Modified K-Nearest Neighbor Optimization with Genetic Algorithm in Chronic Kidney Disease Classification

DOI

10.2991/978-94-6463-413-6_20How to use a DOI?

Keywords

Genetic Algorithms; Chronic Kidney; Modified K-Nearest Neighbor

Abstract

Chronic kidney disease is a global health problem that requires early diagnosis for effective management. According to a WHO survey, in Indonesia alone it is estimated that around 70,000 cases occur each year, while the percentage increase in cases will occur by 46% from 1955–2025. Early detection of kidney disease can provide early help to reduce the death rate. There are similarities between indications which make the diagnosis process difficult. This research proposes an innovative approach in optimizing chronic kidney disease classification models using the Modified K-Nearest Neighbor (MKNN) method with the application of a Genetic algorithm. MKNN has been proven to be effective in classification, however determining critical parameters such as the number of neighbors (k) can affect the model performance. In this research, Genetic algorithm was used to find the optimal k value of the MKNN parameter. This approach allows the model to automatically adapt to data characteristics, increasing classification accuracy and reducing overfitting. Genetic algorithm was used to optimize the k parameters, and its fitness function was based on the classification performance of the model. Testing was carried out using a chronic kidney disease dataset that includes 24 clinical features. The research results show that the Modified K-Nearest Neighbor algorithm with an accuracy of 93%, precision of 93.2% and recall of 93.2%. Based on the research results, the MKKN model optimized using a genetic algorithm provides significant results based on accuracy, precision and recall.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - I W. Supriana
AU  - Cokorda Pramartha
AU  - I G. N. A. C. Putra
AU  - M. D. A. Raharja
AU  - P. P. K. Wiguna
PY  - 2024
DA  - 2024/05/13
TI  - Modified K-Nearest Neighbor Optimization with Genetic Algorithm in Chronic Kidney Disease Classification
BT  - Proceedings of the First International Conference on Applied Mathematics, Statistics, and Computing (ICAMSAC 2023)
PB  - Atlantis Press
SP  - 204
EP  - 213
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-413-6_20
DO  - 10.2991/978-94-6463-413-6_20
ID  - Supriana2024
ER  -