German adult population norm values of the short Warwick Edinburgh mental well-being scale (SWEMWBS).

PURPOSE: The Warwick-Edinburgh Mental Well-Being Scale represents an internationally established inventory to assess population mental well-being. Particularly the short form (SWEMWBS) is recommended for use in Mental Health Surveillance. In the present study, we present normative data of the SWEMWBS for the German adult population. METHODS: Data from the telephone survey German Health Update (GEDA) in 2022 representative of the German adult population (48.9% women, 18-98 years) was processed to estimate SWEMWBS percentile norm values, T-values, z-values and internationally comparable logit-transformed raw scores for the total sample (N = 5,606) as well as stratified by sex, age group and sex with age group combinations. RESULTS: The average mental well-being was comparable to that of other European countries at M = 27.3 (SD = 4.0; logit-transformed: M = 24.79, SD = 3.73). To provide a benchmark, the cut off for low well-being was set at the 15th percentile (raw score: 23; logit-transformed: 20.73), for high well-being at the 85th percentile (raw score: 32; logit-transformed: 29.31). CONCLUSION: The present study provides SWEMWBS norm values for the German adult population. The normative data can be used for national and international comparisons on a population level to initiate, plan and evaluate mental well-being promotion and prevention measures.

The predictive value of supervised machine learning models for insomnia symptoms through smartphone usage behavior.

Introduction: Digital phenotyping can be an innovative and unobtrusive way to improve the detection of insomnia. This study explores the correlations between smartphone usage features (SUF) and insomnia symptoms and their predictive value for detecting insomnia symptoms. Methods: In an observational study of a German convenience sample, the Insomnia Severity Index (ISI) and smartphone usage data (e.g., time the screen was active, longest time the screen was inactive in the night) for the previous 7 days were obtained. SUF (e.g., min, mean) were calculated from the smartphone usage data. Correlation analyses between the ISI and SUF were conducted. For the specification of the machine learning models (ML), 80 % of the data was allocated to training, 20 % to testing, and five-fold cross-validation was used. Six algorithms (support vector machine, XGBoost, Random Forest, k-Nearest-Neighbor, Naive Bayes, and Logistic Regressions) were specified to predict ISI scores ≥15. Results: 752 participants (51.1 % female, mean ISI = 10.23, mean age = 41.92) were included in the analyses. Small correlations between some of the SUF and insomnia symptoms were found. In the ML models, sensitivity was low, ranging from 0.05 to 0.27 in the testing subsample. Random Forest and Naive Bayes were the best-performing algorithms. Yet, their AUCs (0.57, 0.58 respectively) in the testing subsample indicated a low discrimination capacity. Conclusions: Given the small magnitude of the correlations and low discrimination capacity of the ML models, SUFs, as measured in this study, do not appear to be sufficient for detecting insomnia symptoms. Further research is necessary to explore whether examining intra-individual variations and subpopulations or employing alternative smartphone sensors yields more promising outcomes.