Artificial intelligence in chronic kidney disease management: a scoping review.

Journal: Theranostics
PMID:

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.

Authors

  • Charumathi Sabanayagam
    Singapore National Eye Centre, Singapore Eye Research Institute, Singapore, Singapore.
  • Riswana Banu
    Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.
  • Cynthia Lim
    Singapore General Hospital, Singapore.
  • Yih Chung Tham
    Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore. thamyc@nus.edu.sg.
  • Ching-Yu Cheng
    Singapore National Eye Centre, Singapore Eye Research Institute, Singapore, Singapore.
  • Gavin Tan
    Singapore Eye Research Institute, Singapore National Eye Center, Singapore, Singapore.
  • Elif Ekinci
    Department of Medicine, Melbourne Medical School, The University of Melbourne, Australia and Department of Endocrinology, Austin Health, Melbourne, Australia.
  • Bin Sheng
    MOE Key Laboratory of AI, School of Electronic, Information, and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China.
  • Gareth McKay
    Centre for Public Health, Queen's University Belfast, Northern Ireland, United Kingdom.
  • Jonathan E Shaw
    Department of Medicine, The University of Melbourne (Austin Health), Melbourne, Victoria, Australia.
  • Kunihiro Matsushita
    Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland, USA.
  • Navdeep Tangri
    Department of Internal Medicine, University of Manitoba, Winnipeg, MB, Canada.
  • Jason Choo
    Department of Renal Medicine, Singapore General Hospital, Singapore.
  • Tien Y Wong
    Singapore National Eye Center, Duke-NUS Medical School, National University of Singapore, Singapore, Singapore.