Using the K-Nearest Neighbors Algorithm for Automated Detection of Myocardial Infarction by Electrocardiogram Data Entries

This article presents a new approach to solving the problem of automated detection of myocardial infarction of various localization by electrocardiogram data entries. Only the second standard lead is used in the analysis. The signal in this lead undergoes digital filtering in order to remove low-fre...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Pattern recognition and image analysis Jg. 29; H. 4; S. 730 - 737
Hauptverfasser: Savostin, A. A., Ritter, D. V., Savostina, G. V.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Moscow Pleiades Publishing 01.10.2019
Springer Nature B.V
Schlagworte:
Algorithms
Applied Problems
Automation
Classifiers
Computer Science
Electrocardiography
Heart attacks
Image Processing and Computer Vision
Machine learning
Mathematical models
Myocardial infarction
Parameters
Pattern Recognition
k-nearest neighbors algorithm
electrocardiogram
classification
myocardial infarction
ISSN:1054-6618, 1555-6212
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This article presents a new approach to solving the problem of automated detection of myocardial infarction of various localization by electrocardiogram data entries. Only the second standard lead is used in the analysis. The signal in this lead undergoes digital filtering in order to remove low-frequency and high-frequency interference. Then, individual cardio complexes P-QRS-T are extracted from the signal, and the following parameters are calculated for them: minimum value, maximum value, interquartile range, mean absolute deviation, root mean square, mode, and entropy. Using the calculated parameters, a standardized training (learning) dataset is formed. The classifier model represents the k-nearest neighbors algorithm with the Manhattan metric of the distance between the objects and number of neighbors k = 9. After learning, the classifier shows the results by precision pre = 98.60%, by recall rec = 97.34%, by specificity spec = 95.93%, and by accuracy acc = 97.03%. According to the analysis of the obtained results, the suggested classifier model offers certain advantages as compared to existing alternatives.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1054-6618
1555-6212
DOI:10.1134/S1054661819040151