Startseite Extrapolating sparse gold standard cause of death designations to characterize broader catchment areas
Artikel
Lizenziert
Nicht lizenziert Erfordert eine Authentifizierung

Extrapolating sparse gold standard cause of death designations to characterize broader catchment areas

  • Robert H. Lyles EMAIL logo , Solveig A. Cunningham , Suprateek Kundu , Quique Bassat , Inácio Mandomando , Charfudin Sacoor , Victor Akelo , Dickens Onyango , Emily Zielinski-Gutierrez und Allan W. Taylor
Veröffentlicht/Copyright: 11. August 2020
Veröffentlichen auch Sie bei De Gruyter Brill
Manuskript einreichen Informationen für Autor*innen
Epidemiologic Methods
Aus der Zeitschrift Epidemiologic Methods Band 9 Heft 1

Abstract

Objectives

The Child Health and Mortality Prevention Surveillance (CHAMPS) Network is designed to elucidate and track causes of under-5 child mortality and stillbirth in multiple sites in sub-Saharan Africa and South Asia using advanced surveillance, laboratory and pathology methods. Expert panels provide an arguable gold standard determination of underlying cause of death (CoD) on a subset of child deaths, in part through examining tissue obtained via minimally invasive tissue sampling (MITS) procedures. We consider estimating a population-level distribution of CoDs based on this sparse but precise data, in conjunction with data on subgrouping characteristics that are measured on the broader population of cases and are potentially associated with selection for MITS and with cause-specific mortality.

Methods

We illustrate how estimation of each underlying CoD proportion using all available data can be addressed equivalently in terms of a Horvitz-Thompson adjustment or a direct standardization, uncovering insights relevant to the designation of appropriate subgroups to adjust for non-representative sampling. Taking advantage of the functional form of the result when expressed as a multinomial distribution-based maximum likelihood estimator, we propose small-sample adjustments to Bayesian credible intervals based on Jeffreys or related weakly informative Dirichlet prior distributions.

Results

Our analyses of early data from CHAMPS sites in Kenya and Mozambique and accompanying simulation studies demonstrate the validity of the adjustment approach under attendant assumptions, together with marked performance improvements associated with the proposed adjusted Bayesian credible intervals.

Conclusions

Adjustment for non-representative sampling of those validated via gold standard diagnostic methods is a critical endeavor for epidemiologic studies like CHAMPS that seek extrapolation of CoD proportion estimates.

Keywords: credible interval; maximum likelihood; missing data; selection bias
Corresponding author: Robert H. Lyles, Department of Biostatistics and Bioinformatics, The Rollins School of Public Health of Emory University, 1518 Clifton Rd. N.E., Mailstop 1518-002-3AA, Atlanta, GA, 30322, USA, Phone: 404-727-1310, E-mail:

Funding source: Bill and Melinda Gates Foundation

  1. Acknowledgments: We are grateful to Drs. John Williamson, Rob Breiman, Dianna M. Blau, Cynthia Whitney and Pratima Raghunathan for their helpful comments, and to Dr. Donna Brogan for her constructive conceptual input.

  2. Research funding: The CHAMPS study is funded by the Bill & Melinda Gates Foundation. ISGlobal is amember of the CERCA Programme, Generalitat de Catalunya (https://cerca.cat/en/suma/). CISM is supported by the Government of Mozambique and the Spanish Agency for International Development (AECID). Partial support was also provided by the Emory center for AIDS research (P30AI050409).

  3. Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.

  4. Competing interests: The findings and conclusions in this report are those of the author(s) and do not necessarily represent the official position of the Centers for Disease Control and Prevention. The authors declare no conflicts of interest.

  5. Informed consent: Informed consent was obtained from all individuals included in this study.

  6. Ethical approval: The local Institutional Review Board deemed the study exempt from review.

Appendix 1: Standard error estimation

As discussed in Section 2.1, the MLE (π^c,ML) for the proportion of deaths in the target population due to underlying cause c is algebraically equivalent to π^c,A and π^c,B in Eqns. (3) and (4). Writing the MLE in terms of estimates of the G×(C + 1) probabilities in Table 2 yields.

π^c,ML=∑g=1Gp^gc(1+p^g0∑c=1Cp^gc)

where p^gc=ngc/N (g = 1,…, G; c = 0,…, C).

Derivatives of the corresponding function with respect to the pgc’s are as follows (g = 1,…, G; c = 1,…, C):

∂πc∂pg0=pgc∑c=1Cpgc;
∂πc∂pgc′=−pgcpg0(∑c=1Cpgc)−2,if c≠c′;
∂πc∂pgc′=−pgcpg0(∑c=1Cpgc)−2+(1+pg0∑c=1Cpgc),if c=c′

We obtain multivariate delta method-based estimated standard errors by stringing the p^gc’s into a G×(C + 1) element vector: p^=(p^10,p^11,...,p^1C, p^20,p^21,...,p^2C, ..., p^G0,p^G1,...,p^GC)′. The multinomial covariance matrix structure then yields Σ^=Va^r(p^)=(1/N)[Diag(p^)−p^p^′], so that

Va^r(π^c,ML)≐D^c′Σ^D^c

where D^c is the column vector containing estimates of the above derivatives (replacing each pgc by p^gc) aligned with the order of the elements in p^.

References

Bassat, Q., J. Ordi, J. Vila, M. R. Ismail, C. Carrilho, M. Lacerda, K. Munguambe, F. Odhiambo, B. Lell, S. Sow, and Z. A. Bhutta. 2013. “Development of a Post-Mortem Procedure to Reduce the Uncertainty Regarding Causes of Death in Developing Countries.” Lancet Global Health 1: e125–6. https://doi.org/10.1016/S2214-109X(13)70037-8.Suche in Google Scholar

Berger, J. O., J. M. Bernardo, and D. Sun. 2015. “Overall Objective Priors.” Bayesian Analysis 10: 189–221. https://doi.org/10.1214/14-BA915.Suche in Google Scholar

Breiman, L., J. Friedman, C. J. Stone, and R. A. Olshen. 1984. Classification and Regression Trees. Boca Raton, FL: Chapman and Hall/CRC.Suche in Google Scholar

Brown, L. D., T. T. Cai, and A. Das Gupta. 2001. “Interval Estimation for a Binomial Proportion.” Statistical Science 16: 101–33. https://doi.org/10.1214/ss/1009213286.Suche in Google Scholar

Butler, D. 2010. “Verbal Autopsy Methods Questioned.” Nature 467: 1015. https://doi.org/10.1038/4671015a.Suche in Google Scholar

Byass, P. 2014. “Usefulness of the Population Health Metrics Research Consortium Gold Standard Verbal Autopsy Data for General Verbal Autopsy Methods.” BMC Medicine 12: 23. https://doi.org/10.1186/1741-7015-12-23.Suche in Google Scholar

Carlin, B. P., and T. A. Louis. 2009. Bayesian Methods for Data Analysis, 3rd ed. Boca Raton, FL: Chapman and Hall/CRC.Suche in Google Scholar

Garenne, M. 2014. “Prospects for Automated Diagnosis of Verbal Autopsies.” BMC Medicine 12: 18. https://doi.org/10.1186/1741-7015-12-18.Suche in Google Scholar

GBD 2015 Child Mortality Collaborators. 2016. “Global, Regional, National, and Selected Subnational Levels of Stillbirths, Neonatal, Infant, and Under-5 Mortality, 1980–2015: a Systematic Analysis for the Global Burden of Disease Study 2015.” Lancet 388: 1725–74. https://doi.org/10.1016/S0140-6736(16)31575-6.Suche in Google Scholar

Horvitz, D. G., and D. J. Thompson. 1952. “A Generalization of Sampling Without Replacement From a Finite Population.” Journal of the American Statistical Association 47: 663–85. https://doi.org/10.2307/2280784.Suche in Google Scholar

Jeffreys, H. 1946. “An Invariant Form for the Prior Probability in Estimation Problems.” In Proceedings of the Royal Statistical Society (Series A) 186: 453–61. https://doi.org/10.1098/rspa.1946.0056.Suche in Google Scholar PubMed

Jha, P. 2014. “Reliable Direct Measurement of Causes of Death In Low- and Middle-Income Countries.” BMC Medicine 12: 19. https://doi.org/10.1186/1741-7015-12-19.Suche in Google Scholar PubMed PubMed Central

Little, R. J. A., and D. B. Rubin. 2002. Statistical Analysis with Missing Data. New York, NY: John Wiley.10.1002/9781119013563Suche in Google Scholar

Lyles, R. H., L. L. Kupper, H. X. Barnhart, and S. L. Martin. 2015. “Numeric Score-Based Conditional and Overall Change-in-Status Indices for Ordered Categorical Data.” Statistics in Medicine 34: 3622–36. https://doi.org/10.1002/sim.6559.Suche in Google Scholar

McCormick, T. H., Z. Li, C. Calvert, A. C. Crampin, K. Kahn, and S. J. Clark. 2016. “Probabilistic Cause-of-Death Assignment Using Verbal Autopsies.” Journal of the American Statistical Association 111: 1036–49. https://doi.org/10.1080/01621459.2016.1152191.Suche in Google Scholar

Mikkelsen, L., D. E. Phillips, C. AbouZahr, P. W. Setel, D. De Savigny, R. Lozano, and A. D. Lopez. 2015. “A Global Assessment of Civil Registration and Vital Statistics Systems: Monitoring Data Quality and Progress.” Lancet 386: 1395–406. https://doi.org/10.1016/S0140-6736(15)60171-4.Suche in Google Scholar

Rothman, K. J., S. Greenland, and T. L. Lash. 2008. Modern Epidemiology, 3rd ed. Philadelphia, PA: Lippincott, Williams and Wilkins.Suche in Google Scholar

Sangeetha, U., M. Subbiah, and M. R. Srinivasan. 2013. “Estimation of Confidence Intervals for Multinomial Proportions of Sparse Contingency Tables Using Bayesian Methods.” International Journal of Scientific and Research Publications 3: 1–7. https://doi.org/10.29322/www.ijsrp.org.Suche in Google Scholar

Setel, P. W., Macfarlane, S. B., Szreter, S., Mikkelsen, L., Jha, P., Stout, S., AbouZahr, C., and Monitoring of Vital Events (MoVE) writing group. 2007. “A Scandal of Invisibility: Making Everyone Count by Counting Everyone.” Lancet 370: 1569–77, https://doi.org/10.1016/S0140-6736(07)61307-5.Suche in Google Scholar

United Nations Inter-agency Group for Child Mortality Estimation (UN IGME). 2017. Levels & Trends in Child Mortality: Report 2017, Estimates Developed by the Un Inter-Agency Group for Child Mortality Estimation. New York, NY: United Nations Children’s Fund.Suche in Google Scholar

Wakefield, J., G.-A. Fuglstad, A. Riebler, J. Godwin, K. Wilson, and S. J. Clark. 2018. “Estimating Under-Five Mortality in Space and Time in a Developing World Context.” Statistical Methods in Medical Research, 28: 2614–34. https://doi.org/10.1177/0962280218767988.Suche in Google Scholar PubMed PubMed Central

Received: 2019-12-02
Accepted: 2020-04-28
Published Online: 2020-08-11

© 2020 Walter de Gruyter GmbH, Berlin/Boston

Artikel in diesem Heft

  1. Editorial
  2. The mean prevalence
  3. Research Articles
  4. Heterogeneous indirect effects for multiple mediators using interventional effect models
  5. Sleep habits and their association with daytime sleepiness among medical students of Tanta University, Egypt
  6. Population attributable fractions for continuously distributed exposures
  7. A real-time search strategy for finding urban disease vector infestations
  8. Disease mapping models for data with weak spatial dependence or spatial discontinuities
  9. A comparison of cause-specific and competing risk models to assess risk factors for dementia
  10. A simple index of prediction accuracy in multiple regression analysis
  11. A comparison of approaches for estimating combined population attributable risks (PARs) for multiple risk factors
  12. Posterior predictive treatment assignment methods for causal inference in the context of time-varying treatments
  13. Random effects tumour growth models for identifying image markers of mammography screening sensitivity
  14. Extrapolating sparse gold standard cause of death designations to characterize broader catchment areas
  15. Extending balance assessment for the generalized propensity score under multiple imputation
  16. Regression analysis of unmeasured confounding
  17. The Use of Logic Regression in Epidemiologic Studies to Investigate Multiple Binary Exposures: An Example of Occupation History and Amyotrophic Lateral Sclerosis
  18. Meeting the Assumptions of Inverse-Intensity Weighting for Longitudinal Data Subject to Irregular Follow-Up: Suggestions for the Design and Analysis of Clinic-Based Cohort Studies
https://doi.org/10.1515/em-2019-0031
Schlagwörter für diesen Artikel
credible interval; maximum likelihood; missing data; selection bias

Artikel in diesem Heft

  1. Editorial
  2. The mean prevalence
  3. Research Articles
  4. Heterogeneous indirect effects for multiple mediators using interventional effect models
  5. Sleep habits and their association with daytime sleepiness among medical students of Tanta University, Egypt
  6. Population attributable fractions for continuously distributed exposures
  7. A real-time search strategy for finding urban disease vector infestations
  8. Disease mapping models for data with weak spatial dependence or spatial discontinuities
  9. A comparison of cause-specific and competing risk models to assess risk factors for dementia
  10. A simple index of prediction accuracy in multiple regression analysis
  11. A comparison of approaches for estimating combined population attributable risks (PARs) for multiple risk factors
  12. Posterior predictive treatment assignment methods for causal inference in the context of time-varying treatments
  13. Random effects tumour growth models for identifying image markers of mammography screening sensitivity
  14. Extrapolating sparse gold standard cause of death designations to characterize broader catchment areas
  15. Extending balance assessment for the generalized propensity score under multiple imputation
  16. Regression analysis of unmeasured confounding
  17. The Use of Logic Regression in Epidemiologic Studies to Investigate Multiple Binary Exposures: An Example of Occupation History and Amyotrophic Lateral Sclerosis
  18. Meeting the Assumptions of Inverse-Intensity Weighting for Longitudinal Data Subject to Irregular Follow-Up: Suggestions for the Design and Analysis of Clinic-Based Cohort Studies
Jetzt anmelden und 20% sparen
Institutioneller Zugang
Wie funktioniert Authentifizierung?
Haben Sie eine Idee, wie wir unsere Website verbessern können?
Bitte schreiben Sie uns.
© 2025 De Gruyter Brill
Heruntergeladen am 16.9.2025 von https://www.degruyterbrill.com/document/doi/10.1515/em-2019-0031/html
Button zum nach oben scrollen