Automating multi-label crisis detection in psychological support hotlines with pre-trained models
PLOS Digital Health · 13.05.2026 · 5 (5) · e0001383
DOI: 10.1371/journal.pdig.0001383 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 13.05.2026. Verfasst von Shuying Rao und 9 weiteren Autor:innen. Beteiligte Einrichtung: Affiliated Mental Health Center and Hangzhou Seventh People's Hospital and School of Brain Science and Brain Medicine, Zhejiang University School of …. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Major Project, National Natural Science Foundation of China.
Abstract (Originalsprache)
Psychological support hotlines provide immediate help to individuals in crisis, with operators assessing emotional states and suicide risk. However, increasing demand has led to a shortage of trained professionals, emphasizing the need for AI-driven crisis detection models. This study included 1,057 calls from the Hangzhou Hotline (2022–2023) to evaluate the effectiveness of deep learning and pre-trained models in detecting psychological crises using audio (Wave2Vec, Whisper) and transcribed text (RoBERTa, GPT). We adopted two strategies: deep learning classification with pre-trained models and Large Language Models (LLMs)-based prediction via prompt engineering (GPT-4 and DeepSeek series). The deep learning framework, employing GPT embeddings excelled in multi-label predictions compared to auditory model, achieving 80.48% [80.18%, 80.78%] F1 scores for identifying high-risk calls in prospective tests. Fusion experiments revealed that acoustic features offered negligible predictive value compared with text semantics. Notably, GPT-4o and DeepSeek-R1, utilizing few-shot learning, demonstrated performance comparable to the GPT-embedding deep learning model across multiple tasks. This suggests that their advanced Chain-of-Thought reasoning effectively mitigates data dependency gap, enabling LLMs to align with clinical domains using a few examples. Expert evaluation confirmed the clinical applicability of GPT-generated explanations. Taken together, these findings highlight the potential of LLMs in mental health crisis detection and lay the foundation for future research.
Autor:innen und Institutionen
- Affiliated Mental Health Center and Hangzhou Seventh People's Hospital and School of Brain Science and Brain Medicine, Zhejiang University School of Medicine, Hangzhou, China.
- College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China.
- Liangzhu Laboratory, MOE Frontier Science Center for Brain Science and Brain-machine Integration, State Key Laboratory of Brain-machine Intelligence, Zhejiang University, Hangzhou, China.
- School of Biomedical Informatics, University of Texas at Dallas, Richardson, Texas, United States of America.
- College of Computer Science and Technology, Zhejiang University, Hangzhou, China.
- Zhejiang Key Laboratory of Clinical and Basic Research for Psychiatric Diseases, Hangzhou, China.
ORCID-Profile: Guifeng Deng, Haiteng Jiang
Förderung
- National Science and Technology Major Project
- National Natural Science Foundation of China
Zitieren
APA
Rao, S., Deng, G., Song, H., Chen, Q., Luo, M., Zhang, Y., Zhao, S., Pan, G., Li, T., & Jiang, H. (2026). Automating multi-label crisis detection in psychological support hotlines with pre-trained models. PLOS Digital Health, 5(5), e0001383. https://doi.org/10.1371/journal.pdig.0001383
Vancouver
Rao S, Deng G, Song H, Chen Q, Luo M, Zhang Y, et al. Automating multi-label crisis detection in psychological support hotlines with pre-trained models. PLOS Digital Health. 2026;5(5):e0001383. doi:10.1371/journal.pdig.0001383
BibTeX
@article{Rao2026,
author = {Rao, Shuying and Deng, Guifeng and Song, Haidong and Chen, Qiuxia and Luo, Mingjin and Zhang, Yaoyun and Zhao, Sha and Pan, Gang and Li, Tao and Jiang, Haiteng},
title = {Automating multi-label crisis detection in psychological support hotlines with pre-trained models},
journal = {PLOS Digital Health},
year = {2026},
volume = {5},
number = {5},
pages = {e0001383},
doi = {10.1371/journal.pdig.0001383}
}
EUVIMED