From assistant to collaborator: A systematic review of the evolution of artificial intelligence in end-stage renal disease care and management
- 1College of Computer Science and Technology, Zhejiang University, Hangzhou, China
- 2Polytechnic Institute of Zhejiang University, Zhejiang University, Hangzhou, China
- 3Department of Nephrology, Henan Provincial People’s Hospital, Zhengzhou, China
Abstract
We aimed to systematically analyze the historical evolution of artificial intelligence (AI) in end-stage renal disease (ESRD) management and propose a developmental framework to map its progression from assistive tools to cognitive collaborators. A systematic review was conducted following PRISMA 2020 guidelines, identifying 100 eligible studies from PubMed, IEEE Xplore, and Web of Science. A three-stage analytical framework was applied to chart the technological evolution of AI in ESRD care: (1) rule-based assistive tools, (2) data-driven learning systems, and (3) emerging large language model- and agent-based cognitive systems. A total of 100 studies were included, all focusing on patients with end-stage renal disease managed through hemodialysis, peritoneal dialysis, or kidney transplantation. Three primary application domains were identified: risk prediction (49.0%), diagnostic support (25.0%), and monitoring and management (26.0%). The analytical framework revealed a developmental progression from interpretable rule-based systems (Stage 1) to high-performing data-driven models (Stage 2), which achieve clinically relevant metrics (e.g., area under the receiver operating characteristic curve [AUC] 0.80–0.90) but often lack external validation. Emerging large language model- and agent-based systems (Stage 3) demonstrate notable versatility but introduce new challenges related to reliability, factual accuracy, and safety alignment. The proposed three-stage framework clarifies AI’s technological and functional evolution in ESRD care. This perspective highlights a critical need to bridge the gap between high-performance modeling and validated clinical utility. Future work should focus on robust external validation and the development of frameworks for the safe, reliable, and ethical deployment of next-generation cognitive AI agents. Author summary: People whose kidneys have failed completely depend on dialysis or a kidney transplant for the rest of their lives, and their care generates a constant stream of test results, treatment settings and monitoring data that clinical teams cannot realistically take in as a whole. Over the past two decades researchers have built computer systems to help. We read and analyzed one hundred studies published between 2005 and 2025 to trace how those systems have changed. We found three successive generations: early tools that simply followed rules written down by doctors; a much larger group of systems that learn patterns directly from patient records and now perform well in testing; and a small but rapidly growing group built on the technology behind conversational chatbots, which can handle a far wider range of tasks. We also found that very few of these systems have been tested in hospitals other than the one where they were built, and that none has yet been evaluated while actually guiding care. Our work suggests that the central challenge in this field is no longer building accurate systems, but showing that they help patients safely in everyday practice.
Related
- Early Detection of Red Palm Weevil Infestation: A Systematic Review of Sensing Technologies, Artificial Intelligence, and Field Readiness
- Beyond Algorithmic Accuracy: Field Readiness, Ecological Intelligence and Real-World Validation of Artificial Intelligence for Insect Pest Management.
- Remote sensing and artificial intelligence for crop pest and disease monitoring: A systematic review of sensing technologies, AI approaches, and barriers to field adoption
- Artificial intelligence for detecting autism spectrum disorder: a systematic review and meta-analysis
- Transparency, accountability, and scholarly integrity: A systematic narrative review of artificial intelligence governance frameworks in healthcare publication
BibTeX
@article{wang2026from,
title = {{From assistant to collaborator: A systematic review of the evolution of artificial intelligence in end-stage renal disease care and management}},
author = {Mohan Wang and Caogen Hong and Zhengxing Huang and Fengmin Shao and Yue Gu},
journal = {PLOS Digital Health},
year = {2026},
month = sep,
doi = {10.1371/journal.pdig.0001635},
url = {https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001635},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - From assistant to collaborator: A systematic review of the evolution of artificial intelligence in end-stage renal disease care and management
AU - Mohan Wang
AU - Caogen Hong
AU - Zhengxing Huang
AU - Fengmin Shao
AU - Yue Gu
PY - 2026
DA - 2026/09/02
JO - PLOS Digital Health
DO - 10.1371/journal.pdig.0001635
UR - https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001635
AB - We aimed to systematically analyze the historical evolution of artificial intelligence (AI) in end-stage renal disease (ESRD) management and propose a developmental framework to map its progression from assistive tools to cognitive collaborators. A systematic review was conducted following PRISMA 2020 guidelines, identifying 100 eligible studies from PubMed, IEEE Xplore, and Web of Science. A three-stage analytical framework was applied to chart the technological evolution of AI in ESRD care: (1) rule-based assistive tools, (2) data-driven learning systems, and (3) emerging large language model- and agent-based cognitive systems. A total of 100 studies were included, all focusing on patients with end-stage renal disease managed through hemodialysis, peritoneal dialysis, or kidney transplantation. Three primary application domains were identified: risk prediction (49.0%), diagnostic support (25.0%), and monitoring and management (26.0%). The analytical framework revealed a developmental progression from interpretable rule-based systems (Stage 1) to high-performing data-driven models (Stage 2), which achieve clinically relevant metrics (e.g., area under the receiver operating characteristic curve [AUC] 0.80–0.90) but often lack external validation. Emerging large language model- and agent-based systems (Stage 3) demonstrate notable versatility but introduce new challenges related to reliability, factual accuracy, and safety alignment. The proposed three-stage framework clarifies AI’s technological and functional evolution in ESRD care. This perspective highlights a critical need to bridge the gap between high-performance modeling and validated clinical utility. Future work should focus on robust external validation and the development of frameworks for the safe, reliable, and ethical deployment of next-generation cognitive AI agents. Author summary: People whose kidneys have failed completely depend on dialysis or a kidney transplant for the rest of their lives, and their care generates a constant stream of test results, treatment settings and monitoring data that clinical teams cannot realistically take in as a whole. Over the past two decades researchers have built computer systems to help. We read and analyzed one hundred studies published between 2005 and 2025 to trace how those systems have changed. We found three successive generations: early tools that simply followed rules written down by doctors; a much larger group of systems that learn patterns directly from patient records and now perform well in testing; and a small but rapidly growing group built on the technology behind conversational chatbots, which can handle a far wider range of tasks. We also found that very few of these systems have been tested in hospitals other than the one where they were built, and that none has yet been evaluated while actually guiding care. Our work suggests that the central challenge in this field is no longer building accurate systems, but showing that they help patients safely in everyday practice.
SN - 2767-3170
ER -