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

Innovative Ventilator Weaning Strategy Utilizing Artificial Intelligence and Intensive Care Patient Information Systems

Research Project

Project/Area Number 20K17876
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 55060:Emergency medicine-related
Research InstitutionNippon Medical School

Principal Investigator

Igarashi Yutaka  日本医科大学, 医学部, 講師 (50771101)

Project Period (FY) 2020-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2022: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2021: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2020: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Keywords人工知能 / 人工呼吸器 / 集中治療 / 抜管 / 機械学習 / 人工呼吸器離脱
Outline of Research at the Start

人工呼吸器から離脱、抜管に失敗すると死亡率が約5倍上昇することが知られており、抜管
の失敗率を減少させるため、様々な人工呼吸器離脱に関するプロトコルの研究が行われてき
た。多くのプロトコルは、人工呼吸器をある一定の設定とし、バイタルサインや動脈血液ガ
ス所見などから抜管の判断を行っているが、抜管の失敗率は10-15%と未だに高い。そのため、プロトコルに代わる方法として、人工知能(AI)による抜管の判定に着目した。AIを用いた抜管の判定は、人工呼吸管理中に保存されたあらゆる診療データを用いて行うため、抜管前の一時点から判断するプロトコルとは全く異なる手法であり、より精度の高い予測モデルとなりうる。

Outline of Final Research Achievements

Our study aimed at reducing extubation failures and minimizing the duration of mechanical ventilation through AI, and was conducted in the following three phases: (1) Exploration: Using data extracted from the Intensive Care Patient Information System, we assessed the feasibility of predicting the success or failure of extubation. If predictable, we evaluated the significance of various features and their medical validity. (2) Accuracy Improvement: We investigated whether the accuracy of AI predictions for extubation success or failure could be enhanced in comparison with previous studies. (3) Implementation: We examined the possibility of real-time predictions via AI, with an eye toward clinical research implementation.
As a result of these efforts, we have published one original research paper and one review paper in English.

Academic Significance and Societal Importance of the Research Achievements

患者背景、バイタルサイン、検査データ、人工呼吸器のデータなど、57の特徴に関する情報を抽出し、人工呼吸管理が必要であるか否かのラベルを付け、3つの学習アルゴリズムを用いて、抜管の予測モデルを作成した。また、精度を向上させるべく、不確実性を考慮したニューラルネットワークモデルを作成した。最後に入院中の患者データを利用して予測ができるよう実装を行った。

Report

(4 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Research-status Report
  • 2020 Research-status Report
  • Research Products

    (3 results)

All 2022 2021

All Journal Article (3 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 3 results,  Open Access: 3 results)

  • [Journal Article] Machine Learning Prediction for Supplemental Oxygen Requirement in Patients with COVID-192022

    • Author(s)
      Igarashi Yutaka、Nishimura Kan、Ogawa Kei、Miyake Nodoka、Mizobuchi Taiki、Shigeta Kenta、Obinata Hirofumi、Takayama Yasuhiro、Tagami Takashi、Seike Masahiro、Ohwada Hayato、Yokobori Shoji
    • Journal Title

      Journal of Nippon Medical School

      Volume: 89 Issue: 2 Pages: 161-168

    • DOI

      10.1272/jnms.JNMS.2022_89-210

    • NAID

      130008087910

    • ISSN
      1345-4676, 1347-3409
    • Year and Date
      2022-04-25
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Machine learning for predicting successful extubation in patients receiving mechanical ventilation2022

    • Author(s)
      Igarashi Yutaka、Ogawa Kei、Nishimura Kan、Osawa Shuichiro、Ohwada Hayato、Yokobori Shoji
    • Journal Title

      Frontiers in Medicine

      Volume: 9

    • DOI

      10.3389/fmed.2022.961252

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Machine Learning for Prediction of Successful Extubation of Mechanical Ventilated Patients in an Intensive Care Unit: A Retrospective Observational Study2021

    • Author(s)
      Takanobu Otaguro, Hidenori Tanaka, Yutaka Igarashi, Takashi Tagami, Tomohiko Masuno, Shoji Yokobori, Hisashi Matsumoto, Hayato Ohwada, Hiroyuki Yokota
    • Journal Title

      Journal of Nippon Medical School

      Volume: 88 Issue: 5 Pages: 408-417

    • DOI

      10.1272/jnms.JNMS.2021_88-508

    • NAID

      130008117319

    • ISSN
      1345-4676, 1347-3409
    • Year and Date
      2021-10-25
    • Related Report
      2021 Research-status Report 2020 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research

URL: 

Published: 2020-04-28   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi