Risk prediction using natural language processing of electronic mental health records in an inpatient forensic psychiatry setting
Applies seven machine-learning algorithms with four word-list dictionaries (UMLS mental-health terms, DSM-IV diagnoses, a sentiment lexicon, and corpus frequencies) to de-identified forensic-inpatient clinical notes, predicting clinician-assigned risk ratings on three structured instruments: the HCR-20, START, and DASA. Reports best accuracy on the DASA dataset and flags that predicting actual endpoints (self-harm, harm-to-others, victimisation) needs further work.
Publisher
Journal of Biomedical Informatics (Elsevier)
Published
1 Oct 2018
Added
today
Key Findings
- Structured violence-risk instrument ratings (HCR-20/START/DASA) can be partially predicted from free-text clinical notes via NLP
- A sentiment dictionary with LMT/SVM classifiers gave the strongest performance, on the DASA dataset
- Predicting downstream endpoints (self-harm, harm-to-others, victimisation) remained substantially harder than predicting the clinician rating
Methodology Notes
Peer-reviewed, Journal of Biomedical Informatics vol. 86, pp. 49-58 (issue October 2018; exact day not stated), DOI 10.1016/j.jbi.2018.08.007. Retrospective NLP on de-identified forensic inpatient notes; small single-site corpus. sciencedirect.com bot-blocks fetchers; metadata verified via PubMed (PMID 30118855) and Crossref.
Sources
PubMed record (primary)
Archived snapshot (Wayback Machine) — preserved against link rot
Authors
Duy Van Le, James Montgomery, Kenneth C. Kirkby, Joel Scanlan
Tags
Cite This
APA
Duy Van Le et al. (2018). Risk prediction using natural language processing of electronic mental health records in an inpatient forensic psychiatry setting. Journal of Biomedical Informatics (Elsevier). https://pubmed.ncbi.nlm.nih.gov/30118855/
Related Insights
Large language models for psychosocial risk assessment: A multi-method evaluation across suicide, intimate partner violence, and substance misuse
PLOS Digital Health · 27 Apr 2026
Are Natural Language Processing Tools Ready for Predicting Violence Toward Self or Others?
Psychiatric Annals (SLACK Incorporated) · 1 Apr 2026
A machine learning approach to identifying suicide risk among text-based crisis counseling encounters
Frontiers in Psychiatry · 23 Mar 2023
TRAP-18 indicators validated through the forensic linguistic analysis of targeted violence manifestos
Journal of Threat Assessment and Management (American Psychological Association) · 1 Dec 2021