Ulrich Hegerl

Background and Objective: Longitudinal smartphone and wearable monitoring provides increasingly rich personal histories for predicting depressive symptom severity, while data from other individuals may offer additional information. This raises an open question: when does cross-person information add predictive value beyond an individual’s own accumulating history?Methods: Eleven participants provided up to 1 year of longitudinal data, including daily symptom assessments and 118 smartphone and wearable predictors. Elastic net (EN) and random forest (RF) models were evaluated in consecutive 30-day windows after a 90-day tuning period using expanding training histories and strict temporal cutoffs. Individualized, centrally pooled, and federated learning were compared with a participant-specific historical-mean baseline using mean absolute error and R². Controlled empirical analyses varied personal history and contributor numbers, while a complementary simulation independently varied participant count, personal history, and between-participant heterogeneity.Results: Individualized learning had lower median mean absolute error than pooled and federated learning for EN (2.147 vs 3.743 and 3.655) and RF (2.268 vs 2.748 and 3.930), with significant Holm-adjusted differences versus pooling for EN and RF and versus federated learning for RF. Individualized learning outperformed the historical-mean baseline for all 11 participants with EN and for 10 of 11 participants with RF, although median R² remained negative. A shared approach outperformed both individualized learning and the baseline in 28% and 33% of EN and RF evaluation windows. Pooling remained less accurate, with a larger disadvantage at shorter personal histories and a tendency toward greater disadvantage with more contributors. The simulation showed that either approach could be favored depending on participant count, personal history, and heterogeneity.Conclusions: Individualized learning showed an advantage in this small-participant, long-follow-up cohort, while cross-person information remained beneficial in some evaluations despite limited absolute predictive performance. Controlled analyses and the simulation showed that its value varies with personal history, contributor numbers, and between-participant heterogeneity, helping characterize when individualized or shared learning may be useful.

Background: Smartphones and wearables can continuously capture behavioral and physiological data in everyday life. Such mobile-sensing data may help track depressive symptoms more closely than occasional retrospective questionnaires, but prior findings have been mixed. Inconsistent findings do not preclude the presence of predictive relationships in specific individuals or time periods. In addition, it remains unclear which broader sensor domains, rather than single features, contribute most to prediction at the individual level. Objective: The objective of this study is to evaluate whether smartphone and wearable data improve prospective prediction of daily depressive symptom severity beyond a person-specific baseline and, where improvement is observed, to identify contributing sensor feature groups. Methods: Data from the MONDY (secure and open platform for AI-based health care apps) n-of-1 study were analyzed, including adults with recurrent major depressive disorder who provided up to 12 months of daily self-reported depressive symptom ratings, together with continuous smartphone and smartwatch data. To capture individual-specific patterns, separate participant-specific (idiographic) linear and nonlinear models were developed for each individual. Performance was evaluated using repeated temporally separated training and test periods against a person-specific baseline model predicting the mean symptom score from the training period. Explainability analyses were restricted to models showing improvement over baseline, and summarized at the level of sensor feature groups. Results: Among 11 participants with sufficient data, linear models improved predictive performance over the person-specific baseline in 8 (73%) participants, and nonlinear models did so in a different set of 8 (73%) participants. Improvements over the person-specific baseline, expressed as reductions in mean absolute error (change in mean absolute error relative to baseline), ranged from 0.05 to 1.23 points for linear models and from 0.12 to 1.07 points for nonlinear models on the adapted Patient Health Questionnaire-2 scale. Predictive performance varied substantially between individuals, and although nonlinear models exhibited greater aggregate feature-group contributions, this did not translate into a consistent overall predictive advantage over linear models. Feature-group importance profiles were heterogeneous, and no single sensor domain dominated across all participants. Conclusions: Multimodal smartphone and wearable data can provide individual-specific predictive signals for daily depressive symptom severity in a subset of patients when evaluated under prospective, time-aware conditions. Both predictive performance and contributing sensor domains vary markedly across individuals, and no single modeling approach is uniformly superior. These findings suggest that previously reported associations in mobile-sensing research, often arising from heterogeneous study designs and feature representations, may not consistently translate into prospective prediction, and highlight the importance of evaluation frameworks that assess predictive signal at the temporal individual-participant level.

BACKGROUND Large language models (LLMs) such as ChatGPT are increasingly being used by people suffering from depression to discuss mental health problems. OBJECTIVE Based on a representative survey it was studied, i) how widespread the use of these LLMs is, ii) how positive or negative they are perceived by the users and iii) how benefits of LLMs were perceived in comparison to face-to-face psychotherapy. METHODS In March 2026, a representative online survey was conducted in Germany (age 16 to 39; n = 2,500). Among the participants, 537 (21.5%) reported having been professionally diagnosed with a life-time diagnosis of depression. In this subgroup, the use of LLM in the past 30 days concerning depression was assessed as well as how beneficial this use was perceived (n=185). In those who had also undergone psychotherapy (n=143) the experiences with LLMs were compared to those with psychotherapy. RESULTS 56% of people with diagnosed depression reported having used LLMs recently for mental health purposes, and 35% of those had done so specifically concerning their depression. The majority perceived LLMs as positive, e.g. felt empowered after using LLMs (75.3%). However, contrary to these and other positive perceptions, 52.9% reported thoughts of self-harm or suicide following the conversations. Of those who had already undergone psychotherapy, 28.7% claimed that the conversations with LLMs were better than with the psychotherapist, and 17.7% said the opposite. CONCLUSIONS The broad, unguided use of LLMs and both the huge potential benefits and risks for people suffering from depression call for urgent research in this area.

Depression literacy is a multifaceted construct encompassing the knowledge needed to recognize and effectively respond to depression symptoms. This study aimed to develop and validate a self-report questionnaire measuring depression literacy and evaluating its factorial, criterion, convergent, and discriminant validity. Using a 56-item pool from existing studies, we conducted secondary analyses of two representative German adult surveys (ages 18–69; N = 5,178 and 5,285) to develop the Multifaceted Depression Literacy Scale (M-DL). Development comprised five steps: expert rating of the item pool, exploratory factor analysis and item selection (first survey), calculation of psychometric properties, confirmatory factor analysis, and evaluation of construct and discriminant validity (second survey). For validity assessment, scores were compared across subgroups with different depression contact (none, personal, or professional) and correlated with a self-rated depression knowledge item and the Depression Stigma Scale. Confirmatory factor analysis supported a 14-factor, multidimensional structure. Criterion validity was shown by significant score differences between professionals or relatives and those with no depression contact (both p < .05). Convergent validity with the self-assessment item was low but significant (p < .05), and discriminant validity was supported by negative correlations with personal and perceived stigma (p < .001). We developed a brief self-assessment instrument for depression literacy covering all literature-based facets except prevention. The instrument showed good psychometric properties and may help identify those with low depression literacy. Future research should test its applicability in more diverse populations and further examine convergent validity and sensitivity to change over time, including intervention responsiveness.

BACKGROUND Continuous smartphone sensors and app data offer opportunities to detect individual behavioral patterns related to depressive symptom severity. Prior analyses showed that behavior–depression relationships can shift substantially over time, underscoring the need for transparent methods that capture such temporal variability. Vector autoregressive (VAR) models provide an interpretable and parametrized framework for analyzing temporal dynamics, with VAR-derived metrics offering a rigorous basis for identifying significant relationships. They are also computationally efficient, enabling rapid estimation in sequential or rolling-window settings. In this study, we developed and evaluated a rolling static VAR (RSVAR) approach that captures temporal fluctuations using only past information. OBJECTIVE This study evaluated (1) in how many participants and how often RSVAR models identified statistically significant day-to-day directed temporal associations between depressive symptom severity and features derived from mobile sensing (MS), and (2) which features most frequently function as temporal predictors. METHODS One-year longitudinal data from 15 adults with major depressive disorder were analyzed, combining daily self-reported depressive symptom severity assessed using an adapted PHQ-2 score with smartphone- and smartwatch-derived behavioral and physiological features. Individual-level RSVAR models were applied to identify statistically significant day-to-day directed temporal associations between MS features and depressive symptom severity. RESULTS RSVAR models identified directed temporal associations between behavioral indicators and depressive symptom severity in 13 of 15 participants. Such associations were observed on 17% of days with stable VAR models, corresponding to approximately 4% of all monitored participant days. Higher pitch was most frequently associated with subsequent increases in symptom severity (75% of identified instances), whereas higher social media app usage showed a modest predominance of symptom severity increases (57%) over decreases. Higher night-time activity was more often associated with a higher subsequent symptom severity (77%). Indicators of autonomic cardiovascular regulation exhibited a heterogeneous pattern, with symptom severity decreases occurring slightly more often (56%) than increases. Higher physical activity was more often associated with subsequent increases in symptom severity (63%) than decreases. CONCLUSIONS In this proof-of-concept study, RSVAR identified individualized, temporally directed associations between selected MS features and depressive symptom severity in a subset of monitored days. These findings support further investigation of transparent time-series approaches for personalized mobile mental health monitoring. CLINICALTRIAL German Clinical Trials Register (DRKS), DRKS00032618. Registered 12 September 2023.

BACKGROUND Smartphones and wearables can continuously capture behavioral and physiological data in everyday life. Such mobile-sensing data may help track depressive symptoms more closely than occasional retrospective questionnaires, but prior findings have been mixed. Inconsistent findings do not preclude the presence of predictive relationships in specific individuals or time periods. In addition, it remains unclear which broader sensor domains, rather than single features, contribute most to prediction at the individual level. OBJECTIVE The objective of the current study is to evaluate whether smartphone and wearable data improve prospective prediction of daily depressive symptom severity beyond a person-specific baseline and, where improvement is observed, to identify contributing sensor feature groups. METHODS Among 11 participants with sufficient data, 8 (73%) showed improved performance over baseline with linear models and 9 (82%) with nonlinear models. Among models showing improvement, fold-averaged mean absolute error ranged from 0.91 to 2.31 points on the adapted PHQ-2 scale for linear models and from 0.54 to 2.54 points for nonlinear models. Improvements over the person-specific baseline ranged from ΔMAE = 0.04 to 1.19 points for linear models and from ΔMAE = 0.11 to 1.09 points for nonlinear models. Predictive performance varied substantially between individuals, and no consistent overall advantage of nonlinear over linear models was observed. Feature-group importance profiles were heterogeneous, and no single sensor domain dominated across all participants. RESULTS Among 11 participants with sufficient data, 8 (73%) showed improved performance over baseline with linear models and 9 (82%) with nonlinear models. Predictive performance varied substantially between individuals, and no consistent overall advantage of nonlinear over linear models was observed. Feature-group importance profiles were heterogeneous, and no single sensor domain dominated across participants. CONCLUSIONS Multimodal smartphone and wearable data can provide individual-specific predictive signals for daily depressive symptom severity in a subset of patients when evaluated under prospective, time-aware conditions. Both predictive performance and contributing sensor domains vary markedly across individuals, and no single modeling approach is uniformly superior. These findings suggest that previously reported associations in mobile sensing research, often arising from heterogeneous study designs and feature representations, may not consistently translate into prospective prediction, and highlight the importance of evaluation frameworks that assess predictive signal at the temporal individual-participant level. CLINICALTRIAL German Clinical Trials Register (DRKS), DRKS00032618. Registered 12 September 2023.

Background: Internet-based cognitive behavioral therapy (iCBT) for the treatment of depression has proven to be an effective and accessible option. However, iCBTs tend to have low adherence rates, which may negatively impact their effectiveness. One such iCBT program is the browser-based, proven-effective iFightDepression (iFD) tool. An app-based version of the iFD tool is the iFD app, which was developed to improve usability with a smartphone. The iFD app provides enhanced usability and a more optimized user experience on mobile devices. Additionally, it offers more comfortable interaction with worksheets, reduced text with added videos, and quicker access to the program via the smartphone icon. These improved usability on smartphones and could have an impact on adherence. Objective: This study investigated (1) whether adherence parameters, that is, the number of worksheets , the number of sessions , and the number of workshops , significantly differed between users of the iFD app and the iFD tool and (2) exploratorily whether symptom reduction (delta Patient Health Questionnaire-9 [PHQ-9] scores) differed after 5 to 9 weeks between the iFD app and the iFD tool, after controlling for covariates. Methods: We used t tests to compare data from 56 participants using the iFD app for 8 weeks with data from 172 participants using the iFD tool in a previous 6-week study. Exploratively, symptom reduction was compared between formats. A multiple regression model was calculated with the delta PHQ-9 score as the dependent variable and format, baseline PHQ-9 score, adherence, current psychotherapy, antidepressants, age, and sex as independent variables. Results: There was no significant difference between the iFD tool and the iFD app in terms of the number of sessions per week ( t _67.393 =0.920; P =.36; corrected P =.36), the number of workshops ( t _76.368 =–1.217; P =.30; corrected P =.36), and the number of worksheets per week ( t ₇₄ =0.984; P =.33; corrected P =.36). We found no difference in delta PHQ-9 scores between the iFD app and the iFD tool, and baseline PHQ-9 scores were the only significant predictor ( b =–0.61; P <.001). Conclusions: Despite the improved availability of the app version in daily life, there were no significant differences in the use parameters we analyzed and no differences in symptom reduction. This study provides the first evidence that adherence to iCBT content is comparable for browser- and app-based interventions and that symptom reduction is similar for both formats. However, this study used a convenience sample, and therefore, the results must be interpreted with caution. Notably, in the study of the iFD tool, guidance was provided by the study assistants in a standardized manner. In the pilot study on the iFD app, the amount of guidance varied substantially, as it was provided by the participants’ health care practitioners. These differences in guidance could also have an influence on adherence.

Background: Digital health interventions incorporating self-management strategies are increasingly used to support individuals in managing depression. These interventions often leverage self-monitoring and passive sensor-based data collection to provide personalized feedback, guiding behavioral change. With the proliferation of smartphones and wearable devices, there is growing potential to continuously collect behavioral and physiological data. However, a major limitation in the field is the lack of consolidated evidence on which specific parameters are most useful for monitoring and predicting depression-related outcomes. Objective: This scoping review aims to identify and synthesize common digital phenotyping and self-report parameters for monitoring and predicting depression. Specifically, it addresses the methodological and knowledge gap concerning which types of sensor-based and self-reported data are most frequently used and which demonstrate predictive value in tracking changes in depressive symptoms across digital platforms. Methods: A literature search was conducted across 4 databases, including PubMed, Embase, Cochrane Library, and the Web of Science Core Collection. Articles published between January 1, 2021, and November 26, 2025, were included. Eligible studies included adults (≥18 years) with depression confirmed through validated clinical measures and using digital approaches that collected passive sensor data, self-reports, or both. Studies focusing on comorbid disorders, nondigital interventions, or not reporting depression-related outcomes were excluded. The PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines were followed, and a 5-stage methodological framework for scoping reviews was implemented. Quality assessment was performed using the Downs and Black Instrument and the Mixed Methods Appraisal Tool (MMAT). Results: Nineteen studies were included, comprising a total of 85,193 participants. Most studies used smartphone- or wearable-based tools, with passive sensing as the predominant data source and Patient Health Questionnaire-9 (PHQ-9) as the most commonly used depression measure. Five overarching parameter categories were identified: (1) physical activity and location, (2) behavioral patterns, (3) physiological signals, (4) sleep indicators, and (5) sociability and self-reported assessments. Within these categories, 11 metrics, including step count, heart rate variability, sleep duration and mood self-ratings, were most frequently reported. Most studies used a multimodal digital phenotyping approach, integrating passive sensor-derived data with active user-reported input, enabling more individualized symptom monitoring over time. Conclusions: This scoping review provides a novel synthesis of common digital parameters used across diverse tools for monitoring and predicting depression, moving beyond tool- or modality-specific perspectives adopted in prior reviews. Unlike existing reviews focusing on individual sensing modalities, prediction methods, or intervention effectiveness, this review maps shared parameters across observational, predictive, and interventional studies. By identifying convergent digital markers, the review supports comparability across studies and informs future model development. These findings have practical implications for the design of scalable digital mental health tools and for translating digital phenotyping into real-world clinical and self-management contexts.

Background: Depression is a common psychiatric disorder that is associated with both feelings of loneliness and withdrawal from social relationships. However, clinical experience suggests that feelings of loneliness are an integral part of depressive symptomatology and can occur even when a patient has many social relationships. We addressed the following three research questions: 1. How are feelings of loneliness and the number of social relationships associated in people with depression compared with the nondepressed population? 2. Do people with depression have more feelings of loneliness compared with the nondepressed population? 3. Do people with depression have fewer social relationships compared with the nondepressed population? Methods: Cross-sectional data from the German Depression Barometer 2023, a representative survey of the German adult population (N=5196), were analysed. Feelings of loneliness and the number of social relationships were assessed via self-reports. Results: Feelings of loneliness and the number of social relationships are negatively correlated both in people with a lifetime diagnosis of depression (n=1221, Spearman’s ρ = -.234, p <.001, 95% CI [-.288; -.179]) and in people without a depression diagnosis (n=2821, Spearman’s ρ = -.132, p <.001, 95% CI [-.169; -.094]). The strength of the correlation is significantly greater for people with a lifetime diagnosis of depression (Z=2.99, p <.02). Increased feelings of loneliness are found in people with a lifetime diagnosis of depression ( M =6.53) compared with the nondepressed German population ( M =4.30). The difference between the two groups is significant, t(4040) = 19.08 , p <.001, d = 0.654. Additionally, fewer social relationships are found in people with a lifetime diagnosis of depression (39.2% with 0-4 social contacts on a normal day) than in the nondepressed German population (20.5% with 0-4 social contacts on a normal day). The difference between the two groups is again significant, U = 1247054,50, Z = -14.44, p <.001, r = 0.227. Conclusions: Contrary to our expectations, a stronger inverse correlation between feelings of loneliness and the number of social relationships was observed in people with depression than in the nondepressed population. Furthermore, we replicated findings of increased feelings of loneliness and a reduced number of social relationships in people with a lifetime diagnosis of depression. This has possible implications for treatment decisions and intervention programs, namely, that both feelings of loneliness and social relationships should be addressed. Clinical trial number: Not applicable.