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

Computation modes of multivariate positive predictive characteristics

M Malik1, T R Church

  • 1Department of Cardiological Sciences, St. George's Hospital Medical School, London, England. m.malik@sghms.ac.uk

Pacing and Clinical Electrophysiology : PACE
|June 1, 1997
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

Gallbladder tuberculosis: an unlikely diagnosis after laparoscopic cholecystectomy.

South African journal of surgery. Suid-Afrikaanse tydskrif vir chirurgie·2026
Same author

Pediatric asthma management via integration of a remote spirometry device into an EHR-based artificial intelligence-powered clinical decision support system: A feasibility pragmatic clinical trial.

Contemporary clinical trials·2025
Same author

Massive jejunal gastrointestinal stromal tumour bleed - a case report.

South African journal of surgery. Suid-Afrikaanse tydskrif vir chirurgie·2025
Same author

BENNETT'S FRACTURE: A NARRATIVE REVIEW OF CURRENT LITERATURE.

Georgian medical news·2024
Same author

RECENT TRENDS IN THE USE OF CELL SALVAGER FOR ORTHOPAEDIC TRAUMA AND ELECTIVE SURGERIES-A NARRATIVE REVIEW.

Georgian medical news·2024
Same author

THE PREVALENCE OF SARCOPENIA AND ITS EFFECTS ON OUTCOMES IN POLYTRAUMA.

Georgian medical news·2024
Same journal

Conduction-System Versus Biventricular Pacing for CRT in HFrEF: Pairwise and Network Meta-Analysis.

Pacing and clinical electrophysiology : PACE·2026
Same journal

First Report of Left-Sided Transvenous Pacemaker Implantation Through a Bicaval TricValve Prosthesis.

Pacing and clinical electrophysiology : PACE·2026
Same journal

Internal Jugular Vein as an Alternative Access for Pacemaker Implantation: A Mostly Left IJ Case Series.

Pacing and clinical electrophysiology : PACE·2026
Same journal

AV Node Ablation and Conduction System Pacing Versus Biventricular Pacing in Patients With AF and HF.

Pacing and clinical electrophysiology : PACE·2026
Same journal

Evaluation of the Effect of Electromagnetic Fields Emitted by Electric Vehicles on Cardiac Pacemakers.

Pacing and clinical electrophysiology : PACE·2026
Same journal

Dual Coronary Sinus Lead Strategy to Avoid Tricuspid Valve Traversal in Biventricular Pacing.

Pacing and clinical electrophysiology : PACE·2026
See all related articles

Comparing two methods for multivariate receiver operating characteristic (ROC) and positive predictive characteristic (PPC) analysis, this study found that the optimal approach for predicting mortality after myocardial infarction depends on the specific data. Both methods should be used for precise retrospective studies.

Area of Science:

  • * Medical Informatics
  • * Biostatistics
  • * Cardiovascular Research

Background:

  • * Multivariate statistical models are crucial for predicting clinical outcomes.
  • * Receiver Operating Characteristic (ROC) and Positive Predictive Characteristic (PPC) analyses are common methods for evaluating diagnostic tests.
  • * Traditional ROC/PPC computation involves independent variation of dichotomy limits for each clinical variable.

Purpose of the Study:

  • * To compare two distinct methods for computing multivariate ROC and PPC curves.
  • * To assess the performance of these methods in predicting 2-year all-cause mortality post-myocardial infarction.
  • * To determine the optimal approach for retrospective multifactorial studies.

Main Methods:

  • * Two approaches for multivariate ROC/PPC computation were evaluated: independent dichotomy limits vs. linear combination of variables.

Related Experiment Videos

  • * Both methods were implemented using exhaustive computer search without distributional assumptions.
  • * Signal-averaged ECG indices (time- and spectral-domain) were used to predict mortality in a demonstration study.

    • Main Results:

    • * The optimal method for computing ROC and PPC curves was found to be data-dependent.
    • * No single approach universally outperformed the other across all data characteristics.
    • * Both methods demonstrated feasibility for use in multifactorial outcome prediction.

    Conclusions:

    • * The choice between independent dichotomy limits and linear combination for multivariate ROC/PPC analysis is context-specific.
    • * To enhance precision in retrospective multifactorial studies, both computational approaches should be employed and compared.
    • * This comparative analysis aids in selecting the most accurate predictive model for specific clinical datasets.