Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Validation of the Computerized Suicide Risk Scale--a backpropagation neural network instrument (CSRS-BP).

I Modai1, M Ritsner, R Kurs

  • 1Sha'ar Menashe Mental Health Center, Research Institute for Psychiatric Studies, Bruce Rappaport Faculty of Medicine, Technion, Haifa, Israel. shrmodai@matat.health.gov.il

European Psychiatry : the Journal of the Association of European Psychiatrists
|April 26, 2002
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Cancer risk among parents and siblings of patients with schizophrenia.

The British journal of psychiatry : the journal of mental science·2007
Same author

Cancer and schizophrenia.

The British journal of psychiatry : the journal of mental science·2006
Same author

Psychiatric services and training for children and adolescents in Europe: results of a country survey.

European child & adolescent psychiatry·2004
Same author

Maternal transmission disequilibrium of the glutamate receptor GRIK2 in schizophrenia.

Neuroreport·2004
Same author

Is the WKL1 gene associated with schizophrenia?

American journal of medical genetics. Part B, Neuropsychiatric genetics : the official publication of the International Society of Psychiatric Genetics·2004
Same author

Quality of life and coping with schizophrenia symptoms.

Quality of life research : an international journal of quality of life aspects of treatment, care and rehabilitation·2003

The Computerized Suicide Risk Scale based on backpropagation neural networks (CSRS-BP) accurately identified past medically serious suicide attempt (MSSA) records but failed in face-to-face patient interviews. Previous suicide attempt history improved detection but remained insufficient for individual patient assessment.

Area of Science:

  • Psychiatry
  • Artificial Intelligence in Healthcare
  • Clinical Psychology

Background:

  • Medically serious suicide attempts (MSSA) are key predictors of suicide.
  • The Computerized Suicide Risk Scale (CSRS-BP) showed prior success in identifying patient records of MSSA.
  • Validation of CSRS-BP in direct patient assessment is needed.

Purpose of the Study:

  • To validate the CSRS-BP using direct patient interviews.
  • To compare CSRS-BP performance against expert psychiatrists using the CSRS checklist.
  • To compare CSRS-BP with the Risk Estimator for Suicide (RES) and Suicide Risk Scale (SRS).

Main Methods:

  • 250 psychiatric inpatients were assessed using SCID DSM-IV.
  • Expert psychiatrists completed CSRS checklists and RES for patients.

Related Experiment Videos

  • Patients completed the SRS; CSRS-BP was run for each patient.

    • Main Results:

    • Initial performance of CSRS-BP, RES, SRS, and experts was poor.
    • Inclusion of previous suicide attempt data improved sensitivity and specificity 2-4 times.
    • Despite improvements, results remained statistically insignificant for individual patient detection.

    Conclusions:

    • CSRS-BP was effective for MSSA records but not for face-to-face interviews.
    • Previous suicide attempt history is crucial but insufficient for individual MSSA detection.
    • SRS and RES scales demonstrated poor detection rates and could not validate CSRS-BP.