The Efficacy of Machine-Learning-Supported Smart System for Heart Disease Prediction
Nurul Absar1, Emon Kumar Das1, Shamsun Nahar Shoma1
1Department of Computer Science and Engineering, BGC Trust University Bangladesh, Chittagong 4381, Bangladesh.
Insights
Machine learning models accurately detect heart disease, with AdaBoost and K-nearest neighbor achieving 100% accuracy on the CHSLB dataset. This enables convenient and cost-effective early diagnosis of cardiopathy.
Area of Science:
- Cardiology
- Computer Science
- Data Science
Background:
- Cardiopathy is a leading cause of death, often linked to lifestyle factors.
- Early and cost-effective detection of heart disease remains a challenge.
- Machine learning (ML) offers potential for improved diagnostic capabilities.
Purpose of the Study:
- To evaluate the efficacy of four ML models for heart disease detection.
- To identify key predictors contributing to heart disease prognosis.
- To develop a user-friendly, computer-aided system for heart disease prediction.
Main Methods:
- Four ML models were employed: Random Forest (RF), Decision Tree (DT), AdaBoost (AB), and K-nearest neighbor (KNN).
- Models were trained and validated using the combined Cleveland, Hungary, Switzerland, and Long Beach (CHSLB) heart disease datasets.
- A generalized algorithm was developed to assess the predictive strength of relevant factors.
Main Results:
- On the CHSLB dataset, RF, DT, AB, and KNN achieved accuracies of 99.03%, 96.10%, 100%, and 100%, respectively.
- Using the Cleveland dataset alone, RF and KNN demonstrated high accuracies of 93.44% and 97.83%.
- A Streamlit-based application was developed for accessible disease prediction.
Conclusions:
- ML models, particularly AB and KNN, show exceptional accuracy in detecting heart disease.
- The developed system provides a convenient tool for early cardiopathy diagnosis.
- The study contributes significant insights into predictor strength for heart disease prognosis.
Abstract:
The disease may be an explicit status that negatively affects human health. Cardiopathy is one of the common deadly diseases that is attributed to unhealthy human habits compared to alternative diseases. With the help of machine learning (ML) algorithms, heart disease can be noticed in a short time as well as at a low cost. This study adopted four machine learning models, such as random forest (RF), decision tree (DT), AdaBoost (AB), and K-nearest neighbor (KNN), to detect heart disease. A generalized algorithm was constructed to analyze the strength of the relevant factors that contribute to heart disease prediction. The models were evaluated using the datasets Cleveland, Hungary, Switzerland, and Long Beach (CHSLB), and all were collected from Kaggle. Based on the CHSLB dataset, RF, DT, AB, and KNN models predicted an accuracy of 99.03%, 96.10%, 100%, and 100%, respectively. In the case of a single (Cleveland) dataset, only two models, namely RF and KNN, show good accuracy of 93.437% and 97.83%, respectively. Finally, the study used Streamlit, an internet-based cloud hosting platform, to develop a computer-aided smart system for disease prediction. It is expected that the proposed tool together with the ML algorithm will play a key role in diagnosing heart diseases in a very convenient manner. Above all, the study has made a substantial contribution to the computation of strength scores with significant predictors in the prognosis of heart disease.
Related Concept Videos
01:30Heart Failure IV: Classification and Diagnostic Evaluation
01:29Cardiomyopathy III: Hypertrophic Cardiomyopathy
01:29Cardiomyopathy V: Interprofessional Care
01:30Heart Failure V: Medical Management