The dataset comes from MIMIC project ( https://mimic.physionet.org/). MIMIC-III (Medical Information Mart for Intensive Care III) is a large, freely-available database comprising deidentified health-related data associated with over forty thousand patients who stayed in critical care units of the Beth Israel Deaconess Medical Center between 2001 and 2012.
Each row of *mimic_train.csv* correponds to one ICU stay (*hadm_id*+*icustay_id*) of one patient (*subject_id*). Column LOS is the length of stay of the current hospital stay, equal to discharge time minus admit time; this is the outcome to predict in our modelling exercise. The remaining columns correspond to vitals of each patient (when entering the ICU), plus some general characteristics (age, gender, etc.), and their explanation can be found at *mimic_patient_metadata.csv*.
Please don't use any feature that you infer you don't know the first day of a patient in an ICU.
Note that the main cause/disease of patient condition is embedded as a code at *ICD9_diagnosis* column. The meaning of this code can be found at *MIMIC_metadata_diagnose.csv*. But this is only the main one; a patient can have co-occurrent diseases (comorbidities). These secondary codes can be found at *extra_data/MIMIC_diagnoses.csv*.
There is an extra test dataset, mimic_test_los.csv. Apply your final model to this extra dataset and produce a prediction csv file in same format as mimic_kaggle_los_sample_submission.csv.