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

Posttraumatic stress disorder: diagnostic data analysis by data mining methodology.

Igor Marinić1, Fran Supek, Zrnka Kovacić

  • 1Dubrava University Hospital, Department of Psychiatry, Referral Center of the Ministry of Health and Social Welfare for Stress-related Disorders, Zagreb, Croatia.

Croatian Medical Journal
|April 17, 2007
PubMed
Summary
This summary is machine-generated.

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

Age-dependent mutational loads in human tRNA genes are tumor-specific and result in chimeric tRNA sequences that could disrupt the genetic code.

Genome research·2026
Same author

The DNA dialect: a comprehensive guide to pretrained genomic language models.

Molecular systems biology·2026
Same author

The Impact of Prolonged Stress of COVID-19 Pandemic and Earthquakes on Internet-Based Addictive Behaviour and Quality of Life in Croatia.

International journal of environmental research and public health·2025
Same author

Variable efficiency of nonsense-mediated mRNA decay across human tissues, tumors and individuals.

Genome biology·2025
Same author

Schizophrenia treatment preferences of psychiatrists versus guidelines: A European perspective.

European psychiatry : the journal of the Association of European Psychiatrists·2025
Same author

Joint inference of mutational signatures from indels and single-nucleotide substitutions reveals prognostic impact of DNA repair deficiencies.

Genome medicine·2025
Same journal

Updated analysis of the Bronze Age population genetics from Bezdanjača Cave - the case of I2a1a male individuals.

Croatian medical journal·2026
Same journal

Systemic mesenchymal stem cell therapy for reduction of inflammatory burden in a patient with juvenile-onset rheumatoid arthritis and dialysis-dependent renal failure.

Croatian medical journal·2026
Same journal

Systemic metabolic, hormonal, and glycomic remodeling during a 72-hour fast in healthy adults: a pilot study.

Croatian medical journal·2026
Same journal

Artificial intelligence in pathology: a framework for preserving brain capital in the diagnostic apex.

Croatian medical journal·2026
Same journal

When algorithms testify: artificial intelligence-driven DNA analysis, evidentiary standards, and criminal justice reform.

Croatian medical journal·2026
Same journal

Artificial intelligence enables scale, consistency, and rigor in forensic identity inference.

Croatian medical journal·2026
See all related articles

Data mining effectively assesses posttraumatic stress disorder (PTSD) diagnostic symptoms. Comorbid diagnoses, particularly neurotic, stress-related, and somatoform disorders, are crucial indicators in PTSD assessment.

Area of Science:

  • Psychiatry
  • Data Science
  • Computational Psychology

Background:

  • Posttraumatic stress disorder (PTSD) diagnosis relies on symptom assessment.
  • Accurate differentiation from other psychiatric conditions is clinically significant.
  • Intelligent data analysis offers novel approaches to diagnostic challenges.

Purpose of the Study:

  • To apply data mining techniques for enhanced diagnostic symptom assessment in PTSD.
  • To evaluate the predictive power of different data sources for PTSD diagnosis.
  • To identify key diagnostic features using machine learning models.

Main Methods:

  • Utilized random forest classifier for predictive modeling.
  • Developed models based on structured psychiatric interviews, psychiatric scales (CAPS, PANSS, HAMA, HAMD), and combined data.

Related Experiment Videos

  • Trained specialized models weighting PTSD or non-PTSD classes and constructed class prototypes.

    • Main Results:

    • The interview-based model effectively distinguished PTSD from comorbid disorders.
    • Psychiatric scales (CAPS, PANSS) and comorbid diagnoses were key predictors in scale-based and combined models.
    • Specialized models improved prediction for targeted classes, albeit with minor overall accuracy trade-offs.

    Conclusions:

    • Data mining is applicable for analyzing structured psychiatric data in PTSD.
    • Comorbid diagnoses (neurotic, stress-related, somatoform) are consistently important.
    • Key interview data include disability, hospitalizations, and military service duration; scale data include CAPS scores and arousal symptoms.