|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
In this paper, we propose a unique hybrid model that combines the Bayesian and Random Forest algorithms to better predict diabetic heart disease. The hybrid model also includes hyperparameter adjustment, model evaluation, and feature selection using SVM weights. The suggested model beats individual models in terms of accuracy and efficiency, according to experimental findings. In contrast to the Random Forest technique, which generates an ensemble of decision trees to increase prediction accuracy, the Bayesian approach offers interpretability and the ability to explain. The suggested model outperformed the individual models, achieving an accuracy of 95% with a precision of 0.90 and recall of 0.88. Python can be used to implement the hybrid model, and we think this model has a lot of potential for enhancing diagnostics.
Keyword
Bayesian, Random Forest algorithm, diabetic heart disease, prediction, hybrid model.
PDF Download (click here)
|
|
|
|
|