Detection of Sepsis using Neural Networks
This repository contains the code and resources for predicting sepsis using various machine learning classifiers. The primary goal is to identify the best-performing classifier and develop a user-friendly web application to predict sepsis using Flask.
Introduction
Sepsis is a life-threatening condition that arises when the body's response to infection causes tissue damage, organ failure, or death. Early detection and treatment are crucial for improving patient outcomes. This project aims to develop models using various classifiers such as Multi-Layer Perceptron, AdaBoost, Gaussian Naive Bayes, Linear Discriminant Analysis, Gradient Boosting, and Random Forest to predict sepsis efficiently.
Steps
- Data Preprocessing: Clean and prepare the dataset for model training.
- Feature Selection: Select the most relevant features for the models.
- Model Training: Train various machine learning models.
- Model Evaluation: Evaluate and compare the performance of different models.
- Web Application: User-friendly interface for predicting sepsis.
Here I was not able to upload .pkl file and dataset due to size limitations. So I hereby provide the google drive link for those files (https://drive.google.com/drive/folders/1_VBJfeur0gYlixYLc_V2z3UP2-E6VVnY).
Interface
