Multi-State Health Transition Modeling Using Neural Networks

ARC Centre of Excellence in Population Ageing Research Working Paper 2020/25

44 Pages Posted: 29 Oct 2020 Last revised: 20 Aug 2021

See all articles by Qiqi Wang

Qiqi Wang

Renmin University of China - School of Statistics

Katja Hanewald

UNSW Sydney - School of Risk & Actuarial Studies and ARC Centre of Excellence in Population Ageing Research (CEPAR)

Xiaojun Wang

Renmin University of China - School of Statistics

Date Written: September 16, 2020

Abstract

This article proposes a new model that combines a neural network with a generalized linear model (GLM) to estimate and predict health transition intensities. We introduce neural networks to health transition modeling to incorporate socioeconomic and lifestyle factors and to allow for linear and nonlinear relationships between these variables. We use transfer learning to link the models for different health transitions and improve the model estimation for health transitions with limited data. We apply the model to individual-level data from the Chinese Longitudinal Healthy Longevity Survey from 1998–2018. The results show that our model performs better in estimation and prediction than standalone GLM and neural network models. We provide new estimates of the life expectancies for a range of population subgroups. We also describe a wide range of possible applications for further health-related research, including risk prediction using health claim data and mortality prediction based on individual-level mortality data.

Keywords: Neural networks, Transfer learning, Multi-state health transitions

JEL Classification: C13, C53, G22, J11

Suggested Citation

Wang, Qiqi and Hanewald, Katja and Wang, Xiaojun, Multi-State Health Transition Modeling Using Neural Networks (September 16, 2020). ARC Centre of Excellence in Population Ageing Research Working Paper 2020/25, Available at SSRN: https://ssrn.com/abstract=3699161 or http://dx.doi.org/10.2139/ssrn.3699161

Qiqi Wang

Renmin University of China - School of Statistics ( email )

No.59 Zhongguancun Street, Renmin University
Beijing, 100872
China

Katja Hanewald (Contact Author)

UNSW Sydney - School of Risk & Actuarial Studies and ARC Centre of Excellence in Population Ageing Research (CEPAR) ( email )

School of Risk & Actuarial Studies
UNSW Sydney
Sydney, New South Wales NSW 2052
Australia

Xiaojun Wang

Renmin University of China - School of Statistics ( email )

No.59 Zhongguancun Street, Renmin University
Beijing, 100872
China

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
70
Abstract Views
456
Rank
541,457
PlumX Metrics