Summer 2025 (Article In Press)
Back to the articles list |
Back to browse issues page
Ahmad Mousavi Nasab1 
, Amin Golabpour *2 , Kamal Mirzaie3 , Ahmad Khosravi4 , Mahin Ghorban Sabbagh5
, Amin Golabpour *2 , Kamal Mirzaie3 , Ahmad Khosravi4 , Mahin Ghorban Sabbagh5
1- PhD Student in Computer Engineering, Department of Computer Engineering, Maybod Branch, Islamic Azad University, Maybod, Iran
2- Assistant Professor of Medical Informatics, Department of Health Information Technology, School of Allied Medical Sciences, Shahroud University of Medical Sciences, Shahroud, Iran ,a.golabpour@shmu.ac.ir
3- Assistant Professor of Computer Engineering, Department of Computer Engineering, Maybod Branch, Islamic Azad University, Maybod, Iran
4- Associate Professor of Epidemiology, Department of Epidemiology School of Public Health, Shahroud University of Medical Sciences, Shahroud, Iran
5- Associate Professor of Nephrology, Department of Internal Medicine, School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran
2- Assistant Professor of Medical Informatics, Department of Health Information Technology, School of Allied Medical Sciences, Shahroud University of Medical Sciences, Shahroud, Iran ,
3- Assistant Professor of Computer Engineering, Department of Computer Engineering, Maybod Branch, Islamic Azad University, Maybod, Iran
4- Associate Professor of Epidemiology, Department of Epidemiology School of Public Health, Shahroud University of Medical Sciences, Shahroud, Iran
5- Associate Professor of Nephrology, Department of Internal Medicine, School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran
Abstract: (239 Views)
Introduction: Kidney transplant survival duration is one of the most crucial factors in deciding whether to proceed with a kidney transplant. Given its capabilities, artificial intelligence (AI) could be a suitable method for the prediction of kidney transplant survival duration. The present review aimed to evaluate the performance and effectiveness of AI in this field.
Method: In a systematic review study, all articles related to AI in the prediction of survival duration for kidney patients were extracted from PubMed, Scopus, and Web of Science (WOS) databases using a combination of relevant keywords. These articles were analyzed based on sample size, type of algorithm, and evaluation parameters. Then, the evaluation parameters of the articles were compared, and the number of articles using white-box algorithms was identified to determine AI's effectiveness in predicting kidney transplant survival.
Results: A total of 21 articles were included in this systematic review. Approximately 45% of these articles addressed the issue using artificial neural networks and ensemble classification algorithms, while around 35% designed prediction models using regression methods. Regression methods demonstrated lower accuracy than other methods, while ensemble classification algorithms performed better, achieving sensitivity and specificity above 90%. In addition, approximately 20% of the articles used white-box methods.
Conclusion: The present study indicated that the application of AI in kidney transplants is growing and has significantly better performance compared to statistical methods. However, further studies are needed, particularly with an emphasis on white-box algorithms and optimizing algorithm parameters in this field.
Method: In a systematic review study, all articles related to AI in the prediction of survival duration for kidney patients were extracted from PubMed, Scopus, and Web of Science (WOS) databases using a combination of relevant keywords. These articles were analyzed based on sample size, type of algorithm, and evaluation parameters. Then, the evaluation parameters of the articles were compared, and the number of articles using white-box algorithms was identified to determine AI's effectiveness in predicting kidney transplant survival.
Results: A total of 21 articles were included in this systematic review. Approximately 45% of these articles addressed the issue using artificial neural networks and ensemble classification algorithms, while around 35% designed prediction models using regression methods. Regression methods demonstrated lower accuracy than other methods, while ensemble classification algorithms performed better, achieving sensitivity and specificity above 90%. In addition, approximately 20% of the articles used white-box methods.
Conclusion: The present study indicated that the application of AI in kidney transplants is growing and has significantly better performance compared to statistical methods. However, further studies are needed, particularly with an emphasis on white-box algorithms and optimizing algorithm parameters in this field.
Keywords: Artificial intelligence, Kidney transplant, Machine learning, Prediction, Survival duration
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
