- Title
- An actuarial investigation into maternal hospital cost risk factors for public patients
- Creator
- William, Jananie; Martin, Michael A.; Chojenta, Catherine; Loxton, Deborah
- Relation
- Annals of Actuarial Science Vol. 12, Issue 1, p. 106-129
- Publisher Link
- http://dx.doi.org/10.1017/S174849951700015X
- Publisher
- Cambridge University Press
- Resource Type
- journal article
- Date
- 2018
- Description
- We investigate an actuarial approach to identifying the factors impacting government-funded maternal hospital costs in Australia, with a focus on women who experience adverse birth outcomes. We propose a two-phase modelling methodology that adopts actuarial methods from typical insurance claim cost modelling and extends to other statistical techniques to account for the large volume of covariates available for modelling. Specifically, Classification and Regression Trees and generalised linear mixed models are employed to analyse a data set that links longitudinal survey and administrative data from a large sample of women. The results show that adverse births are a statistically significant risk factor affecting maternal hospital costs in the antenatal and delivery periods. Other significant cost risk factors in the delivery period include mode of delivery, private health insurance status, diabetes, smoking status, area of residence and onset of labour. We demonstrate the efficacy of using actuarial techniques in non-traditional areas and highlight how the results can be used to inform public policy.
- Subject
- generalised linear mixed model; Classification and Regression Tree; maternal hospital costs; public health costs; adverse birth outcome
- Identifier
- http://hdl.handle.net/1959.13/1405036
- Identifier
- uon:35428
- Identifier
- ISSN:1748-4995
- Rights
- This article has been published in a revised form in the Annals of Actuarial Science http://dx.doi.org/10.1017/S174849951700015X. This version is published under a Creative Commons CC-BY-NC-ND. No commercial re-distribution or re-use allowed. Derivative works cannot be distributed. © Cambridge University Press.
- Language
- eng
- Full Text
- Reviewed
- Hits: 3028
- Visitors: 2617
- Downloads: 334
Thumbnail | File | Description | Size | Format | |||
---|---|---|---|---|---|---|---|
View Details Download | ATTACHMENT02 | Author final version | 650 KB | Adobe Acrobat PDF | View Details Download |