Identifying past-year self-reported suicidality in outpatients with somatic symptom disorder using an interpretable machine-learning model: a multicenter study with an online calculator
In SSD outpatients, an interpretable RANGER-based model showed strong internal performance for classifying participants who reported past-year self-reported suicidality, and yielded favorable clinical net benefit across relevant decision thresholds. A web-based calculator illustrates potential usability in outpatient settings; external validation and prospective implementation studies are warranted before routine adoption.
Authors
- Xing Wang (ORCID: https://orcid.org/0000-0002-3230-3482)
- Peng Wang (ORCID: https://orcid.org/0000-0002-3475-1561)
- Yunhui Zhong (ORCID: https://orcid.org/0009-0006-0777-7009)
- Shuixiu Lai
- Tieshi Zhu
- Yibo Li (ORCID: https://orcid.org/0009-0004-9696-3801)
Institutions
- Guangdong Medical College (CN)
- Tianjin Medical University General Hospital (CN)
- Huzhou Normal University (CN)
- Ganzhou People's Hospital (CN)
- Central People's Hospital of Zhanjiang (CN)
- Jiangxi Applied Engineering Vocational Institute (CN)
- Third People's Hospital of Huzhou (CN)
- Vrije Universiteit Amsterdam (NL)
- Erasmus University Rotterdam (NL)
Publication Details
- Journal
- BMC Psychiatry
- Published
- 2026-02-18
- DOI
- https://doi.org/10.1186/s12888-026-07901-9
- Primary Topic
- Suicide and Self-Harm Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00