Olier-Caparroso, I, Sansom, A, Lisboa, P and Ortega-Martorell, S (2021) Using MLP partial responses to explain in-hospital mortality in ICU. In: 2020 International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI) . (2020 International Conference on Data Analytics for Business and Industry, 26 October 2020 - 27 October 2020, Sakheer, Bahrain).

Preview

Text Using MLP partial responses to explain in-hospital mortality in ICU.pdf - Accepted Version Download (420kB) | Preview

Abstract

In this paper we propose to use partial responses derived from an initial multilayer perceptron (MLP) to build an explanatory risk prediction model of in-hospital mortality in intensive care units (ICU). Traditionally, MLPs deliver higher performance than linear models such as multivariate logistic regression (MLR). However, MLPs interlink input variables in such a complex way that is not straightforward to explain how the outcome is influenced by inputs and/or input interactions. In this paper, we hypothesized that in some scenarios, such as when the data noise is significant or when the data is just marginally non-linear, we could find slightly more complex associations by obtaining MLP partial responses. That is, by letting change one variable at the time, while keeping constant the rest. Overall, we found that, although the MLR and MLP in-hospital mortality model performances were equivalent, the MLP could explain non-linear associations that otherwise the MLR had considered non-significant. We considered that, although deeming higher-other interactions as disposable noise could be a strong assumption, building explanatory models based on the MLP partial responses could still be more informative than on MLR.

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software R Medicine > RA Public aspects of medicine
Divisions:	Computer Science & Mathematics
Publisher:	IEEE
Date Deposited:	29 Jan 2021 11:52
Last Modified:	13 Apr 2022 15:18
DOI or ID number:	10.1109/ICDABI51230.2020.9325691
URI:	https://researchonline.ljmu.ac.uk/id/eprint/14346

View Item