Development and Evaluation of HopeBot: an LLM-based chatbot for structured and interactive PHQ-9 depression screening

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Guo, Zhijun, Lai, Alvina, Ive, Julia, Petcu, Alexandru, Wang, Yutong, Qi, Luyuan, Thygesen, Johan H, Li, Kezhi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915728939024384
author Guo, Zhijun
Lai, Alvina
Ive, Julia
Petcu, Alexandru
Wang, Yutong
Qi, Luyuan
Thygesen, Johan H
Li, Kezhi
author_facet Guo, Zhijun
Lai, Alvina
Ive, Julia
Petcu, Alexandru
Wang, Yutong
Qi, Luyuan
Thygesen, Johan H
Li, Kezhi
contents Static tools like the Patient Health Questionnaire-9 (PHQ-9) effectively screen depression but lack interactivity and adaptability. We developed HopeBot, a chatbot powered by a large language model (LLM) that administers the PHQ-9 using retrieval-augmented generation and real-time clarification. In a within-subject study, 132 adults in the United Kingdom and China completed both self-administered and chatbot versions. Scores demonstrated strong agreement (ICC = 0.91; 45% identical). Among 75 participants providing comparative feedback, 71% reported greater trust in the chatbot, highlighting clearer structure, interpretive guidance, and a supportive tone. Mean ratings (0-10) were 8.4 for comfort, 7.7 for voice clarity, 7.6 for handling sensitive topics, and 7.4 for recommendation helpfulness; the latter varied significantly by employment status and prior mental-health service use (p < 0.05). Overall, 87.1% expressed willingness to reuse or recommend HopeBot. These findings demonstrate voice-based LLM chatbots can feasibly serve as scalable, low-burden adjuncts for routine depression screening.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05984
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Development and Evaluation of HopeBot: an LLM-based chatbot for structured and interactive PHQ-9 depression screening
Guo, Zhijun
Lai, Alvina
Ive, Julia
Petcu, Alexandru
Wang, Yutong
Qi, Luyuan
Thygesen, Johan H
Li, Kezhi
Artificial Intelligence
Computation and Language
Human-Computer Interaction
Static tools like the Patient Health Questionnaire-9 (PHQ-9) effectively screen depression but lack interactivity and adaptability. We developed HopeBot, a chatbot powered by a large language model (LLM) that administers the PHQ-9 using retrieval-augmented generation and real-time clarification. In a within-subject study, 132 adults in the United Kingdom and China completed both self-administered and chatbot versions. Scores demonstrated strong agreement (ICC = 0.91; 45% identical). Among 75 participants providing comparative feedback, 71% reported greater trust in the chatbot, highlighting clearer structure, interpretive guidance, and a supportive tone. Mean ratings (0-10) were 8.4 for comfort, 7.7 for voice clarity, 7.6 for handling sensitive topics, and 7.4 for recommendation helpfulness; the latter varied significantly by employment status and prior mental-health service use (p < 0.05). Overall, 87.1% expressed willingness to reuse or recommend HopeBot. These findings demonstrate voice-based LLM chatbots can feasibly serve as scalable, low-burden adjuncts for routine depression screening.
title Development and Evaluation of HopeBot: an LLM-based chatbot for structured and interactive PHQ-9 depression screening
topic Artificial Intelligence
Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2507.05984