/patient-survival-prediction

A data mining project that encompass Machine Learning in predicting Patient Survivability, This project is built as a fulfillment for my masters degree.

Primary LanguageR

Patient Survival Prediction using Data Mining Techniques

This project was one of the requirements within my postgraduate module called Data Mining. The domain that i have chosen is the healthcare domain in predicting the survivability of the patient based on APACHE II and APACHE III score. A dataset description can be founded in the github file as well. Generally, the main process flow of this project is performing Exploratory Data Analysis, Data Cleaning, and Model Training. The models that are chosen are Naive Bayes, Random Forest, and Decision Tree. Finally, an evaluation on each of the machine learning algorithm is performed.

The project is coded in R Programming Language using R Studio IDE.

The dataset is too huge to be uploaded to GitHub. Therefore, here is the link to the dataset on Kaggle: https://www.kaggle.com/datasets/mitishaagarwal/patient

The full code can be viewed in the "Data Mining Code.R" file.

If anyone wants to use a part of the code. Please reference it. Thanks.