Improving Mental Health and Well-Being Through the Paradym App: Quantitative Study of Real-World Data
Bibliographic record
Abstract
BACKGROUND: With growing evidence suggesting that levels of emotional well-being have been decreasing globally over the past few years, demand for easily accessible, convenient, and affordable well-being and mental health support has increased. Although mental health apps designed to tackle this demand by targeting diagnosed conditions have been shown to be beneficial, less research has focused on apps aiming to improve emotional well-being. There is also a dearth of research on well-being apps structured around users' lived experiences and emotional patterns and a lack of integration of real-world evidence of app usage. Thus, the potential benefits of these apps need to be evaluated using robust real-world data. OBJECTIVE: This study aimed to explore usage patterns and preliminary outcomes related to mental health and well-being among users of an app (Paradym; Paradym Ltd) designed to promote emotional well-being and positive mental health. METHODS: This is a pre-post, single-arm evaluation of real-world data provided by users of the Paradym app. Data were provided as part of optional built-in self-assessments that users completed to test their levels of depression (Patient Health Questionnaire-9), anxiety (Generalized Anxiety Disorder Questionnaire-7), life satisfaction (Satisfaction With Life Scale), and overall well-being (World Health Organization-5 Well-Being Index) when they first started using the app and at regular intervals following initial usage. Usage patterns, including the number of assessments completed and the length of time between assessments, were recorded. Data were analyzed using within-subjects t tests, and Cohen d estimates were used to measure effect sizes. RESULTS: A total of 3237 app users completed at least 1 self-assessment, and 787 users completed a follow-up assessment. The sample was diverse, with 2000 users (61.8%) being located outside of the United States. At baseline, many users reported experiencing strong feelings of burnout (677/1627, 41.6%), strong insecurities (73/211, 34.6%), and low levels of thriving (140/260, 53.8%). Users also experienced symptoms of depression (mean 9.85, SD 5.55) and anxiety (mean 14.27, SD 6.77) and reported low levels of life satisfaction (mean 12.14, SD 7.42) and general well-being (mean 9.88, SD 5.51). On average, users had been using the app for 74 days when they completed a follow-up assessment. Following app usage, small but significant improvements were reported across all outcomes of interest, with anxiety and depression scores improving by 1.20 and 1.26 points on average, respectively, and life satisfaction and well-being scores improving by 0.71 and 0.97 points, respectively. CONCLUSIONS: This real-world data analysis and evaluation provided positive preliminary evidence for the Paradym app's effectiveness in improving mental health and well-being, supporting its use as a scalable intervention for emotional well-being, with potential applications across diverse populations and settings, and encourages the use of built-in assessments in mental health app research.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.027 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".