• Abstract: Heart disease is easier to treat when it is detected in the early stages. Machine learning techniques may aid a more efficient analysis in the prediction of the disease. Moreover, this prediction is one of the most central problems in medicine, as it is one of the leading diseases related to an unhealthy lifestyle. So, an early prediction of this disease will be useful for a cure or aversion.

• Problem Statement: Analyze the heart disease dataset to explore the machine learning algorithms and build a decision tree model to predict the disease.

• Variable Description: -- age : Age of the patient

-- gender: Gender of the patient - (0,1) - (Male, Female)

-- chest_pain: It refers to the chest pain experienced by the patient -(0,1,2,3)

-- rest_bps: Blood pressure of the patient while resting(in mm/Hg)

-- cholesterol: Patient's cholesterol level (in mg/dl)

-- fasting_blood_sugar: The blood sugar of the patient while fasting

-- rest_ecg: Potassium level (0,1,2)

-- thalach: The patient’ s maximum heart rate

-- exer_angina: It refers to exercise-induced angina - (1=Yes, 0=No)

-- old_peak: It is the ST depression induced by exercise relative to rest(ST relates to the position on ECG plots)

-- slope: It refers to the slope of the peak of the exercise ST-Segment- (0,1,2)

-- ca: Number of major vessels - (0,1,2,3,4)

-- thalassemia: It refers to thalassemia which is a blood disorder - (0,1,2,3)

-- target: The patient has heart disease or not - (1=Yes, 0=No)

• Scope: ● Understand data by performing exploratory data analysis ● Training and building Decision Tree classification algorithm to predict if a patient has heart disease ● Understand feature importances and improve the model ● Understand various model performance metrics and measure the performance of each model