Research Domain Criteria and Deaths by Suicide in the National Violent Death Reporting System

Can large language models be used to assign research domain criteria (RDoC) scores to suicide death narratives so as to better understand sex- and age-associated psychiatric morbidity among decedents?Using cross-sectional information from 72 585 deaths by suicide in the 2020 to 2021 National Violent Death Reporting System (NVDRS), methods of large language models were applied to score text narratives for RDoC domains. Decedents exhibited clinically elevated scores across most domains, with female and younger decedents scoring higher than male and older decedents, respectively.These findings suggest that, despite the relatively low prevalence of clinically depressed mood in NVDRS deaths by suicide, RDoC scores indicate substantial levels of clinically relevant symptoms at the time of death.

Corresponding Author: Susan D. Cochran, PhD, MS, Department of Epidemiology, UCLA Fielding School of Public Health, 650 Charles E. Young Dr S, Los Angeles, CA 90095 (cochran@ucla.edu).

Link to the article in your story

We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)

Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

Need more information? Contact us.