The University of Southampton
University of Southampton Institutional Repository
Warning ePrints Soton is experiencing an issue with some file downloads not being available. We are working hard to fix this. Please bear with us.

CRP (C-reactive protein) in outcome prediction after subarachnoid haemorrhage and the role of machine learning

CRP (C-reactive protein) in outcome prediction after subarachnoid haemorrhage and the role of machine learning
CRP (C-reactive protein) in outcome prediction after subarachnoid haemorrhage and the role of machine learning
Background and purpose: outcome prediction after aneurysmal subarachnoid haemorrhage (aSAH) is challenging. C-reactive protein (CRP) has been reported to be associated with outcome, but it is unclear if this is independent of other predictors and applies to aSAH of all grades. Therefore, the role of CRP in aSAH outcome prediction models is unknown. The purpose of this study is to assess if CRP is an independent predictor of outcome after aSAH, develop new prognostic models incorporating CRP, and test whether these can be improved by application of machine learning. 
Methods: this was an individual patient level analysis of data from patients within 72 hours of aSAH from two prior studies. A panel of statistical learning methods including logistic regression, random forest and support vector machines (SVM) were used to assess the relationship between CRP and modified Rankin Score (mRS). Models were compared to the full SAHIT prediction tool of outcome after aSAH and internally validated using cross-validation.
Results: 1017 patients were included for analysis. CRP on the first day after ictus was an independent predictor of outcome. The full SAHIT model achieved an AUC of 0.831. Addition of CRP to the predictors of the full SAHIT model improved model performance (AUC = 0.846, p = 0.01). This improvement was not enhanced when learning was performed using a random forest (AUC = 0.807), but was with an SVM (AUC of 0.960, p <0.001). 
Conclusions: CRP is an independent predictor of outcome after aSAH. Its inclusion in prognostic models improves performance, although the magnitude of improvement is probably insufficient to be relevant clinically on an individual patient level, and of more relevance in research. Greater improvements in model performance are seen with SVMs but these models have the highest classification error rate on internal validation and require external validation and calibration.
0039-2499
Gaastra, Ben
c6a69fe5-84a6-4a41-990c-8999afb00822
Barron, Peter
2b425830-13ac-45fa-b6cf-28975c20b6ad
Newitt, Laura
698a6e22-a733-4523-8e91-7a9295a9054c
Chhugani, Simran
c97445a2-cd47-4364-9e8b-239626c05e85
Turner, Carole
8e4e5fa4-c97b-4f00-9c65-27119cc5945e
Kirkpatrick, Peter
9ae3c516-4485-49c3-8930-9cc837986311
MacArthur, Ben
4fa2fa9d-b8e5-48b3-b98d-930e1c7f7fff
Galea, Ian
66209a2f-f7e6-4d63-afe4-e9299f156f0b
Bulters, Diederik
f2080cef-122a-486d-925d-455316b8cd41
Gaastra, Ben
c6a69fe5-84a6-4a41-990c-8999afb00822
Barron, Peter
2b425830-13ac-45fa-b6cf-28975c20b6ad
Newitt, Laura
698a6e22-a733-4523-8e91-7a9295a9054c
Chhugani, Simran
c97445a2-cd47-4364-9e8b-239626c05e85
Turner, Carole
8e4e5fa4-c97b-4f00-9c65-27119cc5945e
Kirkpatrick, Peter
9ae3c516-4485-49c3-8930-9cc837986311
MacArthur, Ben
4fa2fa9d-b8e5-48b3-b98d-930e1c7f7fff
Galea, Ian
66209a2f-f7e6-4d63-afe4-e9299f156f0b
Bulters, Diederik
f2080cef-122a-486d-925d-455316b8cd41

Gaastra, Ben, Barron, Peter, Newitt, Laura, Chhugani, Simran, Turner, Carole, Kirkpatrick, Peter, MacArthur, Ben, Galea, Ian and Bulters, Diederik (2021) CRP (C-reactive protein) in outcome prediction after subarachnoid haemorrhage and the role of machine learning. Stroke, 52 (10). (doi:10.1161/STROKEAHA.120.030950).

Record type: Article

Abstract

Background and purpose: outcome prediction after aneurysmal subarachnoid haemorrhage (aSAH) is challenging. C-reactive protein (CRP) has been reported to be associated with outcome, but it is unclear if this is independent of other predictors and applies to aSAH of all grades. Therefore, the role of CRP in aSAH outcome prediction models is unknown. The purpose of this study is to assess if CRP is an independent predictor of outcome after aSAH, develop new prognostic models incorporating CRP, and test whether these can be improved by application of machine learning. 
Methods: this was an individual patient level analysis of data from patients within 72 hours of aSAH from two prior studies. A panel of statistical learning methods including logistic regression, random forest and support vector machines (SVM) were used to assess the relationship between CRP and modified Rankin Score (mRS). Models were compared to the full SAHIT prediction tool of outcome after aSAH and internally validated using cross-validation.
Results: 1017 patients were included for analysis. CRP on the first day after ictus was an independent predictor of outcome. The full SAHIT model achieved an AUC of 0.831. Addition of CRP to the predictors of the full SAHIT model improved model performance (AUC = 0.846, p = 0.01). This improvement was not enhanced when learning was performed using a random forest (AUC = 0.807), but was with an SVM (AUC of 0.960, p <0.001). 
Conclusions: CRP is an independent predictor of outcome after aSAH. Its inclusion in prognostic models improves performance, although the magnitude of improvement is probably insufficient to be relevant clinically on an individual patient level, and of more relevance in research. Greater improvements in model performance are seen with SVMs but these models have the highest classification error rate on internal validation and require external validation and calibration.

Text
Gaastra et al Stroke 2021 inc supp - Accepted Manuscript
Restricted to Repository staff only until 9 January 2022.
Available under License Creative Commons Attribution.
Request a copy

More information

Accepted/In Press date: 31 March 2021
e-pub ahead of print date: 9 July 2021
Published date: 1 October 2021

Identifiers

Local EPrints ID: 449430
URI: http://eprints.soton.ac.uk/id/eprint/449430
ISSN: 0039-2499
PURE UUID: 226624a9-892e-48e6-b318-bfb271d0ce23
ORCID for Ian Galea: ORCID iD orcid.org/0000-0002-1268-5102

Catalogue record

Date deposited: 28 May 2021 16:31
Last modified: 01 Oct 2021 01:39

Export record

Altmetrics

Contributors

Author: Ben Gaastra
Author: Peter Barron
Author: Laura Newitt
Author: Simran Chhugani
Author: Carole Turner
Author: Peter Kirkpatrick
Author: Ben MacArthur
Author: Ian Galea ORCID iD
Author: Diederik Bulters

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×