CoChat
Sign Up
Cited by 38Healthcare Decision-Making and RestraintsMachine Learning in HealthcareElectroconvulsive Therapy Studies

Predicting mechanical restraint of psychiatric inpatients by applying machine learning on electronic health data

Open access
Danielsen, A. A., Fenger, M. H. J., Østergaard, S. D., Nielbo, K. L., Mors, O.·2019·Acta Psychiatrica Scandinavica
DOI 10.1111/acps.13061
Open this paper in CoChat — free accountOpen PDF

Abstract

Objective: Mechanical restraint (MR) is used to prevent patients from harming themselves or others during inpatient treatment. The objective of this study was to investigate whether incident MR occurring in the first 3 days following admission could be predicted based on analysis of electronic health data available after the first hour of admission. Methods: The dataset consisted of clinical notes from electronic health records from the Central Denmark Region and data from the Danish Health Registers from patients admitted to a psychiatric department in the period from 2011 to 2015. Supervised machine learning algorithms were trained on a randomly selected subset of the data and validated using an independent test dataset. Results: A total of 5050 patients with 8869 admissions were included in the study. One hundred patients were mechanically restrained in the period between one hour and 3 days after the admission. A Random Forest algorithm predicted MR with an area under the curve of 0.87 (95% CI 0.79–0.93). At 94% specificity, the sensitivity was 56%. Among the ten strongest predictors, nine were derived from the clinical notes. Conclusions: These findings open for the development of an early warning system that may guide interventions to reduce the use of MR.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1111/acps.13061

Cites

42 of 42 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Once a person was admitted as an involuntary patient they were more likely to be subject to use of coercive treatment modalities such as restraint and seclusion than people admitted on a voluntary basis.

    “A similar cycle of coercive care provision may also be evident during admission, with the available literature indicating that once a person was admitted as an involuntary patient they were more likely to be subject to use of coercive treatment modalities such as restraint and seclusion than people admitted on a voluntary basis (34,76–88), and may be more likely to display aggressive behaviours (”

    From The benefits and harms of inpatient involuntary psychiatric treatment: a scoping review (2025) · cites this paper as [79]

    The “Involuntary admission” section identifies involuntary admission as the model’s most important predictor of mechanical restraint, supporting the restraint portion of the claim. The paper’s outcome is mechanical restraint, however; our copy does not establish that involuntarily admitted patients were also more likely than voluntarily admitted patients to experience seclusion. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 2

  1. Roles S, Gouge A, Smith H. Predicting risk of seclusion and restraint in a psychiatric intensive care (PIC) unit. J Psychiatr Ment Health Nurs. 2014;21(5):466-470.
  2. Almvik R, Woods P, Rasmussen K. The Broset violence checklist -Sensitivity, specificity, and interrater reliability. J Interpers Violence. 2000;15(12):1284-1296.

Cited by

Sorted by citations

Related

Authors
Danielsen, A. A., Fenger, M. H. J., Østergaard, S. D., Nielbo, K. L., & Mors, O.
Affiliations
  • Aarhus University (DK)
  • University of Southern Denmark (DK)
Corresponding author
Danielsen, A. A.
ORCID
Venue
Acta Psychiatrica Scandinavica
Publisher
Wiley
Published
2019-07-06
Volume
140
Issue
2
Pages
147-157
ISSN
  • 0001-690X (ISSN-L)
  • 1600-0447
DOI
10.1111/acps.13061
OpenAlex
W2952147341
Cited by
38
References
42
Citations by year
2026: 4 · 2025: 7 · 2024: 12 · 2023: 3 · 2022: 4 · 2021: 6 · 2020: 2
FWCI
3.50
Type
journal article
Language
en
Open access
Licence
onlinelibrary.wiley.com/termsAndConditions#vor (vor)
Locations
  • Acta Psychiatrica Scandinavica (publishedVersion)
  • PubMed (publishedVersion)
  • University of Southern Denmark Research Portal (University of Southern Denmark) (submittedVersion, other-oa)
Funders
  • Aarhus Universitet
  • Danmarks Frie Forskningsfond (7016‐00048)
Topics
  • Social Sciences › Psychology › Clinical Psychology › Healthcare Decision-Making and Restraints
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Medicine › Psychiatry and Mental health › Electroconvulsive Therapy Studies
Keywords
mechanical restraint, psychiatric inpatients, electronic health records, clinical notes, early warning systems, random forest, risk factors, hospitalization
MeSH terms
Machine Learning, Early Warning Score, Mental Disorders, Denmark, Female, Hospitalization, Humans, Inpatients, Male, Predictive Value of Tests, Restraint, Physical, Sensitivity and Specificity, Time Factors, Case-Control Studies, Self-Injurious Behavior, Electronic Health Records

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review