Effectiveness of a Mental Health Chatbot for People With Chronic Diseases: Randomized Controlled Trial
Bibliographic record
Abstract
BACKGROUND: People with chronic diseases tend to experience more mental health issues than their peers without these health conditions. Mental health chatbots offer a potential source of mental health support for people with chronic diseases. OBJECTIVE: The aim of this study was to determine whether a mental health chatbot can improve mental health in people with chronic diseases. We focused on 2 chronic diseases in particular: arthritis and diabetes. METHODS: Individuals with arthritis or diabetes were recruited using various web-based methods. Participants were randomly assigned to 1 of 2 groups. Those in the treatment group used a mental health chatbot app (Wysa [Wysa Inc]) over a period of 4 weeks. Those in the control group received no intervention. Participants completed measures of depression (Patient Health Questionnaire-9), anxiety (Generalized Anxiety Disorder Scale-7), and stress (Perceived Stress Scale-10) at baseline, with follow-up testing 2 and 4 weeks later. Participants in the treatment group completed feedback questions on their experiences with the app at the final assessment point. RESULTS: A total of 68 participants (n=47, 69% women; mean age 42.87, SD 11.27 years) were included in the analysis. Participants were divided evenly between the treatment and control groups. Those in the treatment group reported decreases in depression (P<.001) and anxiety (P<.001) severity over the study period. No such changes were found among participants in the control group. No changes in stress were reported by participants in either group. Participants with arthritis reported higher levels of depression (P=.004) and anxiety (P=.004) severity than participants with diabetes over the course of the study, as well as higher levels of stress (P=.01); otherwise, patterns of results were similar across these health conditions. In response to the feedback questions, participants in the treatment group said that they liked many of the functions and features of the app, the general design of the app, and the user experience. They also disliked some aspects of the app, with most of these reports focusing on the chatbot's conversational abilities. CONCLUSIONS: The results of this study suggest that mental health chatbots can be an effective source of mental health support for people with chronic diseases such as arthritis and diabetes. Although cost-effective and accessible, these programs have limitations and may not be well suited for all individuals. TRIAL REGISTRATION: ClinicalTrials.gov NCT04620668; https://www.clinicaltrials.gov/study/NCT04620668.
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 | 0.006 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 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".