Volume 26, Issue 8 (11-2019)
RJMS 2019, 26(8): 14-22 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Bastin takhti S, Firouzi jahantigh F. A model for diagnosis of kidney disease using machine learning techniques. RJMS 2019; 26 (8) :14-22
URL: http://rjms.iums.ac.ir/article-1-5727-en.html
URL: http://rjms.iums.ac.ir/article-1-5727-en.html
PhD, Assistant Professor, University of Sistan and Baluchistan, Sistan and Baluchistan, Iran , firouzi@eng.usb.ac.ir
Abstract: (3928 Views)
Background: Today, the application of artificial intelligence in the field of health systems has been expanded. Machine learning as one of the sub-branches of artificial intelligence has many applications in the field of medical diagnosis. Chronic kidney disease is one of the most common kidney diseases around the world, which facilitation and acceleration in its diagnosis will have a very favorable outcome for its future treatment. The purpose of this study is to provide an intelligent model based on machine learning techniques for diagnosis of kidney diseases.
Methods: The data used in this study was extracted from 400 patients and non-patients in India. These data were pre-processed in the Python environment and cleared from noisy and outlying observations. Then support vector machine, multilayer perceptron, and decision tree were used for data classification. Accuracy, Recall and Precision evaluation metrics were calculated for performance evaluation of these classifiers.
Results: For the support vector machine algorithm, the Accuracy, Recall and Precision metrics were calculated to be 0.97, 0.961, and 0.986, respectively. The findings indicated that the support vector machine algorithm performs better in terms of Accuracy. In terms of Recall, the decision tree algorithm with the value of 0.963 had the best performance, and in terms of Precision, multi-layer perceptron algorithm with 0.994 had the best performance in data classification.
Conclusion: The results showed that machine learning techniques could be effective in the diagnosis of kidney disease. The use of these techniques can facilitate and expedite the diagnosis and treatment of these patients and increase the likelihood of recovery. The results also showed that the model presented on the basis of machine learning techniques is more accurate, simpler and less expensive than other techniques.
Methods: The data used in this study was extracted from 400 patients and non-patients in India. These data were pre-processed in the Python environment and cleared from noisy and outlying observations. Then support vector machine, multilayer perceptron, and decision tree were used for data classification. Accuracy, Recall and Precision evaluation metrics were calculated for performance evaluation of these classifiers.
Results: For the support vector machine algorithm, the Accuracy, Recall and Precision metrics were calculated to be 0.97, 0.961, and 0.986, respectively. The findings indicated that the support vector machine algorithm performs better in terms of Accuracy. In terms of Recall, the decision tree algorithm with the value of 0.963 had the best performance, and in terms of Precision, multi-layer perceptron algorithm with 0.994 had the best performance in data classification.
Conclusion: The results showed that machine learning techniques could be effective in the diagnosis of kidney disease. The use of these techniques can facilitate and expedite the diagnosis and treatment of these patients and increase the likelihood of recovery. The results also showed that the model presented on the basis of machine learning techniques is more accurate, simpler and less expensive than other techniques.
Keywords: Artificial intelligence, Machine learning, Classification, Medical diagnosis, Kidney disease
Type of Study: Research |
Subject:
Nephrology
References
1. References
2. 1. Kimmel P, Rosenberg M. Chronic Renal Disease. 1st ed. USA: Academic Press; 2014.
3. 2. Pérez-Sáez MJ, Prieto-Alhambra D, Barrios C, Crespo M, Redondo D, Nogués X, et al. Increased hip fracture and mortality in kidney disease individuals: the importance of competing risks. Bone; 2015.73:154-9.
4. 3. Cueto-Manzano AM, Cortés-Sanabria L, Martínez-Ramírez HR, Rojas-Campos E, Gómez-Navarro B, Castillero-Manzano M. Prevalence of kidney disease in an adult population. Arch Med Res; 2014.45(6):507-13.
5. 4. Kavakiotis I, Tsave O, Salifoglou A, Maglaveras N, Vlahavas I, Chouvarda I. Machine learning and data mining methods in diabetes research. Comput Struct Biotechnol J; 2017.15:104-16.
6. 5. Gharaati Z, Pajoohan M. [Diagnosis of leukemia type by machine learning: dimension reduction and balancing]. IJDO; 2018.5(1):25-34. [Persian]
7. 6. Zheng T, Xie W, Xu L, He X, Zhang Y, You M, et al. A machine learning-based framework to identify type 2 diabetes through electronic health records. Int J Med Inform; 2017.97:120-7.
8. 7. Mercaldo F, Nardone V, Santone A. Diabetes mellitus affected patients classification and diagnosis through machine learning techniques. KES; 2017.112:2519-28.
9. 8. Dunaeva O, Edelsbrunner H, Lukyanov A, Machin M, Malkova D, Kuvaev R, et al. The classification of endoscopy images with persistent homology. Patrec; 2016.83:13-22.
10. 9. 9- Wu CC, Yeh WC, Hsu WD, Islam MM, Nguyen PA, Poly TN, et al. Prediction of fatty liver disease using machine learning algorithms. Comput Methods Programs Biomed; 2019.170:23-9.
11. 10. Lynch C, Abdollahi B, Fuqua J, Carlo A, Bartholomai J, Balgemann R, et al. Prediction of lung cancer patient survival via supervised machine learning classification techniques. Int J Med Inform; 2017.108:1-8.
12. 11. Dumortier A, Beckjord E, Shiffman S, Sejdić E. Classifying smoking urges via machine learning. Comput Methods Programs Biomed; 2016.137:203-13.
13. 12. Martínez-Martínez JM, Escandell-Montero P, Barbieri C, Soria-Olivas E, Mari F, Martínez-Sober M .et al. Prediction of the hemoglobin level in hemodialysis patients using machine learning techniques. Comput Methods Programs Biomed; 2014.117(2):208-17.
14. 13. Chen Z, Zhang Z, Zhu R, Xiang Y, Harrington PB. Diagnosis of patients with kidney disease by using two fuzzy classifiers. CMBEBIH; 2016.153:140-5.
15. 14. Muthukumar P, Krishnan GS. A similarity measure of intuitionistic fuzzy soft sets and its application in medical diagnosis. Appl Soft Comput; 2016.41:148-56.
16. 15. UCI Machine Learning Repository: Kidney disease (CKD) Data Set, 2015. [Internet]. Available from: https://archive.ics.uci.edu/ml/datasets/Chronic_ Kidney_Disease
17. 16. Downey AB. Think stats: exploratory data analysis. USA: O'Reilly Media, Inc.; 2014.
18. 17. Cady F. The Data Science Handbook. 1st ed. USA: John Wiley & Sons; 2017.
19. 18. Deng N, Tian Y, Zhang C. Support vector machines: optimization based theory, algorithms, and extensions. 1st ed. USA: Chapman and Hall/CRC; 2012.
20. 19. Soares FM, Souza AM. Neural network programming with Java. 1st ed: Birmingham UK: Packet Publishing Ltd; 2017.
21. 20. Hackeling G. Mastering Machine Learning with scikit-learn. 1st ed: Birmingham UK: Packet Publishing Ltd; 2017.
22. 21. Sheikhtaheri A, Hamedan F, Sanadgol H, Orooji A. [Development of a fuzzy expert system to diagnose kidney disease]. Razi J Med Sci; 2019.25(10):46-60. [Persian]
23. 22. Akben SB. Early stage kidney disease diagnosis by applying data mining methods to urinalysis, blood analysis and disease history. IRBM; 2018.39(5):353-8.
24. 23. Sinha P, Sinha P. Comparative study of kidney disease prediction using KNN and SVM. Int J Eng Res Technol; 2015.4:608-12.
25. 24. Heravi M, Setayeshi S. [Intelligent and fast recognition of heart disease based on synergy of linear neural network and logistic regression model]. J Mashhad Uni Med Sci; 2014.24(112):78-87. [Persian]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
