Volume 25, Issue 10 (1-2019)
RJMS 2019, 25(10): 46-60 |
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:
Sheikhtaheri A, Hamedan F, Sanadgol H, Orooji A. Development of a fuzzy expert system to diagnose chronic kidney disease. RJMS 2019; 25 (10) :46-60
URL: http://rjms.iums.ac.ir/article-1-5200-en.html
URL: http://rjms.iums.ac.ir/article-1-5200-en.html
Iran University of Medical Sciences, Tehran, Iran , f.hamedan@gmail.cm
Abstract: (4433 Views)
Background: Diagnosis and early intervention of chronic kidney disease is essential to prevent loss of a large amount of financial resources. For this reason, the researcher is seeking to design a fuzzy logic based expert system for diagnosis of chronic kidney disease.
Methods: At first, a strategic search was conducted in the Pubmed database for initial identification of the parameters. A questionnaire was distributed to all nephrologists in Iran University of Medical Sciences (18 physicians). Data analysis was performed using SPSS v.22, which was calculated by taking the average of the scores given to each parameter. Depending on the features selected, a set of general rules for the diagnosis of chronic kidney disease was determined by reviewing the literature, guidelines and consulting with a nephrologist. Fuzzy Expert System was designed using MATLAB software and Mamdani Inference System. Finally, the fuzzy expert system was evaluated using medical records of 216 patients with and without chronic kidney disease.
Results: The main parameters for diagnosis of chronic kidney disease were 16. The accuracy, sensitivity and specificity of the system were respectively 90.74%, 87.03% and 94.44%. The surface under the roc curve was 0.90 and the kappa coefficient was 0.81, indicating a very high correlation between the system diagnosis and the final recorded diagnosis in the patient medical records.
Conclusion: Considering the desirable outcomes resulting from the implementation and evaluation of the proposed expert system, The system can be useful in diagnosis of chronic kidney disease.
Methods: At first, a strategic search was conducted in the Pubmed database for initial identification of the parameters. A questionnaire was distributed to all nephrologists in Iran University of Medical Sciences (18 physicians). Data analysis was performed using SPSS v.22, which was calculated by taking the average of the scores given to each parameter. Depending on the features selected, a set of general rules for the diagnosis of chronic kidney disease was determined by reviewing the literature, guidelines and consulting with a nephrologist. Fuzzy Expert System was designed using MATLAB software and Mamdani Inference System. Finally, the fuzzy expert system was evaluated using medical records of 216 patients with and without chronic kidney disease.
Results: The main parameters for diagnosis of chronic kidney disease were 16. The accuracy, sensitivity and specificity of the system were respectively 90.74%, 87.03% and 94.44%. The surface under the roc curve was 0.90 and the kappa coefficient was 0.81, indicating a very high correlation between the system diagnosis and the final recorded diagnosis in the patient medical records.
Conclusion: Considering the desirable outcomes resulting from the implementation and evaluation of the proposed expert system, The system can be useful in diagnosis of chronic kidney disease.
Type of Study: Research |
Subject:
Nephrology
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
