Cardiovascular disease prevention is now absolutely essential. Effective data-driven cardiac disease prediction systems can enhance the whole research and prevention process, ensuring that a greater number of individuals can lead healthy lives. This is the application of machine learning. Accurate forecasts about heart disorders are made with the aid of machine learning.

The project required accurate data processing and analysis of the patient dataset for heart disease. After that, many models were trained, and various methods were used to make predictions. Logistic regression, KNN, Decision Tree, Random Forest, SVM, and so forth The dataset and notebook code for my Kaggle kernel project, "Binary Classification with Sklearn and Keras," are available here.

I've predicted whether a patient has cardiac disease using a range of Python-based machine learning techniques. This is a classification problem where the goal variable is a binary variable that predicts whether or not heart disease is present. The input features are a range of values.

Machine Learning algorithms used:

1. Logistic Regression (Scikit-learn)
2. Naive Bayes (Scikit-learn)
3. Support Vector Machine (Linear) (Scikit-learn)
4. K-Nearest Neighbours (Scikit-learn)
5. Decision Tree (Scikit-learn)
6. Random Forest (Scikit-learn)
7. XGBoost (Scikit-learn)
8. Artificial Neural Network with 1 Hidden layer (Keras)

Accuracy achieved: 95% (Random Forest)

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