The mortality of patients in intensive care unit is predicted using R packages compatibles with Big Data processing. The predictive model is a logistic regression model. This model uses series of physiological measures obtained from patients in the first 24 hours of ICU admission. The datas were obtained of PhysioNet (Computing in Cardiology Challenge, 2012)


Diego Gachet., ML. Morales Botello, Manuel de Buenaga, Enrique Puertas. (2015). Health Sensors Information Processing and Analytics using Big Data approaches. In Proceedings of the 2nd EAI International Conference on IoT Technologies for HealthCare. Lecture Notes of ICST 2015


Pre-processed data in csv format: PreProcessedData.csv

Original data are availables in PhysioNet/Computing in Cardiology Challenge 2012

Here are available the original data where have been pulled each individual patient file into one dataset and added a new column for RecordID

For more information contact us at: