Improving Well-being With a Mobile Artificial Intelligence–Powered Acceptance Commitment Therapy Tool: Pragmatic Retrospective Study
Bibliographic record
Abstract
Background Research and dissemination of smartphone apps to deliver coaching and psychological driven intervention had seen a great surge in recent years. Notably, Acceptance Commitment Therapy (ACT) protocols were shown to be uniquely effective in treating symptoms for both depression and anxiety when delivered through smartphone apps. The aim of this study is to expand on that work and test the suitability of artificial intelligence–driven interventions delivered directly through popular texting apps. Objective This study evaluated our hypothesis that using Kai.ai will result in improved well-being. Methods We performed a pragmatic retrospective analysis of 2909 users who used Kai.ai on one of the top messaging apps (iMessage, WhatsApp, Discord, Telegram, etc). Users’ well-being levels were tracked using the World Health Organization-Five Well-Being Index throughout the engagement with service. A 1-tailed paired samples t test was used to assess well-being levels before and after usage, and hierarchical linear modeling was used to examine the change in symptoms over time. Results The median well-being score at the last measurement was higher (median 52) than that at the start of the intervention (median 40), indicating a significant improvement (W=2682927; P<.001). Furthermore, HLM results showed that the improvement in well-being was linearly related to the number of daily messages a user sent (β=.029; t81.36=4; P<.001), as well as the interaction between the number of messages and unique number of days (β=–.0003; t81.36=–2.2; P=.03). Conclusions Mobile-based ACT interventions are effective means to improve individuals’ well-being. Our findings further demonstrate Kai.ai’s great promise in helping individuals improve and maintain high levels of well-being and thus improve their daily lives.
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 | 0.008 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 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".