Stabilizing high-dimensional prediction models using feature graphs
MetadataShow full item record
© 2014 IEEE. We investigate feature stability in the context of clinical prognosis derived from high-dimensional electronic medical records. To reduce variance in the selected features that are predictive, we introduce Laplacian-based regularization into a regression model. The Laplacian is derived on a feature graph that captures both the temporal and hierarchic relations between hospital events, diseases, and interventions. Using a cohort of patients with heart failure, we demonstrate better feature stability and goodness-of-fit through feature graph stabilization.
Showing items related by title, author, creator and subject.
Gopakumar, S.; Nguyen, T.; Tran, The Truyen; Phung, D.; Venkatesh, S. (2015)Stability in clinical prediction models is crucial for transferability between studies, yet has received little attention. The problem is paramount in high dimensional data, which invites sparse models with feature selection ...
Diagenesis of Neogene delta-front patch reefs: alteration of coastal, siliciclastic-influenced carbonates from humid equatorial regionsMadden, Robert; Wilson, Moyra (2012)This study offers insights into the diagenetic alteration of coastal carbonates that formed coevally with nearly continuous siliciclastic influx in a humid equatorial setting. A multi-disciplinary petrographic, ...
Tran, The Truyen; Phung, D.; Luo, W.; Venkatesh, S. (2014)The recent wide adoption of electronic medical records (EMRs) presents great opportunities and challenges for data mining. The EMR data are largely temporal, often noisy, irregular and high dimensional. This paper constructs ...