Related Experiment Video
Updated: Aug 8, 2026
03:14
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Mortality Research With Artificial Intelligence Tools: Applying Language Models to the National Violent Death
John R Blosnich1, Jaspreet Ranjit1, Swabha Swayamdipta1
1John R. Blosnich is with the Suzanne Dworak-Peck School of Social Work at the University of Southern California, Los Angeles. Jaspreet Ranjit and Swabha Swayamdipta are with the Thomas Lord Department of Computer Science in the Viterbi School of Engineering at the University of Southern California.
American Journal of Public Health
|August 6, 2026
Summary
Artificial intelligence (AI) tools can analyze suicide death narratives to aid prevention research. This study demonstrates AI
Area of Science:
- Public Health
- Data Science
- Artificial Intelligence
Background:
- Suicide deaths in the US have risen for decades without significant decline.
- Electronic health records and large datasets are increasingly used in suicide prevention research.
- Artificial intelligence (AI) tools, including machine learning and language models, show promise for suicide prediction.
Purpose of the Study:
- To review the application of AI in suicide prevention research.
- To demonstrate how AI tools can expedite the analysis of suicide death narratives.
- To utilize a large dataset of suicide death narratives for AI-driven analysis.
Main Methods:
- Review of AI applications in suicide prevention.
- Analysis of suicide death narratives from the National Violent Death Reporting System (NVDRS) using AI, specifically language models.
- Utilizing 756,645 narratives from 483,303 suicide deaths (2003-2023).
Main Results:
- AI tools, particularly language models, can efficiently process and analyze large volumes of unstructured text data from suicide death narratives.
- The study demonstrates the feasibility of using AI to extract insights from extensive narrative data, which is otherwise unmanageable for humans.
- AI enables faster and potentially more comprehensive analysis of factors contributing to suicide deaths.
Conclusions:
- AI offers a powerful approach to analyze the vast amount of narrative data available in suicide prevention research.
- Language models can significantly expedite the analysis of suicide death narratives, aiding researchers in identifying patterns and risk factors.
- Leveraging AI with datasets like NVDRS can enhance suicide prevention strategies and research efforts.