Related Experiment Video
Updated: Sep 4, 2025
12:09
Patient-specific Modeling of the Heart: Estimation of Ventricular Fiber Orientations
Published on: January 8, 2013
13.8K
A Context-Aware MRIPPER Algorithm for Heart Disease Prediction
Saad Almutairi1, S Manimurugan1, Naveen Chilamkurti2
1Industrial Innovation and Robotics Center, Faculty of Computers and Information Technology, University of Tabuk, Tabuk, Saudi Arabia.
Journal of Healthcare Engineering
|July 21, 2022
Summary
This study introduces an IoT-enabled healthcare system using context awareness for heart disease prediction. The Modified Repeated Incremental Pruning to Produce Error (MRIPPER) algorithm achieved high accuracy, demonstrating its effectiveness in medical data analysis.
Area of Science:
- Medical Informatics
- Artificial Intelligence in Healthcare
- Internet of Things (IoT)
Background:
- Mobile computing and advanced technologies are increasingly integrated into daily life, including the medical domain.
- Context-aware systems and applications are emerging technologies transforming healthcare delivery.
- The need for efficient patient data analysis and disease prediction is paramount.
Purpose of the Study:
- To develop an Internet of Things (IoT)-enabled healthcare system leveraging context awareness for patient data analysis.
- To utilize the Modified Repeated Incremental Pruning to Produce Error (MRIPPER) algorithm for classifying and predicting heart disease.
- To evaluate the performance of the proposed system against other machine learning algorithms.
Main Methods:
- Implementation of an IoT-enabled healthcare system using smart medical devices for data collection and storage.
- Application of the Modified Repeated Incremental Pruning to Produce Error (MRIPPER) algorithm, a rule-based machine learning technique, for data analysis.
- Simulation and performance comparison using MATLAB against Random Forest, J48, CART, JRip, and OneR algorithms.
Main Results:
- The proposed MRIPPER-based model achieved high performance metrics: 98.89% accuracy, 96.76% precision, 99.05% sensitivity, 94.35% specificity, and 97.60% F-score.
- Accurate predictions were made for both normal (97.38%) and abnormal (97.93%) subjects.
- The proposed model outperformed other compared machine learning algorithms in heart disease prediction.
Conclusions:
- The developed IoT-enabled healthcare system effectively utilizes context awareness and the MRIPPER algorithm for accurate heart disease prediction.
- The MRIPPER algorithm demonstrates superior performance in analyzing medical datasets compared to traditional methods like Random Forest and J48.
- This approach offers a promising solution for improving diagnostic accuracy and patient outcomes in healthcare through advanced technology integration.
