided workers into two categories based on their PSQI score: (a) ≤5 (good sleep quality) and (b) >5 (poor sleep quality). We used multiple logistic regressions to assess the association between shift work and sleep quality adjusted for potential confounders. RESULTS: The mean age was 39.2 (SD = 11.3) years, with shift workers being older than their counterparts. Most workers were of Chinese ethnicity (63.9%). Males were significantly more likely to undertake shift work than females (89% v 11%, p-value<0.001), but it should be noted that the majority of workers was male (78.8%) in this sample of workers. Shift workers had a 198% increased odds of poor sleep quality compared to non-shift workers (OR = 2.98; 95% CI:1.53-5.81). CONCLUSION: Shift work was significantly and independently associated with increased odds of poor sleep quality in this sample of workers. The present findings may inform employment guidelines and help develop workplace health promotion interventions aimed at improving sleep quality among workers and ultimately lead to a healthier workforce.

Activity Tracker-Based Metrics as Digital Markers of Cardiometabolic Health in Working Adults: Cross-Sectional Study.

BACKGROUND: Greater adoption of wearable devices with multiple sensors may enhance personalized health monitoring, facilitate early detection of some diseases, and further scale up population health screening. However, few studies have explored the utility of data from wearable fitness trackers in cardiovascular and metabolic disease risk prediction. OBJECTIVE: This study aimed to investigate the associations between a range of activity metrics derived from a wearable consumer-grade fitness tracker and major modifiable biomarkers of cardiometabolic disease in a working-age population. METHODS: This was a cross-sectional study of 83 working adults. Participants wore Fitbit Charge 2 for 21 consecutive days and went through a health assessment, including fasting blood tests. The following clinical biomarkers were collected: BMI, waist circumference, waist-to-hip ratio, blood pressure, triglycerides (TGs), high-density lipoprotein (HDL) and low-density lipoprotein cholesterol, and blood glucose. We used a range of wearable-derived metrics based on steps, heart rate (HR), and energy expenditure, including measures of stability of circadian activity rhythms, sedentary time, and time spent at various intensities of physical activity. Spearman rank correlation was used for preliminary analysis. Multiple linear regression adjusted for potential confounders was used to determine the extent to which each metric of activity was associated with continuous clinical biomarkers. In addition, pairwise multiple regression was used to investigate the significance and mutual dependence of activity metrics when two or more of them had significant association with the same outcome from the previous step of the analysis. RESULTS: The participants were predominantly middle aged (mean age 44.3 years, SD 12), Chinese (62/83, 75%), and male (64/83, 77%). Blood biomarkers of cardiometabolic disease (HDL cholesterol and TGs) were significantly associated with steps-based activity metrics independent of age, gender, ethnicity, education, and shift work, whereas body composition biomarkers (BMI, waist circumference, and waist-to-hip ratio) were significantly associated with energy expenditure-based and HR-based metrics when adjusted for the same confounders. Steps-based interdaily stability of circadian activity rhythm was strongly associated with HDL (beta=5.4 per 10% change; 95% CI 1.8 to 9.0; P=.005) and TG (beta=-27.7 per 10% change; 95% CI -48.4 to -7.0; P=.01). Average daily steps were negatively associated with TG (beta=-6.8 per 1000 steps; 95% CI -13.0 to -0.6; P=.04). The difference between average HR and resting HR was significantly associated with BMI (beta=-.5; 95% CI -1.0 to -0.1; P=.01) and waist circumference (beta=-1.3; 95% CI -2.4 to -0.2; P=.03). CONCLUSIONS: Wearable consumer-grade fitness trackers can provide acceptably accurate and meaningful information, which might be used in the risk prediction of cardiometabolic disease. Our results showed the beneficial effects of stable daily patterns of locomotor activity for cardiometabolic health. Study findings should be further replicated with larger population studies.

A Multifactorial Approach to Sleep and Its Association with Health-Related Quality of Life in a Multiethnic Asian Working Population: A Cross-Sectional Analysis.

This study aims to explore if objectively and subjectively measured sleep parameters are associated with physical and mental health-related quality of life in a multiethnic working population in Singapore. We performed a cross-sectional analysis with data from 329 full-time employees enrolled in a workplace cohort study in Singapore. The Short-Form 36v2 (SF-36v2) survey was used to assess health-related quality of life, in terms of physical and mental health. Subjective and objective sleep parameters were measured using the Pittsburgh Sleep Quality Index and wrist actigraphy, respectively. Generalized linear modeling was performed to examine the association between sleep parameters and health-related quality of life. After adjusting for confounders, subjectively measured sleep disturbances were associated with a lower physical health-related quality of life, whereas higher, objectively measured sleep efficiency was associated with greater physical health-related quality of life. Subjectively measured daytime dysfunction was associated with impaired mental health-related quality of life. Using both objective and subjective measurements of sleep, the current study suggests that there is an association between sleep and health-related quality of life. Workplace health-promotion planners in Singapore should consider programmes that educate workers on better sleep hygiene practices in an effort to improve sleep and health-related quality of life.

Digital phenotyping for assessment and prediction of mental health outcomes: a scoping review protocol.

INTRODUCTION: Rapid advancements in technology and the ubiquity of personal mobile digital devices have brought forth innovative methods of acquiring healthcare data. Smartphones can capture vast amounts of data both passively through inbuilt sensors or connected devices and actively via user engagement. This scoping review aims to evaluate evidence to date on the use of passive digital sensing/phenotyping in assessment and prediction of mental health. METHODS AND ANALYSIS: The methodological framework proposed by Arksey and O'Malley will be used to conduct the review following the five-step process. A three-step search strategy will be used: (1) Initial limited search of online databases namely, MEDLINE for literature on digital phenotyping or sensing for key terms; (2) Comprehensive literature search using all identified keywords, across all relevant electronic databases: IEEE Xplore, MEDLINE, the Cochrane Database of Systematic Reviews, PubMed, the ACM Digital Library and Web of Science Core Collection (Science Citation Index Expanded and Social Sciences Citation Index), Scopus and (3) Snowballing approach using the reference and citing lists of all identified key conceptual papers and primary studies. Data will be charted and sorted using a thematic analysis approach. ETHICS AND DISSEMINATION: The findings from this systematic scoping review will be reported at scientific meetings and published in a peer-reviewed journal.

An AIDS-denialist online community on a Russian social networking service: patterns of interactions with newcomers and rhetorical strategies of persuasion.

BACKGROUND: The rise of social media proved to be a fertile ground for the expansion of the acquired immune deficiency syndrome (AIDS)-denialist movement (in the form of online communities). While there is substantial literature devoted to disproving AIDS-denialist views, there is a lack of studies exploring AIDS-denialists online communities that interact with an external environment. OBJECTIVE: We explored three research areas: (1) reasons for newcomers to come to an AIDS-denialist community, (2) the patterns of interactions of the community with the newcomers, and (3) rhetorical strategies that denialists use for persuasion in the veracity of their views. METHODS: We studied the largest AIDS-denialist community on one of the most popular social networking services in Russia. We used netnography as a method for collecting data for qualitative analysis and observed the community for 9 months (at least 2-3 times a week). While doing netnography, we periodically downloaded community discussions. In total, we downloaded 4821 posts and comments for analysis. Grounded theory approach was used for data analysis. RESULTS: Most users came to the community for the following reasons: their stories did not fit the unitary picture of AIDS disease progression translated by popular medical discourse, health problems, concern about HIV-positive tests, and desire to dissuade community members from false AIDS beliefs. On the basis of strength in AIDS-denialist beliefs, we constructed a typology of the newcomers consisting of three ideal-typical groups: (1) convinced: those who already had become denialists before coming to the group, (2) doubters: those who were undecided about the truth of either human immunodeficiency virus (HIV) science theory or AIDS-denialist theory, and (3) orthodox: those who openly held HIV science views. Reception of a newcomer mainly depended on the newcomer's belief status. Reception was very warm for the convinced, cold or slightly hostile for the doubters, and extremely hostile or derisive for the orthodox. We identified seven main rhetorical strategies of persuasion used by the denialists on the "undecided". CONCLUSIONS: Contrary to the widespread public health depiction of AIDS denialists as totally irrational, our study suggests that some of those who become AIDS denialists have sufficiently reasonable grounds to suspect that "something is wrong" with scientific theory, because their personal experience contradicts the unitary picture of AIDS disease progression. Odd and inexplicable practices of some AIDS centers only fuel these people's suspicions. We can conclude that public health practitioners' practices may play a role in generating AIDS-denialist sentiments. In interactions with the newcomers, the experienced community members highlighted the importance of personal autonomy and freedom of choice in decision making consistent with the consumerist ideology of health care. The study findings suggest that health care workers should change a one-size-fits-all mode of counseling for a more complex and patient-tailored approach, allowing for diversity of disease progression scenarios and scientific uncertainty.