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

Decision support for psychiatric diagnosis based on a simple questionnaire

K Yana1, H Mizuta, K Kawachi

  • 1Department of Electronic Informatics, Hosei University, Tokyo, Japan. kyana@bme.ei.hosei.ac.jp

Methods of Information in Medicine
|February 21, 1998
PubMed
Summary

This study shows that Neural Network and Pseudo Bayesian classifiers can aid psychiatrists in diagnosing psychiatric disorders like schizophrenia. The Neural Network classifier achieved a 77.3% correct decision rate, outperforming an experienced psychiatrist.

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

Plasma cfDNA analysis of alectinib resistance-related gene alterations in the J-ALEX study.

ESMO open·2025
Same author

Effect of pregnancy on lower limb lymphedema in patients treated with multisite lymphaticovenular anastomoses (MLVAS).

Lymphology·2020
Same author

Matrix changes in articular cartilage in the knee of patients with rheumatoid arthritis after biological therapy: 1-year follow-up evaluation by T2 and T1ρ MRI quantification.

Clinical radiology·2018
Same author

Angiopoietin-like protein 2 promotes chondrogenic differentiation during bone growth as a cartilage matrix factor.

Osteoarthritis and cartilage·2017
Same author

Tuneable strong optical absorption in a graphene-insulator-metal hybrid plasmonic device.

Scientific reports·2017
Same author

MRI T1ρ and T2 mapping for the assessment of articular cartilage changes in patients with medial knee osteoarthritis after hemicallotasis osteotomy.

Bone & joint research·2016

Area of Science:

  • Psychiatry
  • Computer Science
  • Medical Informatics

Background:

  • Accurate diagnosis of psychiatric disorders is crucial for effective treatment.
  • Traditional diagnostic methods can be time-consuming and subjective.
  • Developing objective tools to assist clinicians is an ongoing area of research.

Purpose of the Study:

  • To compare the diagnostic accuracy of Pseudo Bayesian and Neural Network classifiers.
  • To evaluate the utility of these classifiers in categorizing patients into common ICD classes (schizophrenic, emotional, neurotic disorders).
  • To assess if these computational methods can assist psychiatrists in diagnosis.

Main Methods:

  • Utilized a dataset of 100 completed yes/no questionnaires from outpatient psychiatric visits.

Related Experiment Videos

  • Developed and trained Pseudo Bayesian and Neural Network classifiers.
  • Compared classifier performance against each other and against an experienced psychiatrist's diagnoses.

    • Main Results:

    • The Neural Network classifier achieved an average correct decision rate of 77.3%.
    • The Pseudo Bayesian Classifier achieved an average correct decision rate of 73.3%.
    • Both classifiers demonstrated higher accuracy than an experienced psychiatrist using the same limited data.

    Conclusions:

    • Computational classifiers, specifically Neural Networks, show promise in assisting psychiatric diagnoses.
    • These tools can potentially improve diagnostic efficiency and accuracy in clinical settings.
    • Further research with larger datasets could validate and refine these diagnostic support systems.