Artificial Intelligence (AI) is transforming the healthcare field, offering innovative tools for improving the prediction, detection, and management of diseases. In nephrology, AI holds the potential to improve the diagnosis and treatment of kidney diseases, as well as the optimization of renal replacement therapies. In this review, a comprehensive analysis of recent literature works on artificial intelligence applied to nephrology is presented. Two key research areas structure this review. The first section examines AI models used to support early prediction of acute and chronic kidney disease. The second section explores artificial intelligence applications for hemodialytic therapies in renal insufficiency. Most studies reported high accuracy (e.g., accuracy ≥ 90%) in early prediction of kidney diseases, while fewer addressed therapy optimization and complication prevention, typically reporting moderate-to-high performance (e.g., accuracy ≃ 85%). Filling this gap and developing more accessible AI solutions that address all stages of kidney disease would therefore be crucial to support physicians’ decision-making and improve patient care.
Nicosia, A., Cancilla, N., Martin Guerrero, J.D., Tinnirello, I., Cipollina, A. (2025). Artificial Intelligence in Nephrology: From Early Detection to Clinical Management of Kidney Diseases. BIOENGINEERING, 12(10) [10.3390/bioengineering12101069].
Artificial Intelligence in Nephrology: From Early Detection to Clinical Management of Kidney Diseases
Nicosia A.;Cancilla N.;Tinnirello I.;Cipollina A.
2025-10-01
Abstract
Artificial Intelligence (AI) is transforming the healthcare field, offering innovative tools for improving the prediction, detection, and management of diseases. In nephrology, AI holds the potential to improve the diagnosis and treatment of kidney diseases, as well as the optimization of renal replacement therapies. In this review, a comprehensive analysis of recent literature works on artificial intelligence applied to nephrology is presented. Two key research areas structure this review. The first section examines AI models used to support early prediction of acute and chronic kidney disease. The second section explores artificial intelligence applications for hemodialytic therapies in renal insufficiency. Most studies reported high accuracy (e.g., accuracy ≥ 90%) in early prediction of kidney diseases, while fewer addressed therapy optimization and complication prevention, typically reporting moderate-to-high performance (e.g., accuracy ≃ 85%). Filling this gap and developing more accessible AI solutions that address all stages of kidney disease would therefore be crucial to support physicians’ decision-making and improve patient care.| File | Dimensione | Formato | |
|---|---|---|---|
|
Versione editoriale.pdf
accesso aperto
Descrizione: This article is an open access article distributed under the termsand conditions of the Creative Commons Attribution (CC BY)license (https://creativecommons.org/ licenses/by/4.0/).
Tipologia:
Versione Editoriale
Dimensione
5.31 MB
Formato
Adobe PDF
|
5.31 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


