The focus of the PhysioNet/CinC Challenge 2012 is to develop methods for patient-specific prediction of in-hospital mortality. Participants will use information collected during the first two days of an ICU stay to predict which patients survive their hospitalizations, and which patients do not.
To predict per patient:
- In-hospital mortality (1: will die, 0: will not die) - Classification
- Length of Stay (LoS) (# days in hospital) - Regression
- Raw Data
- Viz Data - Data prepared for exploratory analysis by Viz_Data_Pipe.ipynb
- Prep Data - Data prepared for modelling by Data_Prep_Pipe.ipynb
Link to Tableau Dashboard used for exploration.
Best Model's Metric
|Mortality Classifier||0.84 (AUC)|
|LoS Regressor||11.46 (RMSE)|