Early Detection of Heart Disease Using Machine Learning and Predictive Analytics

Primary supervisor

Jesmin Nahar

Specialised project:

This project applies machine learning and predictive analytics to detect early signs of heart disease using publicly available cardiovascular datasets. Students will clean and analyse health data, apply algorithms such as Decision Trees and Random Forest, and identify key risk factors for heart disease. The project aims to show how data-driven methods can support early intervention and improve patient outcomes.

Title: Early Detection of Heart Disease Using Machine Learning and Predictive Analytics

Description:
This project focuses on developing machine learning models to detect early signs of heart disease from patient health data. Students will work with publicly available cardiovascular datasets to clean and preprocess data, select important features, and build predictive models using algorithms such as Logistic Regression, Decision Trees, and Random Forest. The aim is to identify patients at risk of heart disease early, enabling timely interventions and better health outcomes.

Student cohort

Single Semester
Double Semester

Aim/outline

Skills Required:
Python or R programming, basic understanding of machine learning classification techniques, and data preprocessing.

Expected Outcomes:

  • A validated predictive model capable of early heart disease detection.
  • Visual reports and dashboards showing key risk factors influencing predictions.

Benefits:
This project can help improve patient care by identifying heart disease risk early, potentially reducing severe health events and healthcare costs.

Required knowledge

Specialist Project Pre-requisite Skills and/or Knowledge:

  • Basic understanding of machine learning concepts, especially classification models.
  • Knowledge of data cleaning and preprocessing techniques.
  • Familiarity with Python or R programming for data analysis.
  • Basic data visualisation skills to present findings clearly.