A multi-stage large language model framework for extracting suicide-related social determinants of health
Our approach improves both the accuracy and transparency of extracting suicide-related SDoH from unstructured texts. These advancements have the potential to support early identification of individuals at risk and inform more effective prevention strategies.
Authors
- Haotian Ma (ORCID: https://orcid.org/0009-0000-9640-3936)
- Yuan Meng (ORCID: https://orcid.org/0000-0002-0963-0581)
- K.K Deng
- Ying Ding (ORCID: https://orcid.org/0000-0003-2567-2009)
- Yunyu Xiao (ORCID: https://orcid.org/0000-0002-0479-1781)
- Xuhai Xu (ORCID: https://orcid.org/0000-0001-5930-3899)
- Yifan Peng (ORCID: https://orcid.org/0000-0001-9309-8331)
- Song Wang (ORCID: https://orcid.org/0000-0002-8224-0424)
- Yuan Wei (ORCID: https://orcid.org/0000-0003-3387-7549)
- Zihan Xu (ORCID: https://orcid.org/0000-0001-6470-6924)
- Jingze Zhang (ORCID: https://orcid.org/0009-0007-4456-8430)
- Joydeep Ghosh (ORCID: https://orcid.org/0000-0002-7366-3548)
- Max Lovitt
Institutions
- Cornell University (US)
- Weill Cornell Medicine (US)
- Columbia University (US)
- The University of Texas at Austin (US)
Publication Details
- Journal
- Communications Medicine
- Published
- 2025-09-29
- DOI
- https://doi.org/10.1038/s43856-025-01114-z
- Primary Topic
- Suicide and Self-Harm Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Institutes of Health
- Centers for Disease Control and Prevention
- National Institute of Mental Health