Machine Learning Approach to Inpatient Violence Risk Assessment Using Routinely Collected Clinical Notes in Electronic Health Records.

Journal: JAMA network open

PMID: 31268542

Abstract

IMPORTANCE: Inpatient violence remains a significant problem despite existing risk assessment methods. The lack of robustness and the high degree of effort needed to use current methods might be mitigated by using routinely registered clinical notes.

Authors

Vincent Menger

Department of Information and Computing Sciences, Utrecht University, Utrecht, the Netherlands.
Marco Spruit

Department of Computing and Information Sciences, Utrecht University, Utrecht, Netherlands.
Roel van Est

Data Research Office, Antes, Parnassia Group, Rotterdam, the Netherlands.
Eline Nap

Data Research Office, Antes, Parnassia Group, Rotterdam, the Netherlands.
Floor Scheepers

Department of Psychiatry, University Medical Center Utrecht, Utrecht, the Netherlands.

Keywords

Adult Aggression Behavior Observation Techniques Electronic Health Records Female Hospitals, Psychiatric Humans Inpatients Machine Learning Male Middle Aged Netherlands Prognosis Reproducibility of Results Risk Assessment Risk Factors Violence

External Resources

View on PubMed Access via DOI PubMed (31268542)

Machine Learning Approach to Inpatient Violence Risk Assessment Using Routinely Collected Clinical Notes in Electronic Health Records.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals