Volume 47 - Article 8 | Pages 199–232  

Leveraging deep neural networks to estimate age-specific mortality from life expectancy at birth

By Andrea Nigri, Susanna Levantesi, José Manuel Aburto

Abstract

Background: Life expectancy is one of the most informative indicators of population health and development. Its stability, which has been observed over time, has made the prediction and forecasting of life expectancy an appealing area of study. However, predicted or estimated values of life expectancy do not tell us about age-specific mortality.

Objective: Reliable estimates of age-specific mortality are essential in the study of health inequalities, well-being and to calculate other demographic indicators. This task comes with several difficulties, including a lack of reliable data in many populations. Models that relate levels of life expectancy to a full age-specific mortality profile are therefore important but scarce.

Methods: We propose a deep neural networks (DNN) model to derive age-specific mortality from observed or predicted life expectancy by leveraging deep-learning algorithms akin to demography’s indirect estimation techniques.

Results: Out-of-sample validation was used to validate the model, and the predictive performance of the DNN model was compared with two state-of-the-art models. The DNN model provides reliable estimates of age-specific mortality for the United States, Italy, Japan, and Russia using data from the Human Mortality Database.

Contribution: We show how the DNN model could be used to estimate age-specific mortality for countries without age-specific data using neighbouring information or populations with similar mortality dynamics. We take a step forward among demographic methods, offering a multi-population indirect estimation based on a data driven-approach, that can be fitted to many populations simultaneously, using DNN optimisation approaches.

Author’s Affiliation

• Andrea Nigri - Università degli studi di Foggia, Italy EMAIL
• Susanna Levantesi - Università degli Studi di Roma La Sapienza, Italy EMAIL
• José Manuel Aburto - London School of Hygiene and Tropical Medicine, United Kingdom EMAIL

Other articles by the same author/authors in Demographic Research

The Average Uneven Mortality index: Building on the ‘e-dagger’ measure of lifespan inequality
Volume 50 - Article 44

How lifespan and life years lost equate to unity
Volume 50 - Article 24

Subnational contribution to life expectancy and life span variation changes: Evidence from the United States
Volume 50 - Article 22

Dynamics of the coefficient of variation of the age at death distribution
Volume 49 - Article 38

Divergent trends in lifespan variation during mortality crises
Volume 46 - Article 11

Mexican mortality 1990‒2016: Comparison of unadjusted and adjusted estimates
Volume 44 - Article 30

Lexis fields
Volume 42 - Article 24

Geofaceting: Aligning small-multiples for regions in a spatially meaningful way
Volume 41 - Article 17

The threshold age of the lifetable entropy
Volume 41 - Article 4

Most recent similar articles in Demographic Research

Feminicide as a determinant of Mexican female life expectancy in the 21st century
Volume 53 - Article 24    | Keywords: female life expectancy, feminicide, life expectancy, Mexico, mortality, violence, women

Modifying model life tables to derive mortality curves for countries with excess mortality
Volume 53 - Article 2    | Keywords: armed conflict, Colombia, homicide, life expectancy, probability of dying, road traffic accidents, violence, war

Life expectancy by religious affiliation in Finland 1972–2020
Volume 52 - Article 17    | Keywords: Finland, life expectancy, register data, religious affiliation

The impact of the COVID-19 pandemic on mortality in Uruguay from 2020 to 2022
Volume 51 - Article 29    | Keywords: COVID-19, excess mortality, life expectancy, Uruguay

On the relationship between life expectancy, modal age at death, and the threshold age of the life table entropy
Volume 51 - Article 24    | Keywords: Gompertz law, life expectancy, lifespan variation, longevity, mode, mortality