EUVIMEDScopri EUVIMED
Randomisierte kontrollierte StudieVergleichsstudieOpen access

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

Vergleich eines KI-Chatbots mit einer Pflege-Hotline zur Senkung von Angst und Depression in der Allgemeinbevölkerung: pilotierte randomisierte kontrollierte Studie

Chen Chen iD, Kok Tai Lam iD, Ka Man Yip iD, Hung Kwan So iD, Terry Yat Sang Lum iD, Ian Chi Kei Wong iD, Jason C Yam iD, Celine Sze Ling Chui iD, Patrick Ip iD

JMIR Human Factors · 2025-03-06 · 12 · e65785-e65785

DOI: 10.2196/65785 ↗

Auf einen Blick

In einer Pilot-RCT mit 124 Teilnehmenden war ein KI-Chatbot bei Angst und Depression nach der Nutzung mit einer Pflege-Hotline vergleichbar. Im Chatbot-Arm sanken die Werte signifikant.

Fragestellung

Wie wirksam ist ein lokaler KI-Chatbot im Vergleich zu einer konventionellen Pflege-Hotline zur Senkung von Angst und Depression in Hongkong?

Methode

Pilot-randomisierte kontrollierte Studie von Oktober 2022 bis März 2023; 124 Personen 1:1 randomisiert; Vergleich von KI-Chatbot und Pflege-Hotline; Auswertung mit t-Tests und χ²-Test.

Ergebnisse

62 Personen im Chatbot-Arm und 41 in der Hotline-Gruppe beendeten beide Fragebögen. Im Chatbot-Arm sank Depression von 5,13 (SD 4,623) auf 3,68 (SD 4,397; P =.008) und Angst von 4,74 (SD 4,742) auf 3,4 (SD 3,748; P =.005).

Schlussfolgerung der Autor:innen

Der KI-Chatbot war mit der traditionellen Pflege-Hotline bei der Linderung von Angst und Depression nach Anfragen vergleichbar und zeigte Potenzial für kurzfristige Effekte. Größere RCTs sind nach Ansicht der Autor:innen nötig.

Kernaussagen

  • Chatbot und Pflege-Hotline waren bei Angst/Depression vergleichbar
  • Im Chatbot-Arm sanken Depressions- und Angstwerte signifikant
  • Zwischen den Plattformen zeigte sich kein Unterschied in der Zufriedenheit

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Randomisierte kontrollierte Studie in JMIR Human Factors, published online on 2025-03-06. Written by Chen Chen and 8 co-authors. Institution: Department of Paediatrics and Adolescent Medicine, School of Clinical Medicine, Li Ka Shing Faculty of Medicine, University of Hong Kong, Room 115, 1…. Major MEDLINE topics: Depression, Anxiety, Artificial Intelligence, Hotlines. Cited 43 times so far (Crossref); 25 references. The full text is freely available in PubMed Central.

Auf einen BlickAbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

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 χ 2 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.

Subjects

MeSH terms (MEDLINE)

DepressionAnxietyArtificial IntelligenceHotlinesHumansFemalePilot ProjectsMaleHong KongMiddle AgedAdultNursesGenerative Artificial Intelligence

Author keywords

AI chatbotanxietyartificial intelligencedepressioneffectiveness

Authors and institutions

  • Department of Paediatrics and Adolescent Medicine, School of Clinical Medicine, Li Ka Shing Faculty of Medicine, University of Hong Kong, Room 115, 1/F, New Clinical Building, Queen Mary Hospital, 102 Pokfulam Road, Hon…
  • Department of Social Work Administration, University of Hong Kong, Hong Kong SAR, China (Hong Kong).
  • Department of Pharmacology and Pharmacy, Li Ka Shing Faculty of Medicine, University of Hong Kong, Hong Kong SAR, China (Hong Kong).
  • School of Pharmacy, Medical Sciences Division, Macau University of Science and Technology, Macau, China.
  • School of Pharmacy, Aston University, Birmingham, United Kingdom.
  • Department of Ophthalmology and Visual Sciences, Chinese University of Hong Kong, Hong Kong SAR, China (Hong Kong).

ORCID profiles: Chen Chen, Kok Tai Lam, Ka Man Yip, Hung Kwan So, Terry Yat Sang Lum, Ian Chi Kei Wong, Jason C Yam, Celine Sze Ling Chui, Patrick Ip

Cite

APA

Chen, C., Lam, K. T., Yip, K. M., So, H. K., Lum, T. Y. S., Wong, I. C. K., Yam, J. C., Chui, C. S. L., & Ip, P. (2025). Comparison of an AI Chatbot With a Nurse Hotline in Reducing Anxiety and Depression Levels in the General Population: Pilot Randomized Controlled Trial. JMIR Human Factors, 12, e65785-e65785. https://doi.org/10.2196/65785

Vancouver

Chen C, Lam KT, Yip KM, So HK, Lum TYS, Wong ICK, et al. Comparison of an AI Chatbot With a Nurse Hotline in Reducing Anxiety and Depression Levels in the General Population: Pilot Randomized Controlled Trial. JMIR Human Factors. 2025;12:e65785-e65785. doi:10.2196/65785

BibTeX
@article{Chen2025,
  author = {Chen, Chen and Lam, Kok Tai and Yip, Ka Man and So, Hung Kwan and Lum, Terry Yat Sang and Wong, Ian Chi Kei and Yam, Jason C and Chui, Celine Sze Ling and Ip, Patrick},
  title = {Comparison of an AI Chatbot With a Nurse Hotline in Reducing Anxiety and Depression Levels in the General Population: Pilot Randomized Controlled Trial},
  journal = {JMIR Human Factors},
  year = {2025},
  volume = {12},
  pages = {e65785--e65785},
  doi = {10.2196/65785}
}
Start for free →