Using elastic nets to estimate frailty burden from routinely collected national aged care data

Research output: Contribution to journalArticle

Abstract

OBJECTIVES: To (1) use an elastic net (EN) algorithm to derive a frailty measure from a national aged care eligibility assessment program; (2) compare the ability of EN-based and a traditional cumulative deficit (CD) based frailty measures to predict mortality and entry into permanent residential care; (3) assess if the predictive ability can be improved by using weighted frailty measures.

MATERIALS AND METHODS: A Cox proportional hazard model based EN algorithm was applied to the 2003-2013 cohort of 903 996 participants for selecting items to enter an EN based frailty measure. The out-of-sample predictive accuracy was measured by the area under the curve (AUC) from Cox models fitted to 80% training and validated on 20% testing samples.

RESULTS: The EN approach resulted in a 178-item frailty measure including items excluded from the 44-item CD-based measure. The EN based measure was not statistically significantly different from the CD-based approach in terms of predicting mortality (AUC 0.641, 95% CI: 0.637-0.644 vs AUC 0.637, 95% CI: 0.634-0.641) and permanent care entry (AUC 0.626, 95% CI: 0.624-0.629 vs AUC 0.627, 95% CI: 0.625-0.63). However, the weighted EN based measure statistically outperforms the weighted CD measure for predicting mortality (AUC 0.774, 95% CI: 0.771-0.777 vs AUC 0.757, 95% CI: 0.754-0.760) and permanent care entry (AUC 0.676, 95% CI: 0.673-0.678 vs AUC 0.671, 95% CI: 0.668-0.674).

CONCLUSIONS: The weighted EN and CD-based measures demonstrated similar prediction performance. The CD-based measure items are relevant to frailty measurement and easier to interpret. We recommend using the weighted and unweighted CD-based frailty measures.

LanguageEnglish
JournalJournal of the American Medical Informatics Association
DOIs
Publication statusPublished - 17 Jan 2020

Cite this

@article{9c53f7c54a63416095437e304fe67661,
title = "Using elastic nets to estimate frailty burden from routinely collected national aged care data",
abstract = "OBJECTIVES: To (1) use an elastic net (EN) algorithm to derive a frailty measure from a national aged care eligibility assessment program; (2) compare the ability of EN-based and a traditional cumulative deficit (CD) based frailty measures to predict mortality and entry into permanent residential care; (3) assess if the predictive ability can be improved by using weighted frailty measures.MATERIALS AND METHODS: A Cox proportional hazard model based EN algorithm was applied to the 2003-2013 cohort of 903 996 participants for selecting items to enter an EN based frailty measure. The out-of-sample predictive accuracy was measured by the area under the curve (AUC) from Cox models fitted to 80{\%} training and validated on 20{\%} testing samples.RESULTS: The EN approach resulted in a 178-item frailty measure including items excluded from the 44-item CD-based measure. The EN based measure was not statistically significantly different from the CD-based approach in terms of predicting mortality (AUC 0.641, 95{\%} CI: 0.637-0.644 vs AUC 0.637, 95{\%} CI: 0.634-0.641) and permanent care entry (AUC 0.626, 95{\%} CI: 0.624-0.629 vs AUC 0.627, 95{\%} CI: 0.625-0.63). However, the weighted EN based measure statistically outperforms the weighted CD measure for predicting mortality (AUC 0.774, 95{\%} CI: 0.771-0.777 vs AUC 0.757, 95{\%} CI: 0.754-0.760) and permanent care entry (AUC 0.676, 95{\%} CI: 0.673-0.678 vs AUC 0.671, 95{\%} CI: 0.668-0.674).CONCLUSIONS: The weighted EN and CD-based measures demonstrated similar prediction performance. The CD-based measure items are relevant to frailty measurement and easier to interpret. We recommend using the weighted and unweighted CD-based frailty measures.",
author = "Max Moldovan and Jyoti Khadka and Renuka Visvanathan and Steve Wesselingh and Inacio, {Maria C}",
note = "{\circledC} The Author(s) 2020. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.",
year = "2020",
month = "1",
day = "17",
doi = "10.1093/jamia/ocz210",
language = "English",
journal = "Journal of the American Medical Informatics Association",
issn = "1067-5027",
publisher = "Oxford University Press",

}

TY - JOUR

T1 - Using elastic nets to estimate frailty burden from routinely collected national aged care data

AU - Moldovan, Max

AU - Khadka, Jyoti

AU - Visvanathan, Renuka

AU - Wesselingh, Steve

AU - Inacio, Maria C

N1 - © The Author(s) 2020. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.

PY - 2020/1/17

Y1 - 2020/1/17

N2 - OBJECTIVES: To (1) use an elastic net (EN) algorithm to derive a frailty measure from a national aged care eligibility assessment program; (2) compare the ability of EN-based and a traditional cumulative deficit (CD) based frailty measures to predict mortality and entry into permanent residential care; (3) assess if the predictive ability can be improved by using weighted frailty measures.MATERIALS AND METHODS: A Cox proportional hazard model based EN algorithm was applied to the 2003-2013 cohort of 903 996 participants for selecting items to enter an EN based frailty measure. The out-of-sample predictive accuracy was measured by the area under the curve (AUC) from Cox models fitted to 80% training and validated on 20% testing samples.RESULTS: The EN approach resulted in a 178-item frailty measure including items excluded from the 44-item CD-based measure. The EN based measure was not statistically significantly different from the CD-based approach in terms of predicting mortality (AUC 0.641, 95% CI: 0.637-0.644 vs AUC 0.637, 95% CI: 0.634-0.641) and permanent care entry (AUC 0.626, 95% CI: 0.624-0.629 vs AUC 0.627, 95% CI: 0.625-0.63). However, the weighted EN based measure statistically outperforms the weighted CD measure for predicting mortality (AUC 0.774, 95% CI: 0.771-0.777 vs AUC 0.757, 95% CI: 0.754-0.760) and permanent care entry (AUC 0.676, 95% CI: 0.673-0.678 vs AUC 0.671, 95% CI: 0.668-0.674).CONCLUSIONS: The weighted EN and CD-based measures demonstrated similar prediction performance. The CD-based measure items are relevant to frailty measurement and easier to interpret. We recommend using the weighted and unweighted CD-based frailty measures.

AB - OBJECTIVES: To (1) use an elastic net (EN) algorithm to derive a frailty measure from a national aged care eligibility assessment program; (2) compare the ability of EN-based and a traditional cumulative deficit (CD) based frailty measures to predict mortality and entry into permanent residential care; (3) assess if the predictive ability can be improved by using weighted frailty measures.MATERIALS AND METHODS: A Cox proportional hazard model based EN algorithm was applied to the 2003-2013 cohort of 903 996 participants for selecting items to enter an EN based frailty measure. The out-of-sample predictive accuracy was measured by the area under the curve (AUC) from Cox models fitted to 80% training and validated on 20% testing samples.RESULTS: The EN approach resulted in a 178-item frailty measure including items excluded from the 44-item CD-based measure. The EN based measure was not statistically significantly different from the CD-based approach in terms of predicting mortality (AUC 0.641, 95% CI: 0.637-0.644 vs AUC 0.637, 95% CI: 0.634-0.641) and permanent care entry (AUC 0.626, 95% CI: 0.624-0.629 vs AUC 0.627, 95% CI: 0.625-0.63). However, the weighted EN based measure statistically outperforms the weighted CD measure for predicting mortality (AUC 0.774, 95% CI: 0.771-0.777 vs AUC 0.757, 95% CI: 0.754-0.760) and permanent care entry (AUC 0.676, 95% CI: 0.673-0.678 vs AUC 0.671, 95% CI: 0.668-0.674).CONCLUSIONS: The weighted EN and CD-based measures demonstrated similar prediction performance. The CD-based measure items are relevant to frailty measurement and easier to interpret. We recommend using the weighted and unweighted CD-based frailty measures.

U2 - 10.1093/jamia/ocz210

DO - 10.1093/jamia/ocz210

M3 - Article

JO - Journal of the American Medical Informatics Association

T2 - Journal of the American Medical Informatics Association

JF - Journal of the American Medical Informatics Association

SN - 1067-5027

ER -