Back to search

University of Ioannina

Empirical assessment of the discrimination ability of cardiovascular disease risk prediction models for mortality

Abstract

dc:description

Prognostic tools should be evaluated in several sequential stages: initial model performance (model development), prospective validation in independent cohorts (external validation of a model), impact on patient management and outcome and cost-effectiveness. However, even for established and widely used prognostic tools, many of these steps suffer from methodological limitations and in many cases are missing. Moreover, it is important to highlight the paucity of evidence around their impact on patient management and clinical outcomes. Such important evidence would ideally come from randomized control trials (RCTs), which compare the outcomes of patients whose management is guided by the proposed prognostic tool with the outcomes of patients who are managed without it. However, there are so many prognostic tools, that it is impossible to evaluate all of them in RCTs. Efforts should focus around those with most promising results. In selecting which models to test in randomized trials, one may wish to consider not only satisfactory, validated discriminating ability, but also what is the respective change in disease management that can be anticipated; how effective are the available preventive or treatment interventions for the disease and how much room exists for improvement; what is the expected cost to get the information required for building the model, and to implement it in practice; and how likely it is that the model can be used widely by non-expert health practitioners. Going through such a checklist is likely to eliminate the large majority of proposed prognostic models. Nevertheless, there are currently no randomized trials assessing the implementation of any cardiovascular prediction models. Such studies should be encouraged. A more through and systematic research agenda would be useful to build surrounding late implementation issues, including ease of use, and impact on resources in diverse settings.The bottom line is that the best test of a prediction model is not accuracy but improved clinical outcomes. Compared with clinician judgment, a prediction model might improve diagnostic accuracy, reduce costs and harms, and lead to improved health outcomes. Documenting this benefit requires RCTs in which providers are randomized to use the proposed prediction model or not, and the outcome is improved health. Very few models have been tested in this way. Prediction of risk is not enough—we need evidence that prediction can lead to actions that reduce risk beyond what would occur without the prediction rule.

Degree

thesis:*
Grantor dc:publisher
University of Ioannina
Year dc:date
2015

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Siontis, Georgios
  • Σιόντης, Γεώργιος

Subjects

dc:subject × 16

Rights

dc:rights
Statement dc:rights
  • BY_NC_ND
Language dc:language
eng

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/41448

Chain of custody

source
Harvested from
Greek National Archive of PhD Theses
Base URL
phdtheses.ekt.gr/eadd_oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Siontis, Georgios; Σιόντης, Γεώργιος. Empirical assessment of the discrimination ability of cardiovascular disease risk prediction models for mortality. University of Ioannina, 2015. http://hdl.handle.net/10442/hedi/41448