Early and Accurate Prediction of Cardiac Disease Using Hybrid AI Techniques
Author Information
Author(s): Bilal Hazrat, Tian Yibin, Ali Ahmad, Muhammad Yar, Yahya Abid, Izneid Basem Abu, Ullah Inam
Primary Institution: Shenzhen University
Hypothesis
The study proposes a hybrid machine learning model for the early and accurate diagnosis of cardiac disease.
Conclusion
The proposed ETCXGB model achieved 99.98% accuracy in predicting cardiac disease, outperforming classical models.
Supporting Evidence
- The ETCXGB model improved prediction accuracy by 3.91%.
- CNN-RNN, CNN-LSTM, and CNN-BLSTM models also enhanced accuracy by 1.95%, 2.44%, and 2.45%, respectively.
- The proposed hybrid models outperformed classical ML and DL models in all performance measures.
Takeaway
This study created a smart computer program that helps doctors find heart disease early and accurately, which can save lives.
Methodology
The study utilized a hybrid model combining ExtraTreeClassifier and XGBoost for diagnosis, along with preprocessing techniques on the UCI Hungarian heart disease dataset.
Limitations
The study does not address real-time health monitoring of cardiac patients.
Participant Demographics
The dataset includes 1025 instances of both males and females.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website