Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Human Factors

Date Submitted: Aug 26, 2024
Date Accepted: Jan 15, 2025

The final, peer-reviewed published version of this preprint can be found here:

Comparison of an AI Chatbot With a Nurse Hotline in Reducing Anxiety and Depression Levels in the General Population: Pilot Randomized Controlled Trial

Chen C, Lam T, Yip KM, So HK, Lum TYS, Wong ICK, Yam JCS, Chui CSL, Ip P

Comparison of an AI Chatbot With a Nurse Hotline in Reducing Anxiety and Depression Levels in the General Population: Pilot Randomized Controlled Trial

JMIR Hum Factors 2025;12:e65785

DOI: 10.2196/65785

PMID: 40048637

PMCID: 11906115

AI Chatbot Versus Nurse Hotline for the Level of Anxiety and Depression in General Population: a Pilot Study

  • Chen Chen; 
  • Tai Lam; 
  • Kan Man Yip; 
  • Hung Kwan So; 
  • Terry Yat Sang Lum; 
  • Ian Chi Kei Wong; 
  • Jason Cheuk Sing Yam; 
  • Celine Sze Ling Chui; 
  • Patrick Ip

ABSTRACT

Background:

The AI chatbot has been customized to deliver on-demand support for people with mental health problems. The effectiveness of AI chatbots in tackling mental health problems in the general public in Hong Kong remains unclear.

Objective:

The study aimed to develop a local AI chatbot and compare the effectiveness of the AI chatbot and conventional nurse hotline in reducing the level of anxiety and depression of subjects in Hong Kong during the COVID-19 outbreak.

Methods:

This was a pilot randomized controlled trial conducted from Oct 2022 to March 2023, involving 124 participants allocated randomly (1:1 ratio) into the AI chatbot group and nurse hotline group. 62 participants in the AI chatbot group and 41 in the nurse hotline group completed both the pre-and post-questionnaires, including the Generalized Anxiety Disorder Scale-7 (GAD-7), Patient Health Questionnaire-9 (PHQ-9), and satisfactory questionnaire. Comparisons were conducted using independent, paired sample t-test, and Chi-square test to analyze changes in anxiety and depression levels.

Results:

Compared to the baseline score (5.13 ± 4.623), the post-depression score (3.68 ± 4.397) was significantly lowered in the chatbot group (P=0.008). Similarly, the reduced anxiety score was also observed after the chatbot test (pre vs. post: 4.74 ± 4.742 vs. 3.4 ± 3.748, P=0.005). No significant differences were found in the pre-post for either depression (P=0.379) or anxiety score (P=0.190). No statistically significant difference was observed in service satisfaction between the two service platforms (P=0.324).

Conclusions:

The AI chatbot was comparable to the traditional nurse hotline in alleviating participants’ anxiety and depression after responding to inquiries during the COVID-19 outbreak. 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.


 Citation

Please cite as:

Chen C, Lam T, Yip KM, So HK, Lum TYS, Wong ICK, Yam JCS, Chui CSL, Ip P

Comparison of an AI Chatbot With a Nurse Hotline in Reducing Anxiety and Depression Levels in the General Population: Pilot Randomized Controlled Trial

JMIR Hum Factors 2025;12:e65785

DOI: 10.2196/65785

PMID: 40048637

PMCID: 11906115

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.