Project Overview:

The Disease Prediction project aims to predict the likelihood of heart disease in patients using machine learning models. This project involves developing a web application that allows users to input patient data and receive predictions on heart disease risk.

Dataset taken from -

https://www.kaggle.com/ronitf/heart-disease-uci

Prediction done by

KNN Classifier

Decision Tree

Random Forest

Dataset:

Source: UCI Heart Disease Dataset on Kaggle

Entries: 303

Features: 14 health indicators

Skills:

Machine Learning: Expertise in model development and evaluation.

Web Development: Creating user-friendly interfaces for model deployment.

Tools:

Python: For data analysis and machine learning using libraries like Pandas, Scikit-Learn, and Seaborn.

Jupyter Notebook: For exploratory data analysis and prototyping models.

Flask/Django: For developing the web application.

HTML/CSS/JavaScript: For front-end development.

AWS/Azure: For cloud deployment.

GitHub: For version control and project sharing.

Exploratory Data Analysis:

Data Exploration: Analyzed the dataset to understand the distribution of features and target classes.

Visualization: Used Seaborn to visualize correlations and distributions.

Feature Selection and Preprocessing:

Feature Engineering: Identified and selected the most relevant features.

Data Processing: Scaled numerical features and converted categorical variables into dummy variables.

Machine Learning Models:

K Neighbors Classifier (K=12): Achieved a mean accuracy of approximately 85%.

Random Forest Classifier: Achieved a mean accuracy of approximately 82%.

Decision Tree Classifier: Achieved a mean accuracy of approximately 73%.

Results:

K Neighbors Classifier: Best performance with mean accuracy ≈ 85%.

Random Forest Classifier: Mean accuracy ≈ 82%.

Decision Tree Classifier: Mean accuracy ≈ 73%.

Next Steps:

Model Optimization: Further fine-tuning and hyperparameter optimization to improve model performance.

Extended Analysis: Exploring additional classifiers and advanced techniques for better accuracy.

Lessons Learned:

Feature Engineering: Crucial for enhancing model performance.

Model Comparison: Importance of evaluating multiple classifiers and tuning their hyperparameters.

Check out the full project on GitHub

#MachineLearning #DataScience #HeartDiseasePrediction #AI #GitHub