ICUonAdmission_sepsisPrediction

Sepsis prediction using ICU single time point on-admission data

Table of Contents

• Introduction
• Problem Statement
• Features
• Installation
• Usage
• Contributing
• License
• Contact

Introduction

Welcome to ICUonAdmission_sepsisPrediction! The goal of this project is to predict sepsis using on-admission ICU data with single entry/patient. Moreover, we perform feature selection strategies to obtain two separate sets of 10 features each.

Problem Statement

Sepsis is host’s dysregulated response to an infection causing life-threatening organ damage and one of the leading causes of mortality in the Intensive Care Unit. With a rapid condition worsening of the critically ill patients, predicting who is likely to become septic is an important challenge.

Features

Our data contains 52 features from University Hospital Mannheim surgical ICU collected between 2016-2022. Generally, the
- Lab results
- Clinical Scores
- SIRS descriptors
- Vital signs
- Demographics

How to run the code?

Installation

To get started with Project Name, you need to have Python installed on your system. Follow these steps:

Running and other comments

1. Clone the repository
   ```bash
   git clone https://github.com/your-username/repo-name.git
   cd repo-name

You can either run with
```bash
python mainWrapper.py

Or open the script in an editor and run from there.