Figure 5

Data subsets obtained by combining data classes. Five candidate modeling subsets of data were created to determine the impact of time series and trend analysis latent features (separately) to baseline multivariable model accuracy. Clinical latent variables were compared to multivariable + time series features to determine their relative impact to model accuracy. Finally, all candidate features were combined to determine the net impact of time series + clinical latent + time series latent features on model accuracy.