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.
|Number of pages||10|
|Journal||Journal of the American Medical Informatics Association : JAMIA|
|Early online date||17 Jan 2020|
|Publication status||Published - Mar 2020|
- penalized regression
- statistical learning