Recent growth in digital technologies has enabled the recruitment and monitoring of large and diverse populations in remote health studies. However, the generalizability of inference drawn from remotely collected health data could be severely impacted by uneven participant engagement and attrition over the course of the study. We report findings on long-term participant retention and engagement patterns in a large multinational observational digital study for depression containing active (surveys) and passive sensor data collected via Android smartphones, and Fitbit devices from 614 participants for up to 2 years. Majority of participants (67.6%) continued to remain engaged in the study after 43 weeks. Unsupervised clustering of participants’ study apps and Fitbit usage data showed 3 distinct engagement subgroups for each data stream. We found: (i) the least engaged group had the highest depression severity (4 PHQ8 points higher) across all data streams; (ii) the least engaged group (completed 4 bi-weekly surveys) took significantly longer to respond to survey notifications (3.8 h more) and were 5 years younger compared to the most engaged group (completed 20 bi-weekly surveys); and (iii) a considerable proportion (44.6%) of the participants who stopped completing surveys after 8 weeks continued to share passive Fitbit data for significantly longer (average 42 weeks). Additionally, multivariate survival models showed participants’ age, ownership and brand of smartphones, and recruitment sites to be associated with retention in the study. Together these findings could inform the design of future digital health studies to enable equitable and balanced data collection from diverse populations.

Background: Major depressive disorder (MDD) affects millions of people worldwide, but timely treatment is not often received owing in part to inaccurate subjective recall and variability in the symptom course. Objective and frequent MDD monitoring can improve subjective recall and help to guide treatment selection. Attempts have been made, with varying degrees of success, to explore the relationship between the measures of depression and passive digital phenotypes (features) extracted from smartphones and wearables devices to remotely and continuously monitor changes in symptomatology. However, a number of challenges exist for the analysis of these data. These include maintaining participant engagement over extended time periods and therefore understanding what constitutes an acceptable threshold of missing data; distinguishing between the cross-sectional and longitudinal relationships for different features to determine their utility in tracking within-individual longitudinal variation or screening individuals at high risk; and understanding the heterogeneity with which depression manifests itself in behavioral patterns quantified by the passive features. Objective: We aimed to address these 3 challenges to inform future work in stratified analyses. Methods: Using smartphone and wearable data collected from 479 participants with MDD, we extracted 21 features capturing mobility, sleep, and smartphone use. We investigated the impact of the number of days of available data on feature quality using the intraclass correlation coefficient and Bland-Altman analysis. We then examined the nature of the correlation between the 8-item Patient Health Questionnaire (PHQ-8) depression scale (measured every 14 days) and the features using the individual-mean correlation, repeated measures correlation, and linear mixed effects model. Furthermore, we stratified the participants based on their behavioral difference, quantified by the features, between periods of high (depression) and low (no depression) PHQ-8 scores using the Gaussian mixture model. Results: We demonstrated that at least 8 (range 2-12) days were needed for reliable calculation of most of the features in the 14-day time window. We observed that features such as sleep onset time correlated better with PHQ-8 scores cross-sectionally than longitudinally, whereas features such as wakefulness after sleep onset correlated well with PHQ-8 longitudinally but worse cross-sectionally. Finally, we found that participants could be separated into 3 distinct clusters according to their behavioral difference between periods of depression and periods of no depression. Conclusions: This work contributes to our understanding of how these mobile health–derived features are associated with depression symptom severity to inform future work in stratified analyses.

Prior research has associated spoken language use with depression, yet studies often involve small or non-clinical samples and face challenges in the manual transcription of speech. This paper aimed to automatically identify depression-related topics in speech recordings collected from clinical samples. The data included 3919 English free-response speech recordings collected via smartphones from 265 participants with a depression history. We transcribed speech recordings via automatic speech recognition (Whisper tool, OpenAI) and identified principal topics from transcriptions using a deep learning topic model (BERTopic). To identify depression risk topics and understand the context, we compared participants' depression severity and behavioral (extracted from wearable devices) and linguistic (extracted from transcribed texts) characteristics across identified topics. From the 29 topics identified, we identified 6 risk topics for depression: 'No Expectations', 'Sleep', 'Mental Therapy', 'Haircut', 'Studying', and 'Coursework'. Participants mentioning depression risk topics exhibited higher sleep variability, later sleep onset, and fewer daily steps and used fewer words, more negative language, and fewer leisure-related words in their speech recordings. Our findings were derived from a depressed cohort with a specific speech task, potentially limiting the generalizability to non-clinical populations or other speech tasks. Additionally, some topics had small sample sizes, necessitating further validation in larger datasets. This study demonstrates that specific speech topics can indicate depression severity. The employed data-driven workflow provides a practical approach for analyzing large-scale speech data collected from real-world settings.

Digital phenotyping offers a novel and cost-efficient approach for managing depression and anxiety. Previous studies, often limited to small-to-medium or specific populations, may lack generalizability. We conducted a cross-sectional analysis of data from 10,129 participants recruited from a UK-based general population between June 2020 and August 2022. Participants shared wearable (Fitbit) data and self-reported questionnaires on depression, anxiety, and mood via a study app. We examined correlations between mental health scores and wearable-derived features, demographics, health variables, and mood assessments. Unsupervised clustering was used to identify behavioural patterns associated with depression and anxiety. Furthermore, we employed XGBoost machine learning models to predict depression and anxiety severity and compared the performance using different subsets of features. We observed significant associations between the severity of depression and anxiety with several factors, including mood, age, gender, BMI, sleep patterns, physical activity, and heart rate. Clustering analysis revealed that participants simultaneously exhibiting lower physical activity levels and higher heart rates reported more severe symptoms. Prediction models incorporating all types of variables achieved the best performance (R² = 0.41, MAE = 3.42 for depression; R² = 0.31, MAE = 3.50 for anxiety) compared to those using subsets of variables. Several wearable-derived features were observed to have non-linear relationships with depression and anxiety in the prediction models. Data collection during the COVID-19 pandemic may introduce biases. This study identified several indicators for depression and anxiety and highlighted the potential of digital phenotyping and machine learning technologies for rapid screening of mental disorders in general populations.

Multiple sclerosis (MS) is a progressive inflammatory and neurodegenerative disease of the central nervous system affecting over 2.5 million people globally. In-clinic six-minute walk test (6MWT) is a widely used objective measure to evaluate the progression of MS. Yet, it has limitations such as the need for a clinical visit and a proper walkway. The widespread use of wearable devices capable of depicting patients' activity profiles has the potential to assess the level of MS-induced disability in free-living conditions. In this work, we extracted 96 features in different temporal granularities (from minute-level to day-level) from wearable data and explored their utility in estimating 6MWT scores in a European (Italy, Spain, and Denmark) MS cohort of 337 participants over an average of 10 months' duration. We combined these features with participants' demographics using three regression models including elastic net, gradient boosted trees and random forest. In addition, we quantified the individual feature's contribution using feature importance in these regression models, linear mixed-effects models, generalized estimating equations, and correlation-based feature selection (CFS). The results showed promising estimation performance with R² of 0.30, which was derived using random forest after CFS. This model was able to distinguish the participants with low disability from those with high disability. Furthermore, we observed that the minute-level (≤ 8 minutes) step count, particularly those capturing the upper end of the step count distribution, had a stronger association with 6MWT. The use of a walking aid was indicative of ambulatory function measured through 6MWT. This study demonstrates the utility of wearables devices in assessing ambulatory impairments in people with MS in free-living conditions and provides a basis for future investigation into the clinical relevance.

Background: Remote measurement technologies (RMTs) such as smartphones and wearables can help improve treatment for depression by providing objective, continuous, and ecologically valid insights into mood and behavior. Engagement with RMTs is varied and highly context dependent; however, few studies have investigated their feasibility in the context of treatment. Objective: A mixed methods design was used to evaluate engagement with active and passive data collection via RMT in people with depression undergoing psychotherapy. We evaluated the effects of treatment on 2 different types of engagement: study attrition (engagement with study protocol) and patterns of missing data (engagement with digital devices), which we termed data availability. Qualitative interviews were conducted to help interpret the differences in engagement. Methods: A total of 66 people undergoing psychological therapy for depression were followed up for 7 months. Active data were gathered from weekly questionnaires and speech and cognitive tasks, and passive data were gathered from smartphone sensors and a Fitbit (Fitbit Inc) wearable device. Results: The overall retention rate was 60%. Higher-intensity treatment (χ21=4.6; P=.03) and higher baseline anxiety (t56.28=−2.80, 2-tailed; P=.007) were associated with attrition, but depression severity was not (t50.4=−0.18; P=.86). A trend toward significance was found for the association between longer treatments and increased attrition (U=339.5; P=.05). Data availability was higher for active data than for passive data initially but declined at a sharper rate (90%-30% drop in 7 months). As for passive data, wearable data availability fell from a maximum of 80% to 45% at 7 months but showed higher overall data availability than smartphone-based data, which remained stable at the range of 20%-40% throughout. Missing data were more prevalent among GPS location data, followed by among Bluetooth data, then among accelerometry data. As for active data, speech and cognitive tasks had lower completion rates than clinical questionnaires. The participants in treatment provided less Fitbit data but more active data than those on the waiting list. Conclusions: Different data streams showed varied patterns of missing data, despite being gathered from the same device. Longer and more complex treatments and clinical characteristics such as higher baseline anxiety may reduce long-term engagement with RMTs, and different devices may show opposite patterns of missingness during treatment. This has implications for the scalability and uptake of RMTs in health care settings, the generalizability and accuracy of the data collected by these methods, feature construction, and the appropriateness of RMT use in the long term.