Bayesian factor models for probabilistic cause of death assessment with verbal autopsies

Kunihama, Tsuyoshi; Li, Zehang; Clark, Samuel J.; McCormick, Tyler H.

doi:10.48550/arxiv.1803.01327

Cited by 2 publications

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, few move beyond the conditional independence assumption (that is, that the probability of observing symptom are independent given COD). Only two current works explicitly model the conditional covariance between symptoms: Li et al [2018b] and Kunihama et al [2018].The former models one common covariance structure across causes, while the latter models cause-specific symptom-level association via a latent factor model. The FActor Regression for Verbal Autopsy (FARVA) model described in the current paper has the most in common with Kunihama et al [2018], which also models symptom-level association via a latent factor model.…”

Section: Cause Of Deathmentioning

confidence: 99%

“…Existing computer-coded VA algorithms include those for which the relationship between symptoms and cause of death is encoded by experts (InterVA [Byass et al, 2012] and InSilicoVA [McCormick et al, 2016]) and those for which it is learned by relying on a labeled subset of the data having known COD (the King and Lu method [King et al, 2008], the Tariff method [James et al, 2011], the Simplified Symptom Pattern method [Murray et al, 2011a], the naive Bayes classifier [Miasnikof et al, 2015], the Bayesian factor model [Kunihama et al, 2018], and latent Gaussian graphical model [Li et al, 2018b]).…”

Section: Introductionmentioning

confidence: 99%

“…That is, assume that once the cause of death is known, the knowledge that an individual had symptom A should not impact belief that an individual had symptom B for ANY combination of symptoms A and B. Recent work [Li et al, 2018b, Kunihama et al, 2018 has shown that this assumption is not valid in general. Logically, this finding is unsurprising; for example, the knowledge that someone had difficulty breathing would increase belief that they had a cough even given that their COD is already known.…”

Section: Introductionmentioning

confidence: 99%

“…Logically, this finding is unsurprising; for example, the knowledge that someone had difficulty breathing would increase belief that they had a cough even given that their COD is already known. Li et al [2018b] and Kunihama et al [2018] have relaxed the conditional independence assumption by probabilistically addressing conditional associations of symptoms given causes. The Bayesian latent Gaussian graphical model of Li et al [2018b] assumes the conditional dependence structure is common across causes, i.e., the symptom-level correlation does not vary with cause.…”

Section: Introductionmentioning

confidence: 99%

“…The Bayesian latent Gaussian graphical model of Li et al [2018b] assumes the conditional dependence structure is common across causes, i.e., the symptom-level correlation does not vary with cause. On the other hand, the latent factor model of Kunihama et al [2018] models the symptomlevel association independently for each cause. Neither allows for covariates (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Bayesian Hierarchical Factor Regression Models to Infer Cause of Death From Verbal Autopsy Data

Moran,

Turner,

Dunson

et al. 2019

Preprint

View full text Add to dashboard Cite

In low-resource settings where vital registration of death is not routine it is often of critical interest to determine and study the cause of death (COD) for individuals and the cause-specific mortality fraction (CSMF) for populations. Post-mortem autopsies, considered the gold standard for COD assignment, are often difficult or impossible to implement due to deaths occurring outside the hospital, expense, and/or cultural norms. For this reason, Verbal Autopsies (VAs) are commonly conducted, consisting of a questionnaire administered to next of kin recording demographic information, known medical conditions, symptoms, and other factors for the decedent. This article proposes a novel class of hierarchical factor regression models that avoid restrictive assumptions of standard methods, allow both the mean and covariance to vary with COD category, and can include covariate information on the decedent, region, or events surrounding death. Taking a Bayesian approach to inference, this work develops an MCMC algorithm and validates the FActor Regression for Verbal Autopsy (FARVA) model in simulation experiments. An application of FARVA to real VA data shows improved goodness-of-fit and better predictive performance in inferring COD and CSMF over competing methods. Code and a user manual are made available at https://github.com/kelrenmor/farva.

show abstract

Section: Cause Of Deathmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Bayesian Hierarchical Factor Regression Models to Infer Cause of Death From Verbal Autopsy Data

Moran,

Turner,

Dunson

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

Using Bayesian Latent Gaussian Graphical Models to Infer Symptom Associations in Verbal Autopsies

Li¹,

McComick²,

Clark³

2020

Bayesian Anal.

Self Cite

View full text Add to dashboard Cite

Learning dependence relationships among variables of mixed types provides insights in a variety of scientific settings and is a well-studied problem in statistics. Existing methods, however, typically rely on copious, high quality data to accurately learn associations. In this paper, we develop a method for scientific settings where learning dependence structure is essential, but data are sparse and have a high fraction of missing values. Specifically, our work is motivated by survey-based cause of death assessments known as verbal autopsies (VAs). We propose a Bayesian approach to characterize dependence relationships using a latent Gaussian graphical model that incorporates informative priors on the marginal distributions of the variables. We demonstrate such information can improve estimation of the dependence structure, especially in settings with little training data. We show that our method can be integrated into existing probabilistic cause-of-death assignment algorithms and improves model performance while recovering dependence patterns between symptoms that can inform efficient questionnaire design in future data collection.

show abstract

Bayesian factor models for probabilistic cause of death assessment with verbal autopsies

Cited by 2 publications

References 0 publications

Bayesian Hierarchical Factor Regression Models to Infer Cause of Death From Verbal Autopsy Data

Bayesian Hierarchical Factor Regression Models to Infer Cause of Death From Verbal Autopsy Data

Using Bayesian Latent Gaussian Graphical Models to Infer Symptom Associations in Verbal Autopsies

Contact Info

Product

Resources

About