Article icon
Original research

Heart plaque detection with improved accuracy using K-nearest neighbors classifier algorithm in comparison with least squares support vector machine

Abstract

Aim: The objective of the work is to evaluate the performance of the k-Nearest Neighbor classifier in detecting heart plaque with high accuracy and comparing it with the Least Squares Support Vector Machine. Materials and Methods:The Kaggle dataset on Heart Plaque Disease yielded a total of 20 samples. Clincalc, which has two groups: alpha, power, and enrollment ratio, is used to assess G power of 0.08 with 95% confidence interval for samples. The training dataset (n = 489 [70 percent]) and the test dataset (n = 277 [30 percent]) are divided into two groups. Accuracy is used to assess the performance of the k-Nearest Neighbor algorithm and the Least Squares Support Vector Machine. Results: The accuracy of the k-Nearest Neighbor algorithm was 86 % and 67.3 % for the Least Squares Support Vector Machine technique. Since p (2-tailed) < 0.05, in SPSS statistical analysis, a significant difference exists between the two groups. Conclusion: In this work, the k-Nearest Neighbor algorithm outperformed the Least Squares Support Vector Machine algorithm in detecting heart plaque disease in the dataset under consideration.

Imprint

Vankamaddi Sunil Kumar, K Vidhya. Heart Plaque Detection with Improved Accuracy using K- Nearest Neighbors classifier Algorithm in comparison with Least Squares Support Vector Machine. Cardiometry; Issue 25; December 2022; p.1590-1594; DOI: 10.18137/cardiometry.2022.25.15901594; Available from: https://www.cardiometry.net/issues/no25-december-2022/k-nearest-neighbors-classifier-algorithm

Keywords

Heart Plaque disease,   Novel grayscale texture feature,   K-Nearest Neighbor algorithm,   Least Squares Support Vector Machine,   Prediction,   Machine learning
Download PDF
Current issue
Cardiometry's library
Founders of Cardiometry
Video about Cardiometry
Our partners