Comparison of an AI Chatbot With a Nurse Hotline in Reducing Anxiety and Depression Levels in the General Population: Pilot Randomized Controlled Trial
Bibliographic record
Abstract
Background: Artificial intelligence (AI) chatbots have been customized to deliver on-demand support for people with mental health problems. However, the effectiveness of AI chatbots in tackling mental health problems among the general public in Hong Kong remains unclear. Objective: This study aimed to develop a local AI chatbot and compare the effectiveness of the AI chatbot with a conventional nurse hotline in reducing the level of anxiety and depression among individuals in Hong Kong. Methods: This study was a pilot randomized controlled trial conducted from October 2022 to March 2023, involving 124 participants allocated randomly (1:1 ratio) into the AI chatbot and nurse hotline groups. Among these, 62 participants in the AI chatbot group and 41 in the nurse hotline group completed both the pre- and postquestionnaires, including the GAD-7 (Generalized Anxiety Disorder Scale-7), PHQ-9 (Patient Health Questionnaire-9), and satisfaction questionnaire. Comparisons were conducted using independent and paired sample t tests (2-tailed) and the χ2 test to analyze changes in anxiety and depression levels. Results: Compared to the mean baseline score of 5.13 (SD 4.623), the mean postdepression score in the chatbot group was 3.68 (SD 4.397), which was significantly lower (P=.008). Similarly, a reduced anxiety score was also observed after the chatbot test (pre vs post: mean 4.74, SD 4.742 vs mean 3.4, SD 3.748; P=.005), respectively. No significant differences were found in the pre-post scores for either depression (P=.38) or anxiety (P=.19). No statistically significant difference was observed in service satisfaction between the two platforms (P=.32). Conclusions: The AI chatbot was comparable to the traditional nurse hotline in alleviating participants' anxiety and depression after responding to inquiries. Moreover, the AI chatbot has shown potential in alleviating short-term anxiety and depression compared to the nurse hotline. While the AI chatbot presents a promising solution for offering accessible strategies to the public, more extensive randomized controlled studies are necessary to further validate its effectiveness.
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 | 0.005 | 0.007 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.003 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.009 | 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".