Mortality Risk Score Prediction in an Elderly Population Using Machine Learning
Open Access
- 29 January 2013
- journal article
- research article
- Published by Oxford University Press (OUP) in American Journal of Epidemiology
- Vol. 177 (5), 443-452
- https://doi.org/10.1093/aje/kws241
Abstract
Standard practice for prediction often relies on parametric regression methods. Interesting new methods from the machine learning literature have been introduced in epidemiologic studies, such as random forest and neural networks. However, a priori, an investigator will not know which algorithm to select and may wish to try several. Here I apply the super learner, an ensembling machine learning approach that combines multiple algorithms into a single algorithm and returns a prediction function with the best cross-validated mean squared error. Super learning is a generalization of stacking methods. I used super learning in the Study of Physical Performance and Age-Related Changes in Sonomans (SPPARCS) to predict death among 2,066 residents of Sonoma, California, aged 54 years or more during the period 1993–1999. The super learner for predicting death (risk score) improved upon all single algorithms in the collection of algorithms, although its performance was similar to that of several algorithms. Super learner outperformed the worst algorithm (neural networks) by 44% with respect to estimated cross-validated mean squared error and had an R2 value of 0.201. The improvement of super learner over random forest with respect to R2 was approximately 2-fold. Alternatives for risk score prediction include the super learner, which can provide improved performance.Keywords
This publication has 60 references indexed in Scilit:
- The iScore Predicts Poor Functional Outcomes Early After Hospitalization for an Acute Ischemic StrokeStroke, 2011
- Implementation of G-Computation on a Simulated Data Set: Demonstration of a Causal Inference TechniqueAmerican Journal of Epidemiology, 2011
- The Advanced Dementia Prognostic Tool: A Risk Score to Estimate Survival in Nursing Home Residents with Advanced DementiaJournal of Pain and Symptom Management, 2010
- Using variable importance measures from causal inference to rank risk factors of schistosomiasis infection in a rural setting in ChinaEpidemiologic Perspectives & Innovations, 2010
- Performance of Common Genetic Variants in Breast-Cancer Risk ModelsThe New England Journal of Medicine, 2010
- Discriminatory Accuracy From Single-Nucleotide Polymorphisms in Models to Predict Breast Cancer RiskJNCI Journal of the National Cancer Institute, 2008
- Personality Predictors of Longevity: Activity, Emotional Stability, and ConscientiousnessPsychosomatic Medicine, 2008
- A breast cancer prediction model incorporating familial and personal risk factorsStatistics in Medicine, 2004
- Compendium of Physical Activities: classification of energy costs of human physical activitiesMedicine & Science in Sports & Exercise, 1993
- Projecting Individualized Probabilities of Developing Breast Cancer for White Females Who Are Being Examined AnnuallyJNCI Journal of the National Cancer Institute, 1989