A simple machine learning project that classifies patient cancer risk levels using demographic and health history data.
Find a file
Ray 148590fba4
Update README with online execution instructions
Added instructions for running the project online using Binder.
2026-06-02 03:39:17 +10:00
.devcontainer Initial commit 2026-03-11 00:06:45 +11:00
.gitignore Initial commit 2026-03-11 00:06:45 +11:00
data.csv Move files around to keep things clean 2026-04-17 05:46:29 +00:00
HospitalCancerClassification.ipynb Final notebook 2026-05-03 09:46:06 +00:00
LICENSE Initial commit 2026-03-11 00:06:45 +11:00
README.md Update README with online execution instructions 2026-06-02 03:39:17 +10:00
requirements.txt Initial commit 2026-03-11 00:06:45 +11:00
Scenario Documentation.pdf Upload Scenario documentation for reference 2026-04-17 06:30:42 +00:00

Hospital Cancer Risk Classification

A simple machine learning project that classifies patient cancer risk levels using demographic and health history data.

Overview

This project was created as part of an ICT and Machine Learning assessment scenario for TAFE NSW.

The goal was to build and evaluate a neural network model capable of classifying patients into:

  • High Risk
  • Medium Risk
  • Low Risk

The model helps healthcare professionals identify patients who may require closer monitoring or early intervention.


Technologies Used

  • Python
  • Jupyter Notebook
  • Scikit-learn
  • Pandas
  • NumPy

Machine Learning Model

This project uses Scikit-learn's:

  • MLPClassifier

The model was trained and evaluated using prepared healthcare data.


Dataset Preparation

Age Categories

Patient ages were grouped into:

  • 0–14
  • 15–24
  • 25–34
  • 35–44
  • 45–54
  • 55–64
  • 65–74
  • 75–84
  • 85+

Data Split

The dataset was split into:

  • 70% Training
  • 15% Validation
  • 15% Testing

Running the Notebook

Clone the repository:

git clone https://github.com/reiyua/HospitalCancerClassification.git

You can also run it online: Binder