Discrete Conditional Phase-type Model Utilising a Multiclass Support Vector Machine for the Prediction of Retinopathy of Prematurity

Rebecca Rollins, Adele H. Marshall, Eibhlin McLoone, Sarah Chamney

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Retinopathy of prematurity (ROP) is a rare disease in which retinal blood vessels of premature infants fail to develop normally, and is one of the major causes of childhood blindness throughout the world. The Discrete Conditional Phase-type (DC-Ph) model consists of two components, the conditional component measuring the inter-relationships between covariates and the survival component which models the survival distribution using a Coxian phase-type distribution. This paper expands the DC-Ph models by introducing a support vector machine (SVM), in the role of the conditional component. The SVM is capable of classifying multiple outcomes and is used to identify the infant's risk of developing ROP. Class imbalance makes predicting rare events difficult. A new class decomposition technique, which deals with the problem of multiclass imbalance, is introduced. Based on the SVM classification, the length of stay in the neonatal ward is modelled using a 5, 8 or 9 phase Coxian distribution.
Original languageEnglish
Title of host publicationComputer-Based Medical Systems (CBMS), 2015 IEEE 28th International Symposium on
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages250-255
Number of pages6
DOIs
Publication statusPublished - Jun 2015
Event2015 IEEE 28th International Symposium on Computer-Based Medical Systems (CBMS) - São Carlos and Ribeirão Preto, Brazil
Duration: 22 Jun 201525 Jun 2015

Conference

Conference2015 IEEE 28th International Symposium on Computer-Based Medical Systems (CBMS)
CountryBrazil
CitySão Carlos and Ribeirão Preto
Period22/06/201525/06/2015

Fingerprint

Support vector machines
Blood vessels
Decomposition

Cite this

Rollins, R., Marshall, A. H., McLoone, E., & Chamney, S. (2015). Discrete Conditional Phase-type Model Utilising a Multiclass Support Vector Machine for the Prediction of Retinopathy of Prematurity. In Computer-Based Medical Systems (CBMS), 2015 IEEE 28th International Symposium on (pp. 250-255). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/CBMS.2015.78
Rollins, Rebecca ; Marshall, Adele H. ; McLoone, Eibhlin ; Chamney, Sarah. / Discrete Conditional Phase-type Model Utilising a Multiclass Support Vector Machine for the Prediction of Retinopathy of Prematurity. Computer-Based Medical Systems (CBMS), 2015 IEEE 28th International Symposium on. Institute of Electrical and Electronics Engineers (IEEE), 2015. pp. 250-255
@inproceedings{626e5fae54ce4e00bdd4bfb35d922318,
title = "Discrete Conditional Phase-type Model Utilising a Multiclass Support Vector Machine for the Prediction of Retinopathy of Prematurity",
abstract = "Retinopathy of prematurity (ROP) is a rare disease in which retinal blood vessels of premature infants fail to develop normally, and is one of the major causes of childhood blindness throughout the world. The Discrete Conditional Phase-type (DC-Ph) model consists of two components, the conditional component measuring the inter-relationships between covariates and the survival component which models the survival distribution using a Coxian phase-type distribution. This paper expands the DC-Ph models by introducing a support vector machine (SVM), in the role of the conditional component. The SVM is capable of classifying multiple outcomes and is used to identify the infant's risk of developing ROP. Class imbalance makes predicting rare events difficult. A new class decomposition technique, which deals with the problem of multiclass imbalance, is introduced. Based on the SVM classification, the length of stay in the neonatal ward is modelled using a 5, 8 or 9 phase Coxian distribution.",
author = "Rebecca Rollins and Marshall, {Adele H.} and Eibhlin McLoone and Sarah Chamney",
year = "2015",
month = "6",
doi = "10.1109/CBMS.2015.78",
language = "English",
pages = "250--255",
booktitle = "Computer-Based Medical Systems (CBMS), 2015 IEEE 28th International Symposium on",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

Rollins, R, Marshall, AH, McLoone, E & Chamney, S 2015, Discrete Conditional Phase-type Model Utilising a Multiclass Support Vector Machine for the Prediction of Retinopathy of Prematurity. in Computer-Based Medical Systems (CBMS), 2015 IEEE 28th International Symposium on. Institute of Electrical and Electronics Engineers (IEEE), pp. 250-255, 2015 IEEE 28th International Symposium on Computer-Based Medical Systems (CBMS), São Carlos and Ribeirão Preto, Brazil, 22/06/2015. https://doi.org/10.1109/CBMS.2015.78

Discrete Conditional Phase-type Model Utilising a Multiclass Support Vector Machine for the Prediction of Retinopathy of Prematurity. / Rollins, Rebecca; Marshall, Adele H.; McLoone, Eibhlin; Chamney, Sarah.

Computer-Based Medical Systems (CBMS), 2015 IEEE 28th International Symposium on. Institute of Electrical and Electronics Engineers (IEEE), 2015. p. 250-255.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Discrete Conditional Phase-type Model Utilising a Multiclass Support Vector Machine for the Prediction of Retinopathy of Prematurity

AU - Rollins, Rebecca

AU - Marshall, Adele H.

AU - McLoone, Eibhlin

AU - Chamney, Sarah

PY - 2015/6

Y1 - 2015/6

N2 - Retinopathy of prematurity (ROP) is a rare disease in which retinal blood vessels of premature infants fail to develop normally, and is one of the major causes of childhood blindness throughout the world. The Discrete Conditional Phase-type (DC-Ph) model consists of two components, the conditional component measuring the inter-relationships between covariates and the survival component which models the survival distribution using a Coxian phase-type distribution. This paper expands the DC-Ph models by introducing a support vector machine (SVM), in the role of the conditional component. The SVM is capable of classifying multiple outcomes and is used to identify the infant's risk of developing ROP. Class imbalance makes predicting rare events difficult. A new class decomposition technique, which deals with the problem of multiclass imbalance, is introduced. Based on the SVM classification, the length of stay in the neonatal ward is modelled using a 5, 8 or 9 phase Coxian distribution.

AB - Retinopathy of prematurity (ROP) is a rare disease in which retinal blood vessels of premature infants fail to develop normally, and is one of the major causes of childhood blindness throughout the world. The Discrete Conditional Phase-type (DC-Ph) model consists of two components, the conditional component measuring the inter-relationships between covariates and the survival component which models the survival distribution using a Coxian phase-type distribution. This paper expands the DC-Ph models by introducing a support vector machine (SVM), in the role of the conditional component. The SVM is capable of classifying multiple outcomes and is used to identify the infant's risk of developing ROP. Class imbalance makes predicting rare events difficult. A new class decomposition technique, which deals with the problem of multiclass imbalance, is introduced. Based on the SVM classification, the length of stay in the neonatal ward is modelled using a 5, 8 or 9 phase Coxian distribution.

U2 - 10.1109/CBMS.2015.78

DO - 10.1109/CBMS.2015.78

M3 - Conference contribution

SP - 250

EP - 255

BT - Computer-Based Medical Systems (CBMS), 2015 IEEE 28th International Symposium on

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

Rollins R, Marshall AH, McLoone E, Chamney S. Discrete Conditional Phase-type Model Utilising a Multiclass Support Vector Machine for the Prediction of Retinopathy of Prematurity. In Computer-Based Medical Systems (CBMS), 2015 IEEE 28th International Symposium on. Institute of Electrical and Electronics Engineers (IEEE). 2015. p. 250-255 https://doi.org/10.1109/CBMS.2015.78