Diabetes Prediction by Optimizing the Nearest Neighbor Algorithm Using Genetic Algorithm
Introduction: Diabetes or diabetes mellitus is a metabolic disorder in body when the body does not produce insulin, and produced insulin cannot function normally. The presence of various signs and symptoms of this disease makes it difficult for doctors to diagnose. Data mining allows analysis of pat...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | fas |
Published: |
Kerman University of Medical Sciences
2019-06-01
|
Series: | مجله انفورماتیک سلامت و زیست پزشکی |
Subjects: | |
Online Access: | http://jhbmi.ir/article-1-311-en.html |
_version_ | 1811176263682883584 |
---|---|
author | Mohammad Momeny Ali Mohammad Latif Mehdi Agha Sarram Kazem Hajmirzazade Sorayya Gharravi NaghiboAlghara Seyed Mahammad |
author_facet | Mohammad Momeny Ali Mohammad Latif Mehdi Agha Sarram Kazem Hajmirzazade Sorayya Gharravi NaghiboAlghara Seyed Mahammad |
author_sort | Mohammad Momeny |
collection | DOAJ |
description | Introduction: Diabetes or diabetes mellitus is a metabolic disorder in body when the body does not produce insulin, and produced insulin cannot function normally. The presence of various signs and symptoms of this disease makes it difficult for doctors to diagnose. Data mining allows analysis of patients’ clinical data for medical decision making. The aim of this study was to provide a model for increasing the accuracy of diabetes prediction.
Method: In this study, the medical records of 1151 patients with diabetes were studied, with 19 features. Patients’ information were collected from the UCI standard database. Each patient has been followed for at least one year. Genetic Algorithm (GA) and the nearest neighbor algorithm were used to provide diabetes prediction model.
Results: It was revealed that the prediction accuracy of the proposed model equals 0.76. Also, for the methods of Naïve Bayes, Multi-layer perceptron (MLP) neural network, and support vector machine (SVM), the prediction accuracy was 0.62, 0.65, and 0.75, respectively.
Conclusion: In predicting diabetes, the proposed model has the lowest error rate and the highest accuracy compared to the other models. Naïve Bayes method has the highest error rate and the lowest accuracy. |
first_indexed | 2024-04-10T19:49:11Z |
format | Article |
id | doaj.art-19acb8560f8f49029b6623437136ba6b |
institution | Directory Open Access Journal |
issn | 2423-3870 2423-3498 |
language | fas |
last_indexed | 2024-04-10T19:49:11Z |
publishDate | 2019-06-01 |
publisher | Kerman University of Medical Sciences |
record_format | Article |
series | مجله انفورماتیک سلامت و زیست پزشکی |
spelling | doaj.art-19acb8560f8f49029b6623437136ba6b2023-01-28T10:31:19ZfasKerman University of Medical Sciencesمجله انفورماتیک سلامت و زیست پزشکی2423-38702423-34982019-06-01611223Diabetes Prediction by Optimizing the Nearest Neighbor Algorithm Using Genetic AlgorithmMohammad Momeny0Ali Mohammad Latif1Mehdi Agha Sarram2Kazem Hajmirzazade3Sorayya Gharravi4NaghiboAlghara Seyed Mahammad5 Ph.D. Student, Electrical and Computer Engineering Dept., School of Electrical and Computer Engineering, Yazd University, Yazd, Iran Assistant Professor, Electrical and Computer Engineering Dept., Yazd University, Yazd, Iran Associate Professor of Computer Sciences, Electrical and Computer Engineering Dept., Yazd University, Yazd, Iran Assistant Professor of Diseases and Diseases, Faculty of Medicine, Islamic Azad University, Yazd. Iran M.Sc. in Computer engineering (Software), Lecturer, Electrical and Computer Engineering Department, Computer Dept., Integrated Higher Education of Esfarayen, North Khorasan, Esfarayen, Iran General Medicine, Faculty of Medicine, Islamic Azad University, Yazd, Iran Introduction: Diabetes or diabetes mellitus is a metabolic disorder in body when the body does not produce insulin, and produced insulin cannot function normally. The presence of various signs and symptoms of this disease makes it difficult for doctors to diagnose. Data mining allows analysis of patients’ clinical data for medical decision making. The aim of this study was to provide a model for increasing the accuracy of diabetes prediction. Method: In this study, the medical records of 1151 patients with diabetes were studied, with 19 features. Patients’ information were collected from the UCI standard database. Each patient has been followed for at least one year. Genetic Algorithm (GA) and the nearest neighbor algorithm were used to provide diabetes prediction model. Results: It was revealed that the prediction accuracy of the proposed model equals 0.76. Also, for the methods of Naïve Bayes, Multi-layer perceptron (MLP) neural network, and support vector machine (SVM), the prediction accuracy was 0.62, 0.65, and 0.75, respectively. Conclusion: In predicting diabetes, the proposed model has the lowest error rate and the highest accuracy compared to the other models. Naïve Bayes method has the highest error rate and the lowest accuracy.http://jhbmi.ir/article-1-311-en.htmlprediction of diabetesgenetic algorithmnearest neighbor algorithmdata mining |
spellingShingle | Mohammad Momeny Ali Mohammad Latif Mehdi Agha Sarram Kazem Hajmirzazade Sorayya Gharravi NaghiboAlghara Seyed Mahammad Diabetes Prediction by Optimizing the Nearest Neighbor Algorithm Using Genetic Algorithm مجله انفورماتیک سلامت و زیست پزشکی prediction of diabetes genetic algorithm nearest neighbor algorithm data mining |
title | Diabetes Prediction by Optimizing the Nearest Neighbor Algorithm Using Genetic Algorithm |
title_full | Diabetes Prediction by Optimizing the Nearest Neighbor Algorithm Using Genetic Algorithm |
title_fullStr | Diabetes Prediction by Optimizing the Nearest Neighbor Algorithm Using Genetic Algorithm |
title_full_unstemmed | Diabetes Prediction by Optimizing the Nearest Neighbor Algorithm Using Genetic Algorithm |
title_short | Diabetes Prediction by Optimizing the Nearest Neighbor Algorithm Using Genetic Algorithm |
title_sort | diabetes prediction by optimizing the nearest neighbor algorithm using genetic algorithm |
topic | prediction of diabetes genetic algorithm nearest neighbor algorithm data mining |
url | http://jhbmi.ir/article-1-311-en.html |
work_keys_str_mv | AT mohammadmomeny diabetespredictionbyoptimizingthenearestneighboralgorithmusinggeneticalgorithm AT alimohammadlatif diabetespredictionbyoptimizingthenearestneighboralgorithmusinggeneticalgorithm AT mehdiaghasarram diabetespredictionbyoptimizingthenearestneighboralgorithmusinggeneticalgorithm AT kazemhajmirzazade diabetespredictionbyoptimizingthenearestneighboralgorithmusinggeneticalgorithm AT sorayyagharravi diabetespredictionbyoptimizingthenearestneighboralgorithmusinggeneticalgorithm AT naghiboalgharaseyedmahammad diabetespredictionbyoptimizingthenearestneighboralgorithmusinggeneticalgorithm |