Heart Disease Prediction using a Support Vector Classifier (SVC)

Project Goal

The objective of this project is to build a machine learning model to predict the presence of heart disease in a patient based on a set of medical attributes. This notebook covers the entire process, from initial data exploration to training and evaluating a Support Vector Classifier (SVC).

---

Dataset Used

Source:
This project uses a consolidated version of the popular Heart Disease dataset.

Content:

• The dataset contains 1025 patient records and 14 key medical attributes.
• An initial analysis showed that the data is of high quality, with no missing values and all features already in numerical format.

Attribute Information:

Feature	Description
age	Age of the patient in years
sex	Gender (1 = male, 0 = female)
cp	Chest pain type (0–3)
trestbps	Resting blood pressure (mm Hg)
chol	Serum cholesterol (mg/dl)
fbs	Fasting blood sugar > 120 mg/dl (1 = true; 0 = false)
restecg	Resting electrocardiographic results (0,1,2)
thalach	Maximum heart rate achieved
exang	Exercise induced angina (1 = yes; 0 = no)
oldpeak	ST depression induced by exercise relative to rest
slope	Slope of peak exercise ST segment
ca	Number of major vessels (0–3) colored by fluoroscopy
thal	0 = normal; 1 = fixed defect; 2 = reversible defect
target	Heart disease presence (0 = no, 1 = yes)

---

Approach: Step-by-Step Breakdown

1. Data Exploration

• Loaded the dataset and performed a quick exploratory analysis using .info() and .describe() to:
  • Confirm data types
  • Check for missing values (there were none)
  • Understand the statistical distribution of each feature

2. Data Preparation

• Feature Scaling:
  Since SVC is a distance-based algorithm and features are on different scales (e.g., age vs chol), applied StandardScaler to standardize features (mean = 0, std = 1). This ensures all features contribute equally to the model.
• Data Splitting:
  Split the dataset into:
  • Training set: 80%
  • Testing set: 20%
    This allows the model to be trained and evaluated on unseen data.

3. Model Training & Evaluation

• Algorithm: Support Vector Classifier (SVC) for binary classification.
• Training: Model trained on the scaled training data.
• Evaluation:
  • Accuracy on test data: ~85%
  • Generated a confusion matrix to analyze true positives, true negatives, false positives, and false negatives.

---

Notes

• This project demonstrates how SVC can be used for binary classification tasks on real-world medical datasets.
• Proper feature scaling and train-test splitting are crucial for good SVC performance.
• The dataset is clean and numerical, making it ideal for practicing SVC and hyperparameter tuning.

---