Preprocessing of natural language process variables using a data-driven method improves the association with suicide risk in a large veterans affairs population
AMC-based categorization substantially enhanced the suicide predictive capacity of NLP variables extracted from clinical text. Transforming skewed NLP data with the AMC method holds promise for improving risk prediction models.
Authors
- Jiang Gui (ORCID: https://orcid.org/0000-0001-5377-8914)
- Joshua Levy (ORCID: https://orcid.org/0000-0001-8050-1291)
- Brian Shiner (ORCID: https://orcid.org/0000-0003-1623-8841)
- Weiyi Wu (ORCID: https://orcid.org/0000-0002-1571-5872)
- Siting Li (ORCID: https://orcid.org/0000-0002-8292-1393)
- Maxwell Levis (ORCID: https://orcid.org/0000-0003-3271-6997)
- Monica Dimambro
Institutions
- Dartmouth College (US)
- Cedars-Sinai Medical Center (US)
- White River Junction VA Medical Center (US)
Publication Details
- Journal
- Computers in Biology and Medicine
- Published
- 2025-03-05
- DOI
- https://doi.org/10.1016/j.compbiomed.2025.109939
- Citations
- 5
- Primary Topic
- Mental Health via Writing
- Type
- article
- Field-Weighted Citation Impact
- 12.19