Supervised Machine Learning-Based Cardiovascular Disease Analysis and Prediction

Table 1

Dataset feature’s information.

Feature	Explanation
Age	Age of the patient in completed years
Sex	Gender of the patient
Cp	Chest pain is classified into four types: (1) conventional angina, (2) unusual angina, (3) nonanginal pain, and (4) asymptomatic
Trestbps	Blood pressure in the resting state
Chol	Cholesterol in the blood
FBS	Fasting blood sugar levels
Resting	The results of an ECG taken while at rest are represented by three separate values: normal condition is represented by value 0, abnormality in the ST-T wave is represented by value 1 (which may include T-wave inversions and/or depression or an elevation of ST of >0.05 mV), and any possibility or certainty of LV hypertrophy per Estes’ criteria is indicated by value 2
Thali	The achievement of the maximal heart rate
Old peak	In compared to a resting state, exercise causes ST depression
Exang	Exercise-induced angina
Slope	The ST segment is depicted in three values based on the slope during peak exercise: (1) level, (2) flat, and (3) downsloping
Ca	Fluorescence imaging colored main vessels numbered from 0 to 3
Thal	The condition of the heart is represented by three distinct numerical values. Normal defects are numbered 3, fixed defects are numbered 6, and reversible defects are numbered 7
Target	It is the dataset’s last column. Column is a class or label. It denotes the number of classes in the dataset. This dataset has a binary categorization, which means it has two classifications (0, 1). In the class, “0” indicates that there is a low risk of heart illness, but “1” indicates that there is a high risk of heart disease. The value “0” or “1” is determined by the other 13 attributes