Regularized Bayesian transfer learning for population-level etiological distributions

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

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.

Transporting a Prediction Model for Use in a New Target Population

We considered methods for transporting a prediction model for use in a new target population, both when outcome and covariate data for model development are available from a source population that has a different covariate distribution compared with the target population and when covariate data (but not outcome data) are available from the target population. We discuss how to tailor the prediction model to account for differences in the data distribution between the source population and the target population. We also discuss how to assess the model's performance (e.g., by estimating the mean squared prediction error) in the target population. We provide identifiability results for measures of model performance in the target population for a potentially misspecified prediction model under a sampling design where the source and the target population samples are obtained separately. We introduce the concept of prediction error modifiers that can be used to reason about tailoring measures of model performance to the target population. We illustrate the methods in simulated data and apply them to transport a prediction model for lung cancer diagnosis from the National Lung Screening Trial to the nationally representative target population of trial-eligible individuals in the National Health and Nutrition Examination Survey.

Toward Understanding Death

Evidence-based approaches to preventing child death require evidence; without data on common causes of child mortality, taking effective action to prevent these deaths is difficult at best. Minimally invasive tissue sampling (MITS) is a potentially powerful, but nascent, technique to obtain gold standard information on causes of death. The Gates Foundation committed to further establishing the methodology and obtain the highest quality information on the major causes of death for children under 5 years. In 2018, the MITS Surveillance Alliance was launched to implement, refine, and enhance the use of MITS across high mortality settings. The Alliance and its members have contributed to some remarkable opportunities to improve mortality surveillance, and we have only just begun to understand the possibilities on larger scales. This supplement showcases studies conducted by MITS Surveillance Alliance members and represents a significant contribution to the cause-of-death literature from high mortality settings.

Minimally Invasive Tissue Sampling Surveillance Alliance-Facilitating the Expansion of Pathology-Based Mortality Surveillance

The Minimally Invasive Tissue Sampling (MITS) Surveillance Alliance was created with funding from the Bill & Melinda Gates Foundation to expand pathology-based mortality surveillance and to support the generation of improved cause-of-death (CoD) data. MITS, also known as minimally invasive autopsy, has evolved to become an important tool to improve CoD ascertainment. Here, we describe the 18 articles included in this supplement that present advanced methods for improving MITS and related areas of research, summarize the expansion of the use of MITS, report on findings from a variety of research projects, and address the importance of postmortem approaches taken during the novel coronavirus disease 2019 pandemic. Support by the scientific and global health community for enhancements and innovation is needed for the broader adoption of MITS-informed CoD as a critical tool to better understand mortality in low- and middle-income countries and identify interventions for the prevention of premature death.

Methods for correcting inference based on outcomes predicted by machine learning

Many modern problems in medicine and public health leverage machine-learning methods to predict outcomes based on observable covariates. In a wide array of settings, predicted outcomes are used in subsequent statistical analysis, often without accounting for the distinction between observed and predicted outcomes. We call inference with predicted outcomes postprediction inference. In this paper, we develop methods for correcting statistical inference using outcomes predicted with arbitrarily complicated machine-learning models including random forests and deep neural nets. Rather than trying to derive the correction from first principles for each machine-learning algorithm, we observe that there is typically a low-dimensional and easily modeled representation of the relationship between the observed and predicted outcomes. We build an approach for postprediction inference that naturally fits into the standard machine-learning framework where the data are divided into training, testing, and validation sets. We train the prediction model in the training set, estimate the relationship between the observed and predicted outcomes in the testing set, and use that relationship to correct subsequent inference in the validation set. We show our postprediction inference (postpi) approach can correct bias and improve variance estimation and subsequent statistical inference with predicted outcomes. To show the broad range of applicability of our approach, we show postpi can improve inference in two distinct fields: modeling predicted phenotypes in repurposed gene expression data and modeling predicted causes of death in verbal autopsy data. Our method is available through an open-source R package: https://github.com/leekgroup/postpi.