Enhancing Heart Disease Prediction Using Ensemble Techniques (original) (raw)
Related papers
Biomedical Materials & Devices
The exact forecast of heart disease is necessary to proficiently treating cardiovascular patients before a heart failure happens. Assuming we talk about artificial intelligence (AI) techniques, can be accomplished utilizing an ideal AI model with rich medical services information on heart diseases. To begin with, the feature extraction technique, gradient boosting-based sequential feature selection (GBSFS) is applied to separate the significant number of features from coronary illness dataset to create important medical services information. Using machine learning algorithms like Decision tree (DT), Random forest (RF), Multilayer perceptron (MLP), Support vector machine (SVM), Extra tree (ET), Gradient boosting (GBC), Linear regression (LR), K-nearest neighbor (KNN), and stacking, a comparison model is created between dataset that include both all features and a significant number of features. With stacking, the proposed framework achieves test accuracy of 98.78 percent, which is higher than the existing frameworks and most notable in the marking model with 11 features. This outcome shows that our framework is more powerful for the expectation of coronary illness, in contrast with other cutting edge strategies.
Ensemble technique to predict heart disease using machine learning classifiers
Network Biology, 2023
The exact forecast of heart disease is necessary to proficiently treat cardiovascular patients before a heart failure happens. Assuming we talk about AI techniques can be accomplished utilizing an ideal AI model with rich medical services information on heart diseases. To begin with, the feature extraction technique, gradient boosting-based sequential feature selection (GBSFS) is applied to separate the significant number of features (5, 7, 9, and 11) from coronary illness dataset to create important medical services information. The stacking model is prepared for coronary illness forecast. A comparison model is made between datasets with prominent features (5, 7, 9, and 11) as well as all features. The proposed framework is assessed with coronary illness information and contrasted and customary classifiers in view of feature elimination include determination strategies. The proposed framework acquires test accuracy of 98.78%, which is most noteworthy in marking model with 11-featuers and higher than existing frameworks. This outcome shows that our framework is more powerful for the expectation of coronary illness, in contrast with other cutting edge strategies.
Ensemble Feature Selection for Heart Disease Classification
Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies
Feature selection is a fundamental data preparation task in any data mining objective. Deciding on the best feature selection technique to use for a specific context is difficult and time-consuming. Ensemble learning can alleviate this issue. Ensemble methods are based on the assumption that the aggregate results of a group of experts with average knowledge can often be superior to those of highly knowledgeable individual ones. The present study aims to propose a heterogeneous ensemble feature selection for heart disease classification. The proposed ensembles were constructed by combining the results of five univariate filter feature selection techniques using two aggregation methods. The performance of the proposed techniques was evaluated with four classifiers and six heart disease datasets. The empirical experiments showed that applying ensemble feature ranking produced very promising results compared to single ones and previous studies.
HEART DISEASE PREDICTION USING ENSEMBLE APPROACH
Journal ijetrm, 2024
A heart attack, also known as a myocardial infarction, occurs when the flow of blood to a part of the heart muscle is suddenly blocked. This blockage prevents the heart from receiving enough oxygen. If blood flow is not promptly restored, the heart muscle begins to die. Machine learning algorithms are a powerful tool for predicting heart disease, allowing for more accurate results than traditional methods. Different models are compared and evaluated to identify the most accurate algorithm. Early detection is key to managing heart disease, and machine learning can help to identify at-risk individuals. Prevention of heart disease is invaluable for saving lives and reducing medical costs. Machine learning algorithms can provide the most accurate predictions possible, offering the best chance of preventing serious health issue
An Effective Heart Disease Prediction Framework based on Ensemble Techniques in Machine Learning
International Journal of Advanced Computer Science and Applications
To design a framework for effective prediction of heart disease based on ensemble techniques, without the need of feature selection, incorporating data balancing, outlier detection and removal techniques, with results that are still at par with cutting-edge research. In this study, the Cleveland dataset, which has 303 occurrences, is used from the UCI repository. The dataset comprises 76 raw attributes, however only 14 of them are listed by the UCI repository as significant risk factors for heart disease when the dataset is uploaded as an open source dataset. Data balancing strategies, such as random over sampling, are used to address the issue of unbalanced data. Additionally, an isolation forest is used to find outliers in multivariate data, which has not been explored in previous research. After eliminating anomalies from the data, ensemble techniques such as bagging, boosting, voting, stacking are employed to create the prediction model. The potential of the proposed model is assessed for accuracy, sensitivity, and specificity, positive prediction value (PPV), negative prediction value (NPV), F1 score, ROC-AUC and model training time. For the Cleveland dataset, the performance of the suggested methodology is superior, with 98.73% accuracy, 98% sensitivity, 100% specificity, 100% PPV, 97% NPV, 1 as F score, and AUC as 1 with comparatively very less training time. The results of this study demonstrate that our proposed approach significantly outperforms the existing scholarly work in terms of accuracy and all the stated performance metrics. No earlier research has focused on these many performance parameters.
Ensemble Based Heart Disease Prediction Using Machine Learning
International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2023
Clinical science has garnered significant attention from researchers due to their efforts in identifying early human mortality causes. The literature has confirmed that diseases can be caused by various factors, including heart-based disorders. To save human lives and assist healthcare professionals in recognizing, preventing, and managing heart disease, numerous researchers have proposed specific techniques.These techniques include the use of decision trees, random forests, XGBoost, and crossover models. The proposed approach dynamically analyzes the performance of each method, starting with the selection of the most appropriate strategy. The analysis involves implementing these approaches with different features to examine the statistics comprehensively. However, it is important to note that each successful plan has its own limitations. The goal is to build an intelligent and effective method through careful examination and refinement.
International Journal of Engineering Research and Technology (IJERT), 2021
https://www.ijert.org/a-multi-stage-approach-combining-feature-selection-with-machine-learning-techniques-for-higher-prediction-reliability-and-accuracy-in-heart-disease-diagnosis https://www.ijert.org/research/a-multi-stage-approach-combining-feature-selection-with-machine-learning-techniques-for-higher-prediction-reliability-and-accuracy-in-heart-disease-diagnosis-IJERTV10IS070057.pdf The accuracy in predicting Heart Disease (HD), obtained using different data mining approaches, is around 85 percent so far. An error of 15 percent or so is either type 1 or type 2, meaning a person with HD goes un-detected (type 1), or a person without HD undergoes an HD treatment (type 2). Several studies exist on the application of ensemble techniques; however, the quest for increasing the accuracy levels will continue until an approach provides 100 percent accuracy and reliability. The literature review shows that there are no single data mining techniques that give consistent results for all types of healthcare datasets, and the performance of data mining techniques depends on the type of dataset [1-3]. In this paper, the authors compared various classification methods and feature selection techniques on the same dataset. In this paper the authors compared the performance of various classification methods and feature selection techniques on the same dataset. This paper combines two stages, first identifying the significant features using different methods and then testing the change in accuracy of prediction using different standalone Machine Learning (ML) algorithms like Naive Bayes (NB), Support Vector Machines (SVM), Logistic Regression (LR), Decision Tree (DT)) and Ensemble Classifiers like Random Forest (RF), Gradient Boosting (GDB) and Extra Trees (ET) for predicting heart disease (HD). A survey of patients shows that the significant factors considered, by doctors, as the first step to assess the possibility of heart disease include age, sex, test results of blood pressure, cholesterol, and echo-cardio-gram (ECG). This study shows that the prediction accuracy using these features can produce accuracy only to 51 percent. Feature selection techniques may be used to recognize and delete unwanted, obsolete, and redundant attributes from dataset that do not contribute to the accuracy of the predictive model which can potentially reduce the accuracy of the model. Fewer attributes are advantageous because they minimize the complexity of the model, and a simpler model is simpler to understand and explain. Most of the research article explains the estimation of heart disease in the medical profession by the use of data science. As several research studies have done on this issue, however, the accuracy of forecasts still needs to be improved. Thus, this study focuses on feature selection methods, and ML algorithms are used for the analysis of observations and the enhancement of accuracy. By this research, authors achieved an accuracy of 96.77 % and a precision level of 100%.
Optimizing heart disease prediction through ensemble and hybrid machine learning techniques
International Journal of Electrical and Computer Engineering (IJECE), 2024
In this modern era, heart diseases have surfaced as the leading factor of fatalities, accounting for around 17.9 million lives annually. Global deaths from heart diseases have surged by 60% over the last 30 years, primarily because of limited human and logistical resources. Early detection is crucial for effective management through counseling and medication. Earlier studies have identified key elements for heart disease diagnosis, including genetic predispositions and lifestyle factors such as age, gender, smoking habits, stress, diastolic blood pressure, troponin levels, and electrocardiogram (ECG). This project aims to develop a model that can identify the best machine learning (ML) algorithm for predicting heart diseases with high accuracy, precision, and the least misclassification. Various ML techniques were evaluated using selected features from the heart disease dataset. Among these techniques, a combination of random forest (RF), multi-layer perceptron (MLP), XGBoost, and LightGBM employing an ensemble method with a stacking classifier, along with logistic regression (LR) as a metamodel, achieved the highest accuracy rate of 95.8%. This surpasses the efficiency of other techniques. The suggested method provides an encouraging framework for early prediction, with the overarching goal of reducing global mortality rates associated with these conditions.
An Ensemble Classifier for the Prediction of Heart Disease
Heart disease has become a silent killer among people of all ages. The major risk factors of heart disease include smoking, blood pressure, cholesterol, diabetes etc. Early diagnosis and treatment can reduce morbidity rate to an extent by identifying patients at higher risk of having a heart disease and providing them right care at right time. However provisioning of quality services at reasonable costs is a major concern of every healthcares. Poor clinical decisions can pose adverse effects on human health. This paper introduces a method based on data mining according to the information of patients' medical records to predict heart disease. An ensemble classifier approach is being used, that is the combination of three classifiers (KNN, Decision Tree, NaiveBayes) composing an ensemble, so that the overall model can be used to give predictions with greater accuracy than that of individual classifiers.
Role of Feature Selection in Building High Performance Heart Disease Prediction Systems
ADBU Journal of Engineering Technology (AJET), 2019
I n the last few years, there has been a tremendous rise in the number of deaths due to heart diseases all over the world. In low- and middle-income countries, heart diseases are usually not detected in early stages which makes the treatment difficult. Early diagnosis can help significantly in preventing these diseases. Machine learning-based prediction systems offer a cost-effective and efficient way to diagnose these diseases in an early stage. Research is being carried out to increase the performance of these systems. Redundant and irrelevant features in the medical dataset deteriorate the performance of prediction systems. In this paper, an exhaustive study has been done to improve the performance of the prediction systems by applying 4 feature selection algorithms. Experimental results prove that the use of feature selection algorithms provides a substantial increase in accuracy and speed of execution of the prediction system. The prediction system proposed in this study shall ...