Heart disease is one of the leading causes of death worldwide and refers to a group of disorders that affect the heart. Among the most common of these disorders is coronary artery disease, which occurs as a result of the narrowing of the coronary arteries, reducing blood flow to the heart muscle and can lead to angina (chest pain) and heart attacks.
Risk factors for heart disease include smoking, high blood pressure, high cholesterol levels, obesity, an unhealthy diet, little physical activity, and a family history of heart disease. The risk of developing heart disease also increases with age.
The goal of my project is to create an intelligent model capable of predicting the likelihood of heart disease based on specific health data and measurements. The model utilizes data that has been collected and recorded in a file named "heart_disease_data.csv", analyzing variables such as age, gender, cholesterol levels, blood pressure, and other factors that can impact heart health.
By implementing the logistic regression algorithm - a method of machine learning. This model represents an important step towards early detection and better management of heart health, which can contribute to improving patients' quality of life and reducing mortality rates associated with heart disease.
This database contains 76 features, but all published experiments report using a subset of 14 of them. In particular, the Cleveland database is the only one used by ML researchers to date. The “Target” field indicates the presence of heart disease in the patient. It is rated from 0 (none) to 4.
Source: https://www.kaggle.com/ronitf/heart-disease-uci
Evaluating our tuned machine learning classifier beyond accuracy:
ROC curve and AUC curve Confusion matrix Classification report Precision Recall F1-score
