Comparative Analysis of Decision Support System for Heart Disease

Gujral, Rajneesh Kumar; Rani, Pooja

doi:10.37418/amsj.9.6.15

Cited by 19 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The specific method is to correct the position of the J peaks to the peak value in the interval of the J peaks, which is closest to , avg J T . Suppose the set of peak positions within a certain J peaks interval is , peak i T (i=1,2,…,N, where N is the number of J peaks intervals), then the corrected , index i J can be represented as Equation (3). Table 1 shows the complete J peak detection algorithm.…”

Section: Error Correctionmentioning

confidence: 99%

“…Among these diseases, diseases caused by heart disease are particularly serious because the heart condition is one of the most basic information about human health [2] . The cardiovascular system is a complex nonlinear system that contains a lot of information about the human circulatory system [3] . Therefore, an economical, simple and portable heart monitoring system has great significance for the prevention and early monitoring of cardiovascular diseases.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

J peaks detection for ballistocardiography based on autocorrelation and dual-threshold

Ma,

Wei

2024

Fourth International Conference on Sensors and Information Technology (ICSI 2024)

View full text Add to dashboard Cite

Ballistocardiography (BCG) is a non-contact method of detecting cardiac activity that measures changes in external pressure caused by heartbeats and arterial blood circulation. In this study, BCG signals were collected using a microbend fiber sensor along with Electrocardiography (ECG) as a reference signal. A heart rate detection algorithm based on autocorrelation and a dual-threshold J peaks detection algorithm were proposed to achieve real-time detection of heart rates and accurate detection of J peaks. Additionally, signals from six healthy adult subjects were collected to evaluate the effectiveness of the algorithms by comparing the differences between ECG and BCG in heart rate detection and ECG R-peaks and BCG J peaks detection. Results showed that the accuracy of the autocorrelation-based heart rate detection algorithm reached 99.77% and the accuracy of the dual-threshold J peaks detection algorithm reached 98.03%.

show abstract

Section: Error Correctionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

J peaks detection for ballistocardiography based on autocorrelation and dual-threshold

Ma,

Wei

2024

Fourth International Conference on Sensors and Information Technology (ICSI 2024)

View full text Add to dashboard Cite

show abstract

“…Giri et al [20] used the discrete wavelet transform to decompose the heart rate signal and applied principal component analysis, linear discriminant analysis, and independent component analysis to the wavelet coefficient set to reduce the data dimension. Then they use the support vector machine, Gaussian mixture model, probabilistic neural network, and K-nearest neighbor four classifiers to identify patients with coronary heart disease and normal people; Alickovic et al [21] used an autoregressive model to extract features from ECG data, using K-nearest neighbors, support vector machines, multilayer perceptrons, and the radial basis function network to distinguish arrhythmia patients from normal people; For an automatic diagnosis system for Parkinson's disease, Lamba et al [22] used four transfer learning architectures: ResNet, DensNet, VGG, and AlexNet to classify spiral images of trainee populations; Kumar et al [23] systematically introduced a decision support system (DSS) for diagnosing cardiac disease, analyzing various current problems and challenges in predicting cardiac disease.…”

Section: Disease Prediction Using Machine Learningmentioning

confidence: 99%

Acute coronary syndrome risk prediction based on gradient boosted tree feature selection and recursive feature elimination: A dataset-specific modeling study

et al. 2022

View full text Add to dashboard Cite

Acute coronary syndrome (ACS) is a serious cardiovascular disease that can lead to cardiac arrest if not diagnosed promptly. However, in the actual diagnosis and treatment of ACS, there will be a large number of redundant related features that interfere with the judgment of professionals. Further, existing methods have difficulty identifying high-quality ACS features from these data, and the interpretability work is insufficient. In response to this problem, this paper uses a hybrid feature selection method based on gradient boosting trees and recursive feature elimination with cross-validation (RFECV) to reduce ACS feature redundancy and uses interpretable feature learning for feature selection to retain the most discriminative features. While reducing the feature set search space, this method can balance model simplicity and learning performance to select the best feature subset. We leverage the interpretability of gradient boosting trees to aid in understanding key features of ACS, linking the eigenvalue meaning of instances to model risk predictions to provide interpretability for the classifier. The data set used in this paper is patient records after percutaneous coronary intervention (PCI) in a tertiary hospital in Fujian Province, China from 2016 to 2021. In this paper, we experimentally explored the impact of our method on ACS risk prediction. We extracted 25 key variables from 430 complex ACS medical features, with a feature reduction rate of 94.19%, and identified 5 key ACS factors. Compared with different baseline methods (Logistic Regression, Random Forest, Gradient Boosting, Extreme Gradient Boosting, Multilayer Perceptron, and 1D Convolutional Networks), the results show that our method achieves the highest Accuracy of 98.8%.

show abstract

“…It has many symptoms including chest pain, heartburn, and breathlessness, etc. It is a challenging and important task to predict heart disease at early stages because it can reduce the mortality rate (Kumar & Rani, 2020). Heart disease must be diagnosed at early stages; otherwise, it can lead to life-threatening situations.…”

Section: Introductionmentioning

confidence: 99%

An Intelligent System for Heart Disease Diagnosis using Regularized Deep Neural Network

Rani

Kumar²,

Jain³

2023

JART

View full text Add to dashboard Cite

Heart disease is one of the deadly diseases. Timely detection of the disease can prevent mortality. In this paper, an intelligent system is proposed for the diagnosis of heart disease using clinical parameters at early stages. The system is developed using the Regularized Deep Neural Network model (Reg-DNN). Cleveland heart disease dataset has been used for training the model. Regularization has been achieved by using dropout and L2 regularization. Efficiency of Reg-DNN was evaluated by using hold-out validation method.70% data was used for training the model and 30% data was used for testing the model. Results indicate that Reg-DNN provided better performance than conventional DNN. Regularization has helped to overcome overfitting. Reg-DNN has achieved an accuracy of 94.79%. Results achieved are quite promising as compared to existing systems in the literature. Authors developed a system containing a graphical user interface. So, the system can be easily used by anyone to diagnose heart disease using the clinical parameters.

show abstract

Comparative Analysis of Decision Support System for Heart Disease

Cited by 19 publications

References 7 publications

J peaks detection for ballistocardiography based on autocorrelation and dual-threshold

J peaks detection for ballistocardiography based on autocorrelation and dual-threshold

Acute coronary syndrome risk prediction based on gradient boosted tree feature selection and recursive feature elimination: A dataset-specific modeling study

An Intelligent System for Heart Disease Diagnosis using Regularized Deep Neural Network

Contact Info

Product

Resources

About