Figure 4From: Time series analysis as input for clinical predictive modeling: Modeling cardiac arrest in a pediatric ICUData classes. Latent variables were derived from the raw physiologic Multivariable and Time Series data sets. Clinical Latent Variables were based on calculations used in clinical medicine in assessing for shock. Trend Analysis Latent Variables were based on slopes, intercepts, means, and the ratios of these features for 5, 10, 15, and 60 minute windows that preceded the arrest event.Back to article page