A novel machine learning model for predicting the incidence of out-of-hospital cardiac arrest using weather data

• Project/Area Number: 20K17914
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 55060:Emergency medicine-related
• Research Institution: National Cardiovascular Center Research Institute
• Principal Investigator: Nakashima Takahiro 国立研究開発法人国立循環器病研究センター, 研究所, 客員研究員 (50796141)
• Project Period (FY): 2020-04-01 – 2024-03-31
• Project Status: Completed (Fiscal Year 2023)
• Budget Amount: ¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000); Fiscal Year 2021: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000); Fiscal Year 2020: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
• Keywords: 機械学習 / 予測モデル / 院外心停止 / 気象情報 / 気象データ / 人工知能

Outline of Research at the Start

本研究は、気温・降雨量・風量・大気汚染を含む気象観測データと心血管疾患の関与を明らかにし、気象情報を基にした心原性院外心停止の発症予測モデルの確立を目的とする。具体的には、総務省消防庁に登録された全国救急搬送データと米国Weather Company社の気象データにおける関連性を検証し、院外心停止発生に寄与する気象観測データ項目指標の同定を行い、さらに人工知能を用いて気象情報から心原性院外心停止の発症率を予測する。心血管疾患および心原性院外心停止発生率の予測が可能となれば、心原性院外心停止の有効な予防対策ならびに心血管疾患の予後改善、さらには医療資源の適正配置にもつながることが期待される。

Outline of Final Research Achievements

In this population-based study, we combined an out-of-hospital cardiac arrest (OHCA) nationwide registry and high-resolution meteorological and chronological datasets from Japan. We developed a model to predict daily OHCA incidence with a training dataset from 2005 to 2013 using the eXtreme Gradient Boosting algorithm. A dataset from 2014 to 2015 was used to test the predictive model.
Among the 1,299,784 OHCA cases, 661,052 OHCA cases of cardiac origin (525,374 cases in the training dataset were included in the analysis. Compared with the ML models using meteorological or chronological variables alone, the ML model with combined meteorological and chronological variables had the highest predictive accuracy in the training and testing datasets. Sunday, Monday, holiday, winter, low ambient temperature and large interday or intraday temperature difference were more strongly associated with OHCA incidence than other the meteorological and chronological variables.

Academic Significance and Societal Importance of the Research Achievements

本研究により複雑な気象条件と心停止発生との関連性を明確にできた。予測モデルの精度をさらに高めることで、将来的に①市民に対しては日々の気象条件に応じた注意喚起を行い、また②医療従事者に対しては限られた医療資源を日々の気象条件をもとに再配置するのに役立つことが期待される。

Research Products

• [Journal Article] A machine learning model for predicting out-of-hospital cardiac arrest incidence using meteorological, chronological, and geographical data from the United States (2023)
  • Author(s): Nakashima Takahiro、Ogata Soshiro、Kiyoshige Eri、Al-Hamdan Mohammad Z、Wang Yifan、Noguchi Teruo、Shields Theresa A、Al-Araji Rabab、McNally Bryan、Nishimura Kunihiro、Neumar Robert W
  • Journal Title: medRxiv Volume: preprint
  • DOI: 10.1101/2023.05.08.23289698
• [Journal Article] A machine learning model for predicting out-of-hospital cardiac arrests using meteorological and chronological data (2021)
  • Author(s): Takahiro Nakashima, Soshiro Ogata, Teruo Noguchi, Yoshio Tahara, Daisuke Onozuka, Satoshi Kato, Yoshiki Yamagata, Sunao Kojima, Taku Iwami, Tetsuya Sakamoto, Ken Nagao, Hiroshi Nonogi, Satoshi Yasuda, Koji Iihara, Robert W Neumar, and Kunihiro Nishimura
  • Journal Title: Heart Volume: - Issue: 13 Pages: 1084-1091
  • DOI: 10.1136/heartjnl-2020-318726
  • Peer Reviewed / Open Access
• [Presentation] Machine learning model for predicting out-of-hospital cardiac arrests using meteorological and chronological data (2021)
  • Author(s): Takahiro Nakashima
  • Organizer: American Heart Association Resuscitation Science Symposium 2021
  • Int'l Joint Research
• [Remarks] 機械学習を用いて気象データと暦情報から院外心停止発症リスクを高精度に予測
  • URL: https://www.ncvc.go.jp/pr/release/20210518_press/