﻿<?xml version="1.0" encoding="UTF-8"?>
<ArticleSet>
  <Article>
    <Journal>
      <PublisherName>Society of Diabetic Nephropathy Prevention</PublisherName>
      <JournalTitle>Journal of Nephropharmacology</JournalTitle>
      <Issn>2345-4202</Issn>
      <Volume>15</Volume>
      <Issue>1</Issue>
      <PubDate PubStatus="ppublish">
        <Year>2026</Year>
        <Month>01</Month>
        <DAY>01</DAY>
      </PubDate>
    </Journal>
    <ArticleTitle>AI-driven innovations in intensive care nephrology; bridging intensive care and kidney diseases</ArticleTitle>
    <FirstPage>e12820</FirstPage>
    <LastPage>e12820</LastPage>
    <ELocationID EIdType="doi">10.34172/npj.2025.12820</ELocationID>
    <Language>EN</Language>
    <AuthorList>
      <Author>
        <FirstName>Malihe</FirstName>
        <LastName>Abniki</LastName>
        <Identifier Source="ORCID">https://orcid.org/0009-0006-3318-5111</Identifier>
      </Author>
      <Author>
        <FirstName>Mahdi</FirstName>
        <LastName>Amirdosara</LastName>
        <Identifier Source="ORCID">https://orcid.org/0000-0001-6865-4543</Identifier>
      </Author>
      <Author>
        <FirstName>Masood</FirstName>
        <LastName>Zangi</LastName>
        <Identifier Source="ORCID">https://orcid.org/0000-0001-9860-925X</Identifier>
      </Author>
    </AuthorList>
    <PublicationType>Journal Article</PublicationType>
    <ArticleIdList>
      <ArticleId IdType="doi">10.34172/npj.2025.12820</ArticleId>
    </ArticleIdList>
    <History>
      <PubDate PubStatus="received">
        <Year>2025</Year>
        <Month>10</Month>
        <Day>07</Day>
      </PubDate>
      <PubDate PubStatus="accepted">
        <Year>2025</Year>
        <Month>11</Month>
        <Day>26</Day>
      </PubDate>
    </History>
    <Abstract>This narrative review explores the transformative role of artificial intelligence (AI) in critical care nephrology, focusing on the early detection, risk prediction, and management of acute kidney injury (AKI) and the optimization of renal replacement therapies in intensive care settings. Drawing from recent valid-indexed studies, the review highlights AI’s ability to enhance clinical decision-making through advanced machine learning models that predict AKI onset hours to days before traditional biomarkers indicate injury. The integration of explainable AI frameworks improves clinician trust and fosters personalized treatment strategies. Additionally, AI applications in continuous renal replacement therapy (CRRT) facilitate individualized dosing and timing, reducing complications and supporting better outcomes. Challenges in data quality, ethical considerations, and clinical implementation are discussed, alongside future directions such as multi-modal data integration and adaptive learning systems. The review underscores AI’s potential to bridge intensive care and nephrology, ultimately aiming to improve patient prognosis in critically ill populations.</Abstract>
    <ObjectList>
      <Object Type="keyword">
        <Param Name="value">Artificial intelligence</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">Machine learning</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">Machine learning</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">Critical care</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">Intensive care unit</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">ICU</Param>
      </Object>
    </ObjectList>
  </Article>
</ArticleSet>