Heart disease prediction using machine learning | ||||
| The International Undergraduate Research Conference | ||||
| Volume 5, Issue 5, 2021, Page 163-165 PDF (778.59 K) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/iugrc.2021.245598 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
| Rahma ELHusseiny1; Muhammed Salah2 | ||||
| 1Arab Academy for Science and Technology, Egypt. | ||||
| 2Teacher Assistant, Arab Academy for Science and Technology, Egypt. | ||||
| Abstract | ||||
| Heart diseases have increased enormously in the modern world. People now are facing inducements (e.g. Fast Food) that can have a direct effect on The Heart. All doctors deal with those cases as they do their best to save their lives. To do this, they must have the right results and to help them in diagnosis. Using a model that can predict the vulnerable situation of The heart. Given the basic symptoms such as age, gender, fasting blood sugar, resting blood pressure, person’s cholesterol, chest pain experience, person’s maximum heart rate, exercise-induced angina, ST depression, The slope of the peak exercise ST segment, The number of major vessels and Thalassemia. This can help doctors to recheck their results. The dataset that’s been used for this analysis is Framingham” obtained from Kaggle and Heart disease dataset with 14 features is obtained from UCI. This paper presents the analysis implemented on different models like Decision trees, Random Forest, and K- Nearest Neighbors. After comparing the analysis of these models with each other it has proven that the Random Forest model has the highest accuracy. With an accuracy of 90.16% means it’s proven that it’s the most accurate and trustworthy. | ||||
|
Statistics Article View: 81 PDF Download: 44 |
||||
