Predicting loneliness in older age using two measures of loneliness

ABSTRACT

Older people are especially vulnerable to loneliness and this has become a major public health concern for people in later life. In this paper, we propose a machine learning based approach to predict loneliness probability using two gradient boosting algorithms, XGBoost and LightGBM. The predictive models are built using data from a large nationally representative sample from, the English Longitudinal Study of Ageing (ELSA) that had seven successive waves (2002–2015). Two measures of loneliness were applied to investigate the impact of different measure strategies on the prediction of loneliness. The models achieved good performance with a high Area Under Curve (AUC) and a low Logarithmic Loss (LogLoss) on the test data, i.e. AUC (0.88) and LogLoss (0.24) using the single-item direct measure of loneliness, and AUC (0.84) and LogLoss (0.31) using the multi-item indirect measure of loneliness. A wide range of variables were investigated to identify significant risk factors associated with loneliness. Specific categories associated with important variables were also recognized by the models. Such information will further enhance our understanding and knowledge of the causes of loneliness in elderly people.

KEYWORDS:

• Loneliness
• measure of loneliness
• older age
• ELSA data
• predictive model
• gradient tree boosting

SUBJECT CLASSIFICATION CODES:

• Applied computing
• health care information systems

Acknowledgement

We would firstly like to thank the team of researchers based at University College London, the Institute of Fiscal Studies and the National Centre for Social Research for providing the English Longitudinal Study of Ageing (ELSA) data for free download. Moreover, we also wish to acknowledge the insightful comments and suggestions received from the anonymous reviewers which helped to improve this paper.

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes

1 https://www.elsa-project.ac.uk.

2 https://www.kaggle.com.

Additional information

Notes on contributors

Hui Yang

Hui Yang, PhD, is currently working as a Research Fellow in the Information School, University of Sheffield, UK. Her area of interest includes health informatics, bioinformatics, business intelligence, and social media.

Peter A. Bath

Peter A. Bath, PhD, is the Professor of Health Informatics in the Information School, University of Sheffield, UK. His research interests include analyzing health data using statistical methods and data mining techniques, the evaluation of health information systems and the use of digital information in health care of older people.