Apparent and Internal Validity of a Monte Carlo–Markov Model for Cardiovascular Disease in a Cohort Follow-up Study

Rogier L. Nijhuis, Theo Stijnen, Anna Peeters, Jacqueline C.M. Witteman, Albert Hofman and M. G. Myriam Hunink
Additional contact information
Theo Stijnen: Department of Epidemiology and Biostatistics, Erasmus Medical Center, Rotterdam, the Netherlands
Anna Peeters: Department of Public Health, Erasmus Medical Center, Rotterdam, the Netherlands
Albert Hofman: Department of Epidemiology and Biostatistics, Erasmus Medical Center, Rotterdam, the Netherlands
M. G. Myriam Hunink: Department of Radiology, Erasmus Medical Center, Rotterdam, the Netherlands; Departments of Health Policy & Management, Harvard School of Public Health, Boston, MA; Dept. of Epidemiology & Biostatistics, Erasmus Medical Center Rotterdam, P.O. Box 1738, 3000 DR Rotterdam, the Netherlands; phone: +31 10 408 7391; fax: +31 10 408 9382 m.hunink@erasmusmc.nl

Medical Decision Making, 2006, vol. 26, issue 2, 134-144

Abstract: Objective . To determine the apparent and internal validity of the Rotterdam Ischemic heart disease & Stroke Computer (RISC) model, a Monte Carlo–Markov model, designed to evaluate the impact of cardiovascular disease (CVD) risk factors and their modification on life expectancy (LE) and cardiovascular disease–free LE (DFLE) in a general population (hereinafter, these will be referred to together as (DF)LE). Methods. The model is based on data from the Rotterdam Study, a cohort follow-up study of 6871 subjects aged 55 years and older who visited the research center for risk factor assessment at baseline (1990–1993) and completed a follow-up visit 7 years later (original cohort). The transition probabilities and risk factor trends used in the RISC model were based on data from 3501 subjects (the study cohort). To validate the RISC model, the number of simulated CVD events during 7 years’ follow-up were compared with the observed number of events in the study cohort and the original cohort, respectively, and simulated (DF)LEs were compared with the (DF)LEs calculated from multistate life tables. Results .Both in the study cohort and in the original cohort, the simulated distribution of CVD events was consistent with the observed number of events (CVD deaths: 7.1% v. 6.6% and 7.4% v. 7.6%, respectively; non-CVD deaths: 11.2% v. 11.5% and 12.9% v. 13.0%, respectively). The distribution of (DF)LEs estimated with the RISC model consistently encompassed the (DF)LEs calculated with multistate life tables. Conclusions. The simulated events and (DF)LE estimates from the RISC model are consistent with observed data from a cohort follow-up study

Keywords: validation; apparent and internal; Monte Carlo–Markov model; cardiovascular disease; cohort follow-up study (search for similar items in EconPapers)
Date: 2006
References: View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://journals.sagepub.com/doi/10.1177/0272989X05284103 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:sae:medema:v:26:y:2006:i:2:p:134-144

DOI: 10.1177/0272989X05284103

Access Statistics for this article

More articles in Medical Decision Making
Bibliographic data for series maintained by SAGE Publications ().