Prediction Models for Cardiac Risk Classification with Nuclear Cardiology Techniques

Mario Petretta, Alberto Cuocolo

Research output: Contribution to journalArticlepeer-review

Abstract

Regression modeling strategies are increasingly used for the management of subjects with cardiovascular diseases as well as for decision-making of subjects without known disease but who are at risk of disease in the short- or long-term or during life span. Accurate individual risk assessment, taking in account clinical, laboratory, and imaging data is useful for choosing among prevention strategies and/or treatments. The value of nuclear cardiology techniques for risk stratification has been well documented. Many models have been proposed and are available for diagnostic and prognostic purposes and several statistical techniques are available for risk stratification. However, current approaches for prognostic modeling are not perfect and present limitations. This review analyzes some specific aspects related to prediction model development and validation.

Original languageEnglish
Article number3
Pages (from-to)1-8
Number of pages8
JournalCurrent Cardiovascular Imaging Reports
Volume9
Issue number1
DOIs
Publication statusPublished - Jan 1 2016

Keywords

  • Algorithms for risk prediction
  • Cardiovascular disease
  • Myocardial perfusion imaging
  • Nuclear cardiology
  • Risk stratification

ASJC Scopus subject areas

  • Cell Biology
  • Histology
  • Applied Microbiology and Biotechnology

Fingerprint Dive into the research topics of 'Prediction Models for Cardiac Risk Classification with Nuclear Cardiology Techniques'. Together they form a unique fingerprint.

Cite this