The Effectiveness of Fully Automated Digital Interventions in Promoting Mental Well-Being in the General Population: Systematic Review and Meta-Analysis
Bibliographic record
Abstract
BACKGROUND: Recent years have highlighted an increasing need to promote mental well-being in the general population. This has led to a rapidly growing market for fully automated digital mental well-being tools. Although many individuals have started using these tools in their daily lives, evidence on the overall effectiveness of digital mental well-being tools is currently lacking. OBJECTIVE: This study aims to review the evidence on the effectiveness of fully automated digital interventions in promoting mental well-being in the general population. METHODS: Following the preregistration of the systematic review protocol on PROSPERO, searches were carried out in MEDLINE, Web of Science, Cochrane, PsycINFO, PsycEXTRA, Scopus, and ACM Digital (initial searches in February 2022; updated in October 2022). Studies were included if they contained a general population sample and a fully automated digital intervention that exclusively used psychological mental well-being promotion activities. Two reviewers, blinded to each other's decisions, conducted data selection, extraction, and quality assessment of the included studies. Narrative synthesis and a random-effects model of per-protocol data were adopted. RESULTS: We included 19 studies that involved 7243 participants. These studies included 24 fully automated digital mental well-being interventions, of which 15 (63%) were included in the meta-analysis. Compared with no intervention, there was a significant small effect of fully automated digital mental well-being interventions on mental well-being in the general population (standardized mean difference 0.19, 95% CI 0.04-0.33; P=.02). Specifically, mindfulness-, acceptance-, commitment-, and compassion-based interventions significantly promoted mental well-being in the general population (P=.006); insufficient evidence was available for positive psychology and cognitive behavioral therapy-based interventions; and contraindications were found for integrative approaches. Overall, there was substantial heterogeneity, which could be partially explained by the intervention duration, comparator, and study outcomes. The risk of bias was high, and confidence in the quality of the evidence was very low (Grading of Recommendations, Assessment, Development, and Evaluations), primarily because of the high rates of study dropout (average 37%; range 0%-85%) and suboptimal intervention adherence (average 40%). CONCLUSIONS: This study provides a novel contribution to knowledge regarding the effectiveness, strengths, and weaknesses of fully automated digital mental well-being interventions in the general population. Future research and practice should consider these findings when developing fully automated digital mental well-being tools. In addition, research should aim to investigate positive psychology and cognitive behavioral therapy-based tools as well as develop further strategies to improve adherence and reduce dropout in fully automated digital mental well-being interventions. Finally, it should aim to understand when and for whom these interventions are particularly beneficial. TRIAL REGISTRATION: PROSPERO CRD42022310702; https://tinyurl.com/yc7tcwy7.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.005 | 0.003 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".