Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Learning and Large Language Models for Audio and Text Analysis in Predicting Suicidal Acts in Chinese Psychological Support Hotlines

Yining Chen, Jianqiang Li, Changwei Song, Qing Zhao, Yongsheng Tong, Guanghui Fu

TL;DR

This study designed to validate whether deep learning models and LLMs, using audio and transcribed text from support hotlines, can effectively predict suicide risk, and proposed a simple LLM-based pipeline that first summarizes transcribed text from approximately one hour of speech to extract key features, and then predict suicidial bahaviours in the future.

Abstract

Suicide is a pressing global issue, demanding urgent and effective preventive interventions. Among the various strategies in place, psychological support hotlines had proved as a potent intervention method. Approximately two million people in China attempt suicide annually, with many individuals making multiple attempts. Prompt identification and intervention for high-risk individuals are crucial to preventing tragedies. With the rapid advancement of artificial intelligence (AI), especially the development of large-scale language models (LLMs), new technological tools have been introduced to the field of mental health. This study included 1284 subjects, and was designed to validate whether deep learning models and LLMs, using audio and transcribed text from support hotlines, can effectively predict suicide risk. We proposed a simple LLM-based pipeline that first summarizes transcribed text from approximately one hour of speech to extract key features, and then predict suicidial bahaviours in the future. We compared our LLM-based method with the traditional manual scale approach in a clinical setting and with five advanced deep learning models. Surprisingly, the proposed simple LLM pipeline achieved strong performance on a test set of 46 subjects, with an F1 score of 76\% when combined with manual scale rating. This is 7\% higher than the best speech-based deep learning models and represents a 27.82\% point improvement in F1 score compared to using the manual scale apporach alone. Our study explores new applications of LLMs and demonstrates their potential for future use in suicide prevention efforts.

Deep Learning and Large Language Models for Audio and Text Analysis in Predicting Suicidal Acts in Chinese Psychological Support Hotlines

TL;DR

This study designed to validate whether deep learning models and LLMs, using audio and transcribed text from support hotlines, can effectively predict suicide risk, and proposed a simple LLM-based pipeline that first summarizes transcribed text from approximately one hour of speech to extract key features, and then predict suicidial bahaviours in the future.

Abstract

Suicide is a pressing global issue, demanding urgent and effective preventive interventions. Among the various strategies in place, psychological support hotlines had proved as a potent intervention method. Approximately two million people in China attempt suicide annually, with many individuals making multiple attempts. Prompt identification and intervention for high-risk individuals are crucial to preventing tragedies. With the rapid advancement of artificial intelligence (AI), especially the development of large-scale language models (LLMs), new technological tools have been introduced to the field of mental health. This study included 1284 subjects, and was designed to validate whether deep learning models and LLMs, using audio and transcribed text from support hotlines, can effectively predict suicide risk. We proposed a simple LLM-based pipeline that first summarizes transcribed text from approximately one hour of speech to extract key features, and then predict suicidial bahaviours in the future. We compared our LLM-based method with the traditional manual scale approach in a clinical setting and with five advanced deep learning models. Surprisingly, the proposed simple LLM pipeline achieved strong performance on a test set of 46 subjects, with an F1 score of 76\% when combined with manual scale rating. This is 7\% higher than the best speech-based deep learning models and represents a 27.82\% point improvement in F1 score compared to using the manual scale apporach alone. Our study explores new applications of LLMs and demonstrates their potential for future use in suicide prevention efforts.
Paper Structure (31 sections, 4 figures, 2 tables)

This paper contains 31 sections, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Suicide related prediction by audio
  4. Suicide related prediction by text
  5. LLM in medical domain
  6. Comparison with related studies
  7. Processes of the Beijing psychological support hotline
  8. Suicide risk assessment
  9. Crisis intervention
  10. Follow-up support
  11. Methods
  12. LLMs based text analysis
  13. Speech to text transformation
  14. Context-based text summarization for memory stream conduction
  15. LLM for suicide prediction
  16. ...and 16 more sections

Figures (4)

  • Figure 1: The flowchart of this research, including (A) the workflow of the psychological support hotline, and two parts of experiments for the suicidal prediction task: (B) deep learning based speech analysis models, and (C) the proposed LLM text analysis pipeline.
  • Figure 2: Process and Details of Generating Methods for Segmentation and Summarization.
  • Figure 3: Data distribution for deep learning model training and validation, and few-shot prompt LLM conduction. $N$ denotes the number of subjects.
  • Figure 4: The summarized transcripts and key factors related to the final decision generated by the LLM, along with the meta-information (including the ground truth) of case (A), (B), (C) and (D) and model predictions. Note that, The GPT output is not a direct mental scale score but is instead designed to align with the manual scale scoring system for combined manual+GPT calculations. "High risk" refers to a high risk of suicide.