Ischemic heart disease recognition by k-NN classification of current density distribution maps

Udovychenko, Yevhenii; Попов, Антон; Chaikovsky, Illya

doi:10.1109/elnano.2015.7146919

Cited by 8 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our further study, we developed a multiclass classifier based on correlation analysis ( 9 ), with value of accuracy equal to 95%, in order to provide a tool for the complex analysis of a patient's cardiovascular system by MCG. In other study, we applied a k-NN algorithm for the binary classification of CDDMs for ischemic heart disease recognition ( 10 ). Developed classifiers showed accuracy in the range of 60–90% depending on the type of CDDM.…”

Section: Introductionmentioning

confidence: 99%

Multistage Classification of Current Density Distribution Maps of Various Heart States Based on Correlation Analysis and k-NN Algorithm

Udovychenko

Попов

Chaikovsky

2021

Front. Med. Technol.

Self Cite

View full text Add to dashboard Cite

Magnetocardiography is a modern method of registration of the magnetic component of electromagnetic field, generated by heart activity. Magnetocardiography results are a useful source for the diagnosis of various heart diseases and states, but their usage is still undervalued in the cardiology community. In this study, a two-stage classification by correlation analysis using a k-Nearest Neighbor (k-NN) algorithm is applied for the binary classification of myocardium current density distribution maps (CDDMs). Fourteen groups of CDDMs from patients with different heart states, healthy volunteers, sportsmen, patients with negative T-peak, patients with myocardial damage, male and female patients with microvascular disease, patients with ischemic heart disease, and patients with left ventricular hypertrophy, divided into five and three different groups depending on the degree of pathology, were compared. Selection of best metric, used in classifier and number of neighbors, was performed to define the classifier with best performance for each pair of heart states. Accuracy, specificity, sensitivity, and precision values dependent on the number of neighbors are obtained for each class. The proposed method allows to obtain a value of average accuracy equal to 96%, 70% sensitivity, 98% specificity, and 70% precision.

show abstract

Section: Introductionmentioning

confidence: 99%

Multistage Classification of Current Density Distribution Maps of Various Heart States Based on Correlation Analysis and k-NN Algorithm

Udovychenko

Попов

Chaikovsky

2021

Front. Med. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is more typically used for classification tasks than for regression tasks. Study [23] classified heart disease using KNN. In paper [24], the authors suggested a model for offline handwritten digit prediction using KNN.…”

Section: Instance Based/lazy Learningmentioning

confidence: 99%

Supervised Learning - A Systematic Literature Review

Dridi

2024

Preprint

View full text Add to dashboard Cite

Machine Learning (ML) is a rapidly emerging field that enables a plethora of innovative approaches to solving real-worldproblems. It enables machines to learn without human intervention from data and is used in a variety of applications,from fraud detection to recommendation systems and medical imaging. Supervised learning, unsupervised learning, andreinforcement learning are the 3 main categories of ML. Supervised learning involves pre-training the model on a labeleddataset and entails two distinct types of learning: classification and regression. Regression is used when the output iscontinuous. By contrast, classification is used when the output is categorical.Supervised learning aims to optimize class label models using predictor features. Following that, a second classifieris used to assign class labels to the test data in cases where the values of the predictor characteristics are known butthe value of the class label is unknown. In classification, the label identifies the class to which the training set belongs.However, in regression, the label is a real-value response that corresponds to the example.

show abstract

“…From the experiment results obtained 80-88% accuracy range, 70-95% sensitivity, 78-95% specification and 77-93% precision. In another research, Udovychenko et al, [21] classified the Ischemic heartbeat using the K-Means method. Based on the results of the experiment, the optimal number of neighbors in increasing accuracy was 20-25 neighbors.…”

Section: Literature Studymentioning

confidence: 99%

Performance Analysis of Data Mining Methods for Sexually Transmitted Disease Classification

Yuliastuti¹,

Alfiyatin²,

Rizki³

et al. 2018

IJECE

View full text Add to dashboard Cite

According to health reports of Malang city, many people are exposed to sexually transmitted diseases and most sufferers are not aware of the symptoms. Malang city being known as a city of education so that every year the population number increases, it is at risk of increasing the spread of sexually transmitted diseases virus. This problem is important to be solved to treat earlier sufferers sexually transmitted diseases virus in order to reduce the burden of patient spending. In this research, authors conduct data mining methods to classifying sexually transmitted diseases. From the experiment result shows that K-NN is the best method for solve this problem with 90% accuracy.

show abstract

Ischemic heart disease recognition by k-NN classification of current density distribution maps

Cited by 8 publications

References 7 publications

Multistage Classification of Current Density Distribution Maps of Various Heart States Based on Correlation Analysis and k-NN Algorithm

Multistage Classification of Current Density Distribution Maps of Various Heart States Based on Correlation Analysis and k-NN Algorithm

Supervised Learning - A Systematic Literature Review

Performance Analysis of Data Mining Methods for Sexually Transmitted Disease Classification

Contact Info

Product

Resources

About