Risk predictive modelling for diabetes and cardiovascular disease

Andre Pascal Kengne, Katya Masconi, Vivian Nchanchou Mbanya, Alain Zingraff Lekoubou Looti, Justin Basile Echouffo-Tcheugui, Tandi E. Matsha

Research output: Contribution to journalReview article

12 Citations (Scopus)

Abstract

Absolute risk models or clinical prediction models have been incorporated in guidelines, and are increasingly advocated as tools to assist risk stratification and guide prevention and treatments decisions relating to common health conditions such as cardiovascular disease (CVD) and diabetes mellitus. We have reviewed the historical development and principles of prediction research, including their statistical underpinning, as well as implications for routine practice, with a focus on predictive modelling for CVD and diabetes. Predictive modelling for CVD risk, which has developed over the last five decades, has been largely influenced by the Framingham Heart Study investigators, while it is only ∼20 years ago that similar efforts were started in the field of diabetes. Identification of predictive factors is an important preliminary step which provides the knowledge base on potential predictors to be tested for inclusion during the statistical derivation of the final model. The derived models must then be tested both on the development sample (internal validation) and on other populations in different settings (external validation). Updating procedures (e.g. recalibration) should be used to improve the performance of models that fail the tests of external validation. Ultimately, the effect of introducing validated models in routine practice on the process and outcomes of care as well as its cost-effectiveness should be tested in impact studies before wide dissemination of models beyond the research context. Several predictions models have been developed for CVD or diabetes, but very few have been externally validated or tested in impact studies, and their comparative performance has yet to be fully assessed. A shift of focus from developing new CVD or diabetes prediction models to validating the existing ones will improve their adoption in routine practice.

Original languageEnglish (US)
Pages (from-to)1-12
Number of pages12
JournalCritical Reviews in Clinical Laboratory Sciences
Volume51
Issue number1
DOIs
StatePublished - Jan 1 2014

Fingerprint

Medical problems
Cardiovascular Diseases
Knowledge Bases
Research
Cost-Benefit Analysis
Diabetes Mellitus
Research Personnel
Guidelines
Cost effectiveness
Health
Population

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Clinical Biochemistry
  • Biochemistry, medical

Cite this

Kengne, Andre Pascal ; Masconi, Katya ; Mbanya, Vivian Nchanchou ; Lekoubou Looti, Alain Zingraff ; Echouffo-Tcheugui, Justin Basile ; Matsha, Tandi E. / Risk predictive modelling for diabetes and cardiovascular disease. In: Critical Reviews in Clinical Laboratory Sciences. 2014 ; Vol. 51, No. 1. pp. 1-12.
@article{c91d4d62205a4800af7679f1098c2a42,
title = "Risk predictive modelling for diabetes and cardiovascular disease",
abstract = "Absolute risk models or clinical prediction models have been incorporated in guidelines, and are increasingly advocated as tools to assist risk stratification and guide prevention and treatments decisions relating to common health conditions such as cardiovascular disease (CVD) and diabetes mellitus. We have reviewed the historical development and principles of prediction research, including their statistical underpinning, as well as implications for routine practice, with a focus on predictive modelling for CVD and diabetes. Predictive modelling for CVD risk, which has developed over the last five decades, has been largely influenced by the Framingham Heart Study investigators, while it is only ∼20 years ago that similar efforts were started in the field of diabetes. Identification of predictive factors is an important preliminary step which provides the knowledge base on potential predictors to be tested for inclusion during the statistical derivation of the final model. The derived models must then be tested both on the development sample (internal validation) and on other populations in different settings (external validation). Updating procedures (e.g. recalibration) should be used to improve the performance of models that fail the tests of external validation. Ultimately, the effect of introducing validated models in routine practice on the process and outcomes of care as well as its cost-effectiveness should be tested in impact studies before wide dissemination of models beyond the research context. Several predictions models have been developed for CVD or diabetes, but very few have been externally validated or tested in impact studies, and their comparative performance has yet to be fully assessed. A shift of focus from developing new CVD or diabetes prediction models to validating the existing ones will improve their adoption in routine practice.",
author = "Kengne, {Andre Pascal} and Katya Masconi and Mbanya, {Vivian Nchanchou} and {Lekoubou Looti}, {Alain Zingraff} and Echouffo-Tcheugui, {Justin Basile} and Matsha, {Tandi E.}",
year = "2014",
month = "1",
day = "1",
doi = "10.3109/10408363.2013.853025",
language = "English (US)",
volume = "51",
pages = "1--12",
journal = "Critical Reviews in Clinical Laboratory Sciences",
issn = "1040-8363",
publisher = "Informa Healthcare",
number = "1",

}

Risk predictive modelling for diabetes and cardiovascular disease. / Kengne, Andre Pascal; Masconi, Katya; Mbanya, Vivian Nchanchou; Lekoubou Looti, Alain Zingraff; Echouffo-Tcheugui, Justin Basile; Matsha, Tandi E.

In: Critical Reviews in Clinical Laboratory Sciences, Vol. 51, No. 1, 01.01.2014, p. 1-12.

Research output: Contribution to journalReview article

TY - JOUR

T1 - Risk predictive modelling for diabetes and cardiovascular disease

AU - Kengne, Andre Pascal

AU - Masconi, Katya

AU - Mbanya, Vivian Nchanchou

AU - Lekoubou Looti, Alain Zingraff

AU - Echouffo-Tcheugui, Justin Basile

AU - Matsha, Tandi E.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Absolute risk models or clinical prediction models have been incorporated in guidelines, and are increasingly advocated as tools to assist risk stratification and guide prevention and treatments decisions relating to common health conditions such as cardiovascular disease (CVD) and diabetes mellitus. We have reviewed the historical development and principles of prediction research, including their statistical underpinning, as well as implications for routine practice, with a focus on predictive modelling for CVD and diabetes. Predictive modelling for CVD risk, which has developed over the last five decades, has been largely influenced by the Framingham Heart Study investigators, while it is only ∼20 years ago that similar efforts were started in the field of diabetes. Identification of predictive factors is an important preliminary step which provides the knowledge base on potential predictors to be tested for inclusion during the statistical derivation of the final model. The derived models must then be tested both on the development sample (internal validation) and on other populations in different settings (external validation). Updating procedures (e.g. recalibration) should be used to improve the performance of models that fail the tests of external validation. Ultimately, the effect of introducing validated models in routine practice on the process and outcomes of care as well as its cost-effectiveness should be tested in impact studies before wide dissemination of models beyond the research context. Several predictions models have been developed for CVD or diabetes, but very few have been externally validated or tested in impact studies, and their comparative performance has yet to be fully assessed. A shift of focus from developing new CVD or diabetes prediction models to validating the existing ones will improve their adoption in routine practice.

AB - Absolute risk models or clinical prediction models have been incorporated in guidelines, and are increasingly advocated as tools to assist risk stratification and guide prevention and treatments decisions relating to common health conditions such as cardiovascular disease (CVD) and diabetes mellitus. We have reviewed the historical development and principles of prediction research, including their statistical underpinning, as well as implications for routine practice, with a focus on predictive modelling for CVD and diabetes. Predictive modelling for CVD risk, which has developed over the last five decades, has been largely influenced by the Framingham Heart Study investigators, while it is only ∼20 years ago that similar efforts were started in the field of diabetes. Identification of predictive factors is an important preliminary step which provides the knowledge base on potential predictors to be tested for inclusion during the statistical derivation of the final model. The derived models must then be tested both on the development sample (internal validation) and on other populations in different settings (external validation). Updating procedures (e.g. recalibration) should be used to improve the performance of models that fail the tests of external validation. Ultimately, the effect of introducing validated models in routine practice on the process and outcomes of care as well as its cost-effectiveness should be tested in impact studies before wide dissemination of models beyond the research context. Several predictions models have been developed for CVD or diabetes, but very few have been externally validated or tested in impact studies, and their comparative performance has yet to be fully assessed. A shift of focus from developing new CVD or diabetes prediction models to validating the existing ones will improve their adoption in routine practice.

UR - http://www.scopus.com/inward/record.url?scp=84893104891&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893104891&partnerID=8YFLogxK

U2 - 10.3109/10408363.2013.853025

DO - 10.3109/10408363.2013.853025

M3 - Review article

C2 - 24304342

AN - SCOPUS:84893104891

VL - 51

SP - 1

EP - 12

JO - Critical Reviews in Clinical Laboratory Sciences

JF - Critical Reviews in Clinical Laboratory Sciences

SN - 1040-8363

IS - 1

ER -