Forecasting Mortality in the Middle-Aged and Older Population of England: A 1D-CNN Approach

TL;DR

This paper demonstrates that 1D convolutional neural networks can effectively forecast mortality in the English aging population using longitudinal data, with improvements from oversampling and the swish activation function.

Contribution

It introduces a novel application of 1D-CNNs to longitudinal mortality data and explores techniques to handle class imbalance and optimize activation functions.

Findings

Oversampling improves model performance on imbalanced data.

Swish activation function outperforms others in mortality forecasting.

1D-CNNs effectively model longitudinal health data for mortality prediction.

Abstract

Convolutional Neural Networks (CNNs) are proven to be effective when data are homogeneous such as images, or when there is a relationship between consecutive data such as time series data. Although CNNs are not famous for tabular data, we show that we can use them in longitudinal data, where individuals' information is recorded over a period and therefore there is a relationship between them. This study considers the English Longitudinal Study of Ageing (ELSA) survey, conducted every two years. We use one-dimensional convolutional neural networks (1D-CNNs) to forecast mortality using socio-demographics, diseases, mobility impairment, Activities of Daily Living (ADLs), Instrumental Activities of Daily Living (IADLs), and lifestyle factors. As our dataset is highly imbalanced, we try different over and undersampling methods and find that over-representing the small class improves the results. We also try our model with different activation functions. Our results show that swish nonlinearity outperforms other functions.