EUVIMEDEUVIMED entdecken
Open Access

Tree-informed Bayesian multi-source domain adaptation: cross-population probabilistic cause-of-death assignment using verbal autopsy

Zhenke Wu iD, Zehang R Li iD, Irena Chen, Mengbing Li

Biostatistics · 2024

DOI: 10.1093/biostatistics/kxae005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biostatistics, 2024. Verfasst von Zhenke Wu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics, University of Michigan, Ann Arbor, MI 48109, United States. Hauptthemen laut MEDLINE: Bayes Theorem, Autopsy, Cause of Death. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NICHD NIH HHS, National Institute of Child Health and Human Development, Michigan Institute of Data Science.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Determining causes of deaths (CODs) occurred outside of civil registration and vital statistics systems is challenging. A technique called verbal autopsy (VA) is widely adopted to gather information on deaths in practice. A VA consists of interviewing relatives of a deceased person about symptoms of the deceased in the period leading to the death, often resulting in multivariate binary responses. While statistical methods have been devised for estimating the cause-specific mortality fractions (CSMFs) for a study population, continued expansion of VA to new populations (or “domains”) necessitates approaches that recognize between-domain differences while capitalizing on potential similarities. In this article, we propose such a domain-adaptive method that integrates external between-domain similarity information encoded by a prespecified rooted weighted tree. Given a cause, we use latent class models to characterize the conditional distributions of the responses that may vary by domain. We specify a logistic stick-breaking Gaussian diffusion process prior along the tree for class mixing weights with node-specific spike-and-slab priors to pool information between the domains in a data-driven way. The posterior inference is conducted via a scalable variational Bayes algorithm. Simulation studies show that the domain adaptation enabled by the proposed method improves CSMF estimation and individual COD assignment. We also illustrate and evaluate the method using a validation dataset. The article concludes with a discussion of limitations and future directions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bayes TheoremAutopsyCause of DeathHumansModels, StatisticalBiostatistics

Stichwörter der Autor:innen

domain adaptationlatent class modelsspike-and-slab priorvariational Bayesverbal autopsy

Autor:innen und Institutionen

  • Department of Biostatistics, University of Michigan, Ann Arbor, MI 48109, United States.
  • Michigan Institute for Data Science, University of Michigan, Ann Arbor, MI 48109, United States.
  • Department of Statistics, University of California, Santa Cruz, CA 95064, United States.

ORCID-Profile: Zhenke Wu, Zehang R Li

Förderung

  • NICHD NIH HHS
  • National Institute of Child Health and Human Development
  • Michigan Institute of Data Science

Zitieren

APA

Wu, Z., Li, Z. R., Chen, I., & Li, M. (2024). Tree-informed Bayesian multi-source domain adaptation: cross-population probabilistic cause-of-death assignment using verbal autopsy. Biostatistics. https://doi.org/10.1093/biostatistics/kxae005

Vancouver

Wu Z, Li ZR, Chen I, Li M. Tree-informed Bayesian multi-source domain adaptation: cross-population probabilistic cause-of-death assignment using verbal autopsy. Biostatistics. 2024. doi:10.1093/biostatistics/kxae005

BibTeX
@article{Wu2024,
  author = {Wu, Zhenke and Li, Zehang R and Chen, Irena and Li, Mengbing},
  title = {Tree-informed Bayesian multi-source domain adaptation: cross-population probabilistic cause-of-death assignment using verbal autopsy},
  journal = {Biostatistics},
  year = {2024},
  doi = {10.1093/biostatistics/kxae005}
}
Kostenlos starten →