Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2012 Jan 6;10:1.
doi: 10.1186/1478-7954-10-1.

Modeling Causes of Death: An Integrated Approach Using CODEm

Affiliations
Free PMC article

Modeling Causes of Death: An Integrated Approach Using CODEm

Kyle J Foreman et al. Popul Health Metr. .
Free PMC article

Abstract

Background: Data on causes of death by age and sex are a critical input into health decision-making. Priority setting in public health should be informed not only by the current magnitude of health problems but by trends in them. However, cause of death data are often not available or are subject to substantial problems of comparability. We propose five general principles for cause of death model development, validation, and reporting.

Methods: We detail a specific implementation of these principles that is embodied in an analytical tool - the Cause of Death Ensemble model (CODEm) - which explores a large variety of possible models to estimate trends in causes of death. Possible models are identified using a covariate selection algorithm that yields many plausible combinations of covariates, which are then run through four model classes. The model classes include mixed effects linear models and spatial-temporal Gaussian Process Regression models for cause fractions and death rates. All models for each cause of death are then assessed using out-of-sample predictive validity and combined into an ensemble with optimal out-of-sample predictive performance.

Results: Ensemble models for cause of death estimation outperform any single component model in tests of root mean square error, frequency of predicting correct temporal trends, and achieving 95% coverage of the prediction interval. We present detailed results for CODEm applied to maternal mortality and summary results for several other causes of death, including cardiovascular disease and several cancers.

Conclusions: CODEm produces better estimates of cause of death trends than previous methods and is less susceptible to bias in model specification. We demonstrate the utility of CODEm for the estimation of several major causes of death.

Figures

Figure 1
Figure 1
Examples of missingness patterns observed in data for a single country and cause of death. Green represents available data and red represents missing.
Figure 2
Figure 2
Example weighting schemes for 100 component models at different values of ψ.
Figure 3
Figure 3
Heatmap of stability in maternal mortality component model rankings. Each row represents a component model, and each column corresponds to how many hold-outs are used when ranking. Rows are sorted by rankings using all 25 hold-outs. Cells are colored based on their ranking, with the green models being the best and red the worst. The last column displays in-sample ranks. The figure shows that rankings stabilize as hold-outs increase, and that in-sample ranking does not correlate well with out-of-sample.
Figure 4
Figure 4
In-sample, test 1, and test 2 performance on RMSE and trend test for maternal mortality component models.
Figure 5
Figure 5
Correlation between test 1 and test 2 rankings of maternal mortality component models.
Figure 6
Figure 6
Correlation in maternal mortality component model rankings by number of hold-outs performed.

Similar articles

See all similar articles

Cited by 103 articles

See all "Cited by" articles

References

    1. Mathers CD, Fat DM, Inoue M, Rao C, Lopez AD. Counting the dead and what they died from: an assessment of the global status of cause of death data. Bull World Health Organ. 2005;83:171–177. - PMC - PubMed
    1. Sibai AM. Mortality certification and cause-of-death reporting in developing countries. Bull World Health Organ. 2004;82:83–83. - PMC - PubMed
    1. Ruzicka LT, Lopez AD. The use of cause-of-death statistics for health situation assessment: national and international experiences. World Health Stat Q. 1990;43:249–258. - PubMed
    1. Gakidou E, Mallinger L, Abbot-Klafter J, Guerrero R, Villalpando S, Lopez Ridaura R, Aekplakorn W, Naghavi M, Lim S, Lozano R, Murray CJ. Management of diabetes and associated cardiovascular risk factors in seven countries: A comparison of data from national health examination surveys. Bulletin of the World Health Organization. 2011;89:172–183. doi: 10.2471/BLT.10.080820. - DOI - PMC - PubMed
    1. Danaei G, Finucane MM, Lu Y, Singh GM, Cowan MJ, Paciorek CJ, Lin JK, Farzadfar F, Khang Y-H, Stevens GA, Rao M, Ali MK, Riley LM, Robinson CA, Ezzati M. National, regional, and global trends in fasting plasma glucose and diabetes prevalence since 1980: systematic analysis of health examination surveys and epidemiological studies with 370 country-years and 2·7 million participants. The Lancet. 2011;378:31–40. doi: 10.1016/S0140-6736(11)60679-X. - DOI - PubMed

LinkOut - more resources

Feedback