• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Prediction and stratification of acute kidney injury with a machine learning algorithm in intensive care unit

Research Project

Project/Area Number 19K18321
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 55060:Emergency medicine-related
Research InstitutionThe University of Tokyo (2022-2023)
Kyoto University (2019-2021)

Principal Investigator

Sato Noriaki  東京大学, 医科学研究所, 助教 (90838997)

Project Period (FY) 2019-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2022: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2021: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2020: ¥390,000 (Direct Cost: ¥300,000、Indirect Cost: ¥90,000)
Fiscal Year 2019: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Keywords機械学習 / 急性腎障害 / 集中治療部 / 腎疾患 / ネットワーク解析 / 畳み込みニューラルネットワーク
Outline of Research at the Start

急性腎障害(acute kidney injury: AKI)は、急性に糸球体ろ過量の低下を示す病態である急性腎不全に加え、早期段階の腎機能低下も包括した概念であり、致死的な病態を合併する。特に集中治療部(intensive care unit: ICU)において敗血症性ショックをはじめとした様々な病態が原因になり、高頻度で発生する。事前にAKIの高リスク患者を同定し、適切に介入を行うことは臨床上重要である。本研究ではICU患者時系列データに対して、昨今発展の著しい機械学習手法を適用しAKIの発症予測、最適な介入法を同定することを目的とする。

Outline of Final Research Achievements

Acute kidney injury (AKI) occurs frequently in the intensive care unit due to a variety of conditions, including septic shock. It is clinically important to identify high-risk patients for AKI in advance and to intervene appropriately. In this study, we developed a model for real-time prediction of AKI onset and its rationale visualization using a one-dimensional convolutional neural network (CNN) and verified its accuracy. As a result, the model was able to predict the onset of AKI with high accuracy, and the basis for the prediction was clinically valid. Furthermore, we developed methods for evaluating pathological images in an unsupervised manner and quantifying uncertainty in the prediction basis in CNN.

Academic Significance and Societal Importance of the Research Achievements

集中治療部において高頻度に発症するAKIを高精度で予測し、その根拠をリアルタイムで予測する手法を開発した。このことから、例としてAKIアラートシステムへの応用といった有用性が示唆された。さらに、このようなモデルの不確実性を予測根拠に反映する手法を開発した。これは例として日常的に行われるモニタリングシステムへの導入など、医療現場への応用可能性が示唆される結果と考えられた。

Report

(6 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • 2020 Research-status Report
  • 2019 Research-status Report
  • Research Products

    (17 results)

All 2024 2023 2022 2021 2019

All Journal Article (7 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 7 results,  Open Access: 6 results) Presentation (8 results) (of which Int'l Joint Research: 5 results) Book (2 results)

  • [Journal Article] Exploring the mechanism of BK polyomavirus-associated nephropathy through consensus gene network approach2023

    • Author(s)
      Sato Noriaki、Mori Keita P.、Sakai Kaoru、Miyata Hitomi、Yamamoto Shinya、Kobayashi Takashi、Haga Hironori、Yanagita Motoko、Okuno Yasushi
    • Journal Title

      PLOS ONE

      Volume: 18 Issue: 6 Pages: e0282534-e0282534

    • DOI

      10.1371/journal.pone.0282534

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] ggkegg: analysis and visualization of KEGG data utilizing the grammar of graphics.2023

    • Author(s)
      Sato N, Uematsu M, Fujimoto K, Uematsu S, Imoto S.
    • Journal Title

      Bioinformatics

      Volume: 39 Issue: 10

    • DOI

      10.1093/bioinformatics/btad622

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Preemptive Intravenous Human Immunoglobulin G Suppresses BK Polyomavirus Replication and Spread of Infection In Vitro2023

    • Author(s)
      Sato Noriaki、Shiraki Atsuko、Mori Keita P.、Sakai Kaoru、Takemura Yoshinori、Yanagita Motoko、Imoto Seiya、Tanabe Kazunari、Shiraki Kimiyasu
    • Journal Title

      American Journal of Transplantation

      Volume: - Issue: 5 Pages: 862-866

    • DOI

      10.1016/j.ajt.2023.11.007

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] CBNplot: Bayesian network plots for enrichment analysis2022

    • Author(s)
      Sato Noriaki、Tamada Yoshinori、Yu Guangchuang、Okuno Yasushi
    • Journal Title

      Bioinformatics

      Volume: 38 Issue: 10 Pages: 2959-2960

    • DOI

      10.1093/bioinformatics/btac175

    • Related Report
      2022 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Everolimus reduces BK polyomavirus infection by suppressing its replication and spread of infection2022

    • Author(s)
      Sato Noriaki、Shiraki Atsuko、Mori Keita P.、Sakai Kaoru、Tan Long、Takemura Yoshinori、Okuno Yasushi、Tanabe Kazunari、Shiraki Kimiyasu
    • Journal Title

      Antiviral Research

      Volume: 208 Pages: 105456-105456

    • DOI

      10.1016/j.antiviral.2022.105456

    • Related Report
      2022 Research-status Report
    • Peer Reviewed
  • [Journal Article] Prediction and visualization of acute kidney injury in intensive care unit using one-dimensional convolutional neural networks based on routinely collected data2021

    • Author(s)
      Sato Noriaki、Uchino Eiichiro、Kojima Ryosuke、Hiragi Shusuke、Yanagita Motoko、Okuno Yasushi
    • Journal Title

      Computer Methods and Programs in Biomedicine

      Volume: 206 Pages: 106129-106129

    • DOI

      10.1016/j.cmpb.2021.106129

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Evaluation of Kidney Histological Images Using Unsupervised Deep Learning2021

    • Author(s)
      Sato Noriaki、Uchino Eiichiro、Kojima Ryosuke、Sakuragi Minoru、Hiragi Shusuke、Minamiguchi Sachiko、Haga Hironori、Yokoi Hideki、Yanagita Motoko、Okuno Yasushi
    • Journal Title

      Kidney International Reports

      Volume: 6 Issue: 9 Pages: 2445-2454

    • DOI

      10.1016/j.ekir.2021.06.008

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] Classifying electrocardiogram with uncertainty-aware explanation2024

    • Author(s)
      Sato Noriaki、Kojima Ryosuke、Kohjitani Hirohiko、Ueda Akihiko、Shiraki Atsuko、Okuno Yasushi、Imoto Seiya
    • Organizer
      The 3rd Joint Scientific Congress of TSCCM, TSECCM and JSICM
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Analysis of the alleviation of BK polyomavirus infection by everolimus in vitro2022

    • Author(s)
      Sato Noriaki、Shiraki Atsuko、Mori Keita P.、Sakai Kaoru、Tan Long、Takemura Yoshinori、Okuno Yasushi、Tanabe Kazunari、Shiraki Kimiyasu
    • Organizer
      Transplantation Science Symposium Asian Regional Meeting 2022
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research
  • [Presentation] wcGeneSummary: Text Mining And Annotating Gene Cluster2022

    • Author(s)
      Sato Noriaki
    • Organizer
      Bioconductor conference 2022
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research
  • [Presentation] 教師なし深層学習を用いたIgA腎症患者の病理所見の評価2021

    • Author(s)
      佐藤憲明、内野詠一郎、小島諒介、櫻木実、平木秀輔、南口早智子、羽賀博典、横井秀基、柳田素子、奥野恭史
    • Organizer
      第64回日本腎臓学会(発表確定)
    • Related Report
      2020 Research-status Report
  • [Presentation] 機械学習による急性腎障害(AKI)発症予測ツールの構築と臨床的有用性の後方視的検証2021

    • Author(s)
      内野詠一郎、櫻木実、佐藤憲明、奥野恭史、柳田素子
    • Organizer
      第64回日本腎臓学会(発表確定)
    • Related Report
      2020 Research-status Report
  • [Presentation] 免疫チェックポイント阻害薬投与患者における急性腎障害発症予測モデルの構築と検証2021

    • Author(s)
      櫻木実、内野詠一郎、佐藤憲明、奥野恭史、柳田素子
    • Organizer
      第64回日本腎臓学会(発表確定)
    • Related Report
      2020 Research-status Report
  • [Presentation] Prediction of AKI in ICU Using Routinely Collected Data by Machine-Learning Algorithms and Its Visualization2019

    • Author(s)
      Noriaki Sato, Eiichiro Uchino, Ryosuke Kojima, Shusuke Hiragi, Motoko Yanagita, Yasushi Okuno
    • Organizer
      Kidney Week 2019 - American Society of Nephrology
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Development of Machine Learning Models for Predicting AKI Onset Using Electronic Medical Records2019

    • Author(s)
      Eiichiro Uchino, Kazuki Kume, Kazuki Iwamoto, Tatsuo Hayakawa, Noriaki Sato, Yoshinori Tamada, Motoko Yanagita, Yasushi Okuno
    • Organizer
      Kidney Week 2019 - American Society of Nephrology
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Book] Artificial Intelligence in Kidney Pathology2021

    • Author(s)
      Sato Noriaki, Uchino Eiichiro, Okuno Yasushi
    • Total Pages
      11
    • Publisher
      Springer International Publishing
    • ISBN
      9783030580803
    • Related Report
      2021 Research-status Report
  • [Book] Artificial Intelligence in Predicting Kidney Function and Acute Kidney Injury2021

    • Author(s)
      Uchino Eiichiro, Sato Noriaki, Okuno Yasushi
    • Total Pages
      17
    • Publisher
      Springer International Publishing
    • ISBN
      9783030580803
    • Related Report
      2021 Research-status Report

URL: 

Published: 2019-04-18   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi