Leveraging deep neural networks to estimate age-specific mortality from life expectancy at birth
<b>Background</b>: 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 andforecasting of life expectancy an appealing area of study. However, predicted or estimatedvalues...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Max Planck Institute for Demographic Research
2022-07-01
|
Series: | Demographic Research |
Subjects: | |
Online Access: | https://www.demographic-research.org/articles/volume/47/8 |
_version_ | 1797739409957715968 |
---|---|
author | Andrea Nigri Susanna Levantesi Jose Manuel Aburto |
author_facet | Andrea Nigri Susanna Levantesi Jose Manuel Aburto |
author_sort | Andrea Nigri |
collection | DOAJ |
description | <b>Background</b>: 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 andforecasting of life expectancy an appealing area of study. However, predicted or estimatedvalues of life expectancy do not tell us about age-specific mortality. <b>Objective</b>: 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. <b>Methods</b>: We propose a deep neural networks (DNN) model to derive age-specific mortality fromobserved or predicted life expectancy by leveraging deep-learning algorithms akin to demography's indirect estimation techniques. <b>Results</b>: Out-of-sample validation was used to validate the model, and the predictive performanceof 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. <b>Contribution</b>: 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. |
first_indexed | 2024-03-12T13:57:48Z |
format | Article |
id | doaj.art-6cec58d7db744610b6452556e1dc83cc |
institution | Directory Open Access Journal |
issn | 1435-9871 |
language | English |
last_indexed | 2024-03-12T13:57:48Z |
publishDate | 2022-07-01 |
publisher | Max Planck Institute for Demographic Research |
record_format | Article |
series | Demographic Research |
spelling | doaj.art-6cec58d7db744610b6452556e1dc83cc2023-08-22T11:19:16ZengMax Planck Institute for Demographic ResearchDemographic Research1435-98712022-07-0147810.4054/DemRes.2022.47.85772Leveraging deep neural networks to estimate age-specific mortality from life expectancy at birthAndrea Nigri0Susanna Levantesi1Jose Manuel Aburto2Università degli studi di FoggiaUniversità degli Studi di Roma La SapienzaLondon School of Hygiene and Tropical Medicine<b>Background</b>: 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 andforecasting of life expectancy an appealing area of study. However, predicted or estimatedvalues of life expectancy do not tell us about age-specific mortality. <b>Objective</b>: 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. <b>Methods</b>: We propose a deep neural networks (DNN) model to derive age-specific mortality fromobserved or predicted life expectancy by leveraging deep-learning algorithms akin to demography's indirect estimation techniques. <b>Results</b>: Out-of-sample validation was used to validate the model, and the predictive performanceof 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. <b>Contribution</b>: 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.https://www.demographic-research.org/articles/volume/47/8death ratesdeep neural networkforecastinglife expectancy |
spellingShingle | Andrea Nigri Susanna Levantesi Jose Manuel Aburto Leveraging deep neural networks to estimate age-specific mortality from life expectancy at birth Demographic Research death rates deep neural network forecasting life expectancy |
title | Leveraging deep neural networks to estimate age-specific mortality from life expectancy at birth |
title_full | Leveraging deep neural networks to estimate age-specific mortality from life expectancy at birth |
title_fullStr | Leveraging deep neural networks to estimate age-specific mortality from life expectancy at birth |
title_full_unstemmed | Leveraging deep neural networks to estimate age-specific mortality from life expectancy at birth |
title_short | Leveraging deep neural networks to estimate age-specific mortality from life expectancy at birth |
title_sort | leveraging deep neural networks to estimate age specific mortality from life expectancy at birth |
topic | death rates deep neural network forecasting life expectancy |
url | https://www.demographic-research.org/articles/volume/47/8 |
work_keys_str_mv | AT andreanigri leveragingdeepneuralnetworkstoestimateagespecificmortalityfromlifeexpectancyatbirth AT susannalevantesi leveragingdeepneuralnetworkstoestimateagespecificmortalityfromlifeexpectancyatbirth AT josemanuelaburto leveragingdeepneuralnetworkstoestimateagespecificmortalityfromlifeexpectancyatbirth |