• Corpus ID: 245424726

Bayesian Nested Latent Class Models for Cause-of-Death Assignment using Verbal Autopsies Across Multiple Domains

@inproceedings{Li2021BayesianNL,
  title={Bayesian Nested Latent Class Models for Cause-of-Death Assignment using Verbal Autopsies Across Multiple Domains},
  author={Zehang Richard Li and Zhenke Wu and I-Chen Chen and Samuel J. Clark},
  year={2021}
}
Understanding cause-specific mortality rates is crucial for monitoring population health and designing public health interventions. Worldwide, two-thirds of deaths do not have a cause assigned. Verbal autopsy (VA) is a well-established tool to collect information describing deaths outside of hospitals by conducting surveys to caregivers of a deceased person. It is routinely implemented in many lowand middle-income countries. Statistical algorithms to assign cause of death using VAs are… 
Tree-informed Bayesian multi-source domain adaptation: cross-population probabilistic cause-of-death assignment using verbal autopsy
TLDR
Simulation studies show that the domain adaptation enabled by the proposed method improves CSMF estimation and individual COD assignment and the paper concludes with a discussion on limitations and future directions.

References

SHOWING 1-10 OF 39 REFERENCES
Tree-informed Bayesian multi-source domain adaptation: cross-population probabilistic cause-of-death assignment using verbal autopsy
TLDR
Simulation studies show that the domain adaptation enabled by the proposed method improves CSMF estimation and individual COD assignment and the paper concludes with a discussion on limitations and future directions.
Bayesian hierarchical factor regression models to infer cause of death from verbal autopsy data
TLDR
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 are proposed.
Probabilistic Cause-of-Death Assignment Using Verbal Autopsies
TLDR
A new statistical tool known as InSilicoVA is developed to classify cause of death using information acquired through verbal autopsy, which shares uncertainty between cause ofdeath assignments for specific individuals and the distribution of deaths by cause across the population.
Regularized Bayesian transfer learning for population-level etiological distributions
TLDR
A parsimonious hierarchical Bayesian transfer learning framework to directly estimate population-level class probabilities in a target domain, using any baseline classifier trained on source-domain, and a small labeled target-domain dataset and introduces a novel shrinkage prior for the transfer error rates.
Quantifying the Contributions of Training Data and Algorithm Logic to the Performance of Automated Cause-assignment Algorithms for Verbal Autopsy.
TLDR
It is demonstrated that in general the adequacy of the information about the joint distribution between symptoms and cause affects performance at least as much or more than algorithm logic.
Verbal Autopsy Methods with Multiple Causes of Death
TLDR
By generalizing current approaches to analyze multiple causes, it is shown how most of the difficult assumptions underlying existing methods can be dropped and make physician review, expert algorithms, and parametric statistical assumptions unnecessary.
Using Bayesian Latent Gaussian Graphical Models to Infer Symptom Associations in Verbal Autopsies.
TLDR
This work proposes a Bayesian approach to characterize dependence relationships using a latent Gaussian graphical model that incorporates informative priors on the marginal distributions of the variables and demonstrates such information can improve estimation of the dependence structure, especially in settings with little training data.
Extracting Cause of Death From Verbal Autopsy With Deep Learning Interpretable Methods
TLDR
This work addresses the gap in technology allowed to automatically analyze the responses of the VA questionnaire with the narrative captured by the interviewer excluded by developing a set of models for automatic Cause of Death ascertainment in VAs with a focus on the textual information.
Improving performance of the Tariff Method for assigning causes of death to verbal autopsies
TLDR
Tariff 2.0 provides an estimation of COD from VAs with better performance at the individual and population level than the previous version of this method, and it is publicly available for use.
Population-aware hierarchical bayesian domain adaptation via multi-component invariant learning
TLDR
Experimental results for an influenza prediction task on four datasets gathered from different contexts show the model can improve prediction in the case of largely unlabelled target data from a new environment and different constituent population, by harnessing both environment and population invariant information.
...
...