Joint Models for Cause-of-Death Mortality in Multiple Populations

TL;DR

This paper introduces a novel multi-output Gaussian process approach to jointly model cause-specific mortality rates across multiple countries and genders, enabling better smoothing, extrapolation, and understanding of mortality trends.

Contribution

The paper develops a scalable, multi-level MOGP model with Kronecker kernels tailored for mortality data, capturing heterogeneity and dependencies across causes, countries, and genders.

Findings

Models effectively smooth and extrapolate cause-specific mortality rates.

Case studies reveal shared mortality trends across countries and causes.

Data fusion enhances understanding of cause-specific mortality dynamics.

Abstract

We investigate jointly modeling Age-specific rates of various causes of death in a multinational setting. We apply Multi-Output Gaussian Processes (MOGP), a spatial machine learning method, to smooth and extrapolate multiple cause-of-death mortality rates across several countries and both genders. To maintain flexibility and scalability, we investigate MOGPs with Kronecker-structured kernels and latent factors. In particular, we develop a custom multi-level MOGP that leverages the gridded structure of mortality tables to efficiently capture heterogeneity and dependence across different factor inputs. Results are illustrated with datasets from the Human Cause-of-Death Database (HCD). We discuss a case study involving cancer variations in three European nations, and a US-based study that considers eight top-level causes and includes comparison to all-cause analysis. Our models provide insights into the commonality of cause-specific mortality trends and demonstrate the opportunities for respective data fusion.