Skip to content

Repository for the project in the course Computational Machine Learning at the Barcelona School of Economics

Notifications You must be signed in to change notification settings

wallstein/Predicting-Patient-Mortality

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Predicting Patient Mortality

Method

In this project, I develop predictive models to assess the mortality risk of patients admitted to Intensive Care Units (ICUs). I utilize two machine learning algorithms: K-Nearest Neighbors (KNN) and Support Vector Machines (SVM). Through cross-validation, I achieved an Area Under the Receiver Operating Characteristic Curve (AUC) score of 92.3% with KNN and 93.2% with SVM, signifying a high level of accuracy in mortality prediction.

Data

The dataset comes from the MIMIC project. MIMIC-III (Medical Information Mart for Intensive Care III) is a large, freely-available database comprising de-identified 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.

About

Repository for the project in the course Computational Machine Learning at the Barcelona School of Economics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published