Heart Disease Prediction Using Classification Techniques of Supervised Machine Learning
Abstrak
The heart stands as the most essential part in the human system, providing the circulatory system to each part of the body. The prediction of cardiovascular diseases is an important task in medicine. Machine learning helps process large medical data and reveal hidden knowledge that would otherwise be impossible to detect with the human eye. Various data mining and machine learning approaches, including Decision Tree, Logistic Regression, K-Nearest Neighbor (KNN), Naive Bayes, and Support Vector Machine (SVM), are utilized to predict cardiovascular disease. This large-scale project seeks to find the potential of using machine learning for accurate disease prediction (cardiovascular diseases), contributing to the advancement of health research. The Random Forest Classifier achieved the highest accuracy of 93%, along with impressive scores for AUC (98%), recall (94%), precision (94%), F1-score (94%), and MCC (87%). Other ensemble algorithms like Extra Trees and Gradient Boosting variants also exhibited high accuracies above 90%. In contrast, traditional algorithms like Logistic Regression, Naive Bayes, and linear models lagged behind, with accuracies ranging from 84-87%.
Penulis (5)
G. Balaraju
M. Reddy
S. Manjunath
M. Hemalatha
N. Veena
Akses Cepat
PDF tidak tersedia langsung
Cek di sumber asli →- Tahun Terbit
- 2024
- Bahasa
- en
- Total Sitasi
- 16×
- Sumber Database
- Semantic Scholar
- DOI
- 10.1109/NMITCON62075.2024.10699057
- Akses
- Open Access ✓