Journal Article Scoping Review Epublish
PubMed: 40225559 DOI: 10.7150/thno.108552
Artificial intelligence in chronic kidney disease management: a scoping review.
Theranostics 15(10):4566-4578
Authors: Charumathi Sabanayagam, Riswana Banu, Cynthia Lim, Yih Chung Tham, Ching-Yu Cheng, Gavin Tan, Elif Ekinci, Bin Sheng, Gareth McKay, Jonathan E Shaw, Kunihiro Matsushita, Navdeep Tangri, Jason Choo, Tien Y Wong
Affiliations
- 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.
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore. Ophthalmology and Visual Science Academic Clinical Program, Duke-NUS Medical School, 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.
- Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China.
- Centre for Public Health, Queen's University Belfast, Northern Ireland, United Kingdom.
- Baker Heart and Diabetes Institute, Melbourne, Victoria, Australia.
- Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland, USA.
- Department of Medicine and Community Health Sciences, University of Manitoba, Winnipeg, Manitoba, Canada.
- School of Clinical Medicine, Beijing Tsinghua Changgung Hospital, Tsinghua Medicine, Tsinghua University, Beijing, China.
Abstract
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. 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. 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. 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.
MeSH
Kidney Diseases, Disease Management, Intelligence, Language, Nanomedicine, Communication, Kidney, Solutions, Machine Learning, Deep Learning, Patient Care, Cluster Analysis, Therapeutics, Learning, Artificial Intelligence