Fig_1.tif (4.19 MB)
Download fileMortality prediction performance of death counting among similar patients.
figure
posted on 2015-05-15, 04:16 authored by Joon Lee, David M. Maslove, Joel A. DubinThe solid and dashed lines are the mean and 95% confidence intervals, respectively, from 10-fold cross-validation. A trade-off between training data homogeneity and size is apparent; as the number of similar patients in the training data increases, predictive performance improves initially at a rapid rate thanks to increasing training data size but starts to degrade gradually due to decreasing homogeneity within the training data. AUROC: area under the receiver operating characteristic curve; AUPRC: area under the precision-recall curve.
History
Usage metrics
Read the peer-reviewed publication
Categories
Keywords
illness scoressample sizesBig Data technologiestraining data sizeperformance degradesoutcome prediction performancedata analyticsdecision supportcare unitpsmPersonalized Mortality PredictionEMR dataElectronic Medical Dataindex patientproduct recommendationICU severitytraining dataprediction performancePatient Similarity Metric BackgroundClinical outcome prediction