Artificial intelligence in chronic kidney disease management: a scoping review
Theranostics · 21.03.2025 · 15 (10) · 4566-4578
DOI: 10.7150/thno.108552 ↗Kurz gefasst
Scoping Review in der Zeitschrift Theranostics, erschienen am 21.03.2025. Verfasst von Charumathi Sabanayagam und 13 weiteren Autor:innen. Beteiligte Einrichtung: Singapore Eye Research Institute, Singapore National Eye Centre, Singapore. Hauptthemen laut MEDLINE: Artificial Intelligence, Renal Insufficiency, Chronic. Die Arbeit wurde bisher 46-mal zitiert (Crossref). Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Rationale
Chronic kidney disease (CKD) is a major public health problem worldwide associated with cardiovascular disease, renal failure, and mortality. To effectively address this growing burden, innovative solutions to management are urgently required. We conducted a scoping review to identify key use cases in which artificial intelligence (AI) could be leveraged for improving management of CKD. Additionally, we examined the challenges faced by AI in CKD management, proposed potential solutions to overcome these barriers.
Methods
We reviewed 41 articles published between 2014-2024 which examined various AI techniques including machine learning (ML) and deep learning (DL), unsupervised clustering, digital twin, natural language processing (NLP) and large language models (LLMs) in CKD management. We focused on four areas: early detection, risk stratification and prediction, treatment recommendations and patient care and communication.
Results
We identified 41 articles published between 2014-2024 that assessed image-based DL models for early detection (n = 6), ML models for risk stratification and prediction (n = 14) and treatment recommendations (n = 4), and NLP and LLMs for patient care and communication (n = 17). Key challenges in integrating AI models into healthcare include technical issues such as data quality and access, model accuracy, and interpretability, alongside adoption barriers like workflow integration, user training, and regulatory approval.
Conclusions
There is tremendous potential of integrating AI into clinical care of CKD patients to enable early detection, prediction, and improved patient outcomes. Collaboration among healthcare providers, researchers, regulators, and industries is crucial to developing robust protocols that ensure compliance with legal standards, while minimizing risks and maintaining patient safety.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.
- Ophthalmology and Visual Science Academic Clinical Program, Duke-NUS Medical School, Singapore.
- Saw Swee Hock School of Public Health, National University of Singapore, Singapore.
- Department of Renal Medicine, Singapore General Hospital, Singapore.
- Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore.
- Department of Medicine, Melbourne Medical School, The University of Melbourne, Australia and Department of Endocrinology, Austin Health, Melbourne, Australia.
Zitieren
APA
Sabanayagam, C., Banu, R., Lim, C., Tham, Y. C., Cheng, C. Y., Tan, G., Ekinci, E., Sheng, B., McKay, G., Shaw, J. E., Matsushita, K., Tangri, N., Choo, J., & Wong, T. Y. (2025). Artificial intelligence in chronic kidney disease management: a scoping review. Theranostics, 15(10), 4566-4578. https://doi.org/10.7150/thno.108552
Vancouver
Sabanayagam C, Banu R, Lim C, Tham YC, Cheng CY, Tan G, et al. Artificial intelligence in chronic kidney disease management: a scoping review. Theranostics. 2025;15(10):4566-4578. doi:10.7150/thno.108552
BibTeX
@article{Sabanayagam2025,
author = {Sabanayagam, Charumathi and Banu, Riswana and Lim, Cynthia and Tham, Yih Chung and Cheng, Ching-Yu and Tan, Gavin and Ekinci, Elif and Sheng, Bin and McKay, Gareth and Shaw, Jonathan E and Matsushita, Kunihiro and Tangri, Navdeep and Choo, Jason and Wong, Tien Y},
title = {Artificial intelligence in chronic kidney disease management: a scoping review},
journal = {Theranostics},
year = {2025},
volume = {15},
number = {10},
pages = {4566--4578},
doi = {10.7150/thno.108552}
}
EUVIMED