Big data analytics on artificial intelligence technologies for cardiovascular risk stratification

• Project/Area Number: 20H03681
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Review Section: Basic Section 53020:Cardiology-related
• Research Institution: Tohoku University
• Principal Investigator: Yasuda Satoshi 東北大学, 医学系研究科, 教授 (00431578)
• Co-Investigator(Kenkyū-buntansha): 西村 邦宏 国立研究開発法人国立循環器病研究センター, 研究所, 部長 (70397834) ; 野口 暉夫 国立研究開発法人国立循環器病研究センター, 病院, 副院長 (70505099) ; 泉 知里 国立研究開発法人国立循環器病研究センター, 病院, 部門長 (70768100)
• Project Period (FY): 2020-04-01 – 2023-03-31
• Project Status: Completed (Fiscal Year 2022)
• Budget Amount: ¥17,810,000 (Direct Cost: ¥13,700,000、Indirect Cost: ¥4,110,000); Fiscal Year 2022: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000); Fiscal Year 2021: ¥6,890,000 (Direct Cost: ¥5,300,000、Indirect Cost: ¥1,590,000); Fiscal Year 2020: ¥7,540,000 (Direct Cost: ¥5,800,000、Indirect Cost: ¥1,740,000)
• Keywords: 循環器病 / 人工知能 / 器械学習 / バイオカーマー / 予測医療 / 先制医療 / 心不全 / 機械学習 / バイオマーカー / 循環器疾患 / 予後

Outline of Research at the Start

循環器疾患は、比較的長い間身体機能が保たれるガンとは異なり、適切なタイミングで適切な介入を行わないと、ドミノ倒しのように軽快と増悪を繰り返しながら連続的に進行してしまう一連の疾患群である。加齢に伴ってリスクが増大する循環器病に対して発症前またはできるだけ早期の段階で治療的介入を行うこと、特に一人ひとりに着目して将来予想される病気を防ぐ、「個の視点」で発症・重症化を予測する診断方法が求められている。本研究では、先端的な診断技術（生体バイオマーカー）とその経験を定量化し、診断精度向上/自動化を実現する人工知能を活用した診断支援システムを開発し、先制医療への応用を目指す。

Outline of Final Research Achievements

Risk prediction for heart failure (HF) using machine learning methods (MLM) has not yet been established at practical application levels in clinical settings. This study aimed to create a new risk prediction model for HF with a minimum number of predictor variables using MLM
In the patients with HF (n = 987), CCEs occurred in 142 patients. In the testing dataset, the substantial predictive power of the MLM-risk model was obtained (AUC = 0.87). We generated the model using 15 variables. Our MLM-risk model showed superior predictive power in the prospective study compared to conventional risk models such as the Seattle Heart Failure Model (c-statistics: 0.86 vs. 0.68, p < 0.05). Notably, the model with an input variable number (n = 5) has comparable predictive power for CCE with the model (variable number = 15). This study developed and validated a model with minimized five variables to predict mortality more accurately in patients with HF, using a MLM, than the existing risk scores.

Academic Significance and Societal Importance of the Research Achievements

超高齢化社会を迎えたわが国において心筋梗塞・心不全などの循環器系疾患の克服は重要な課題の一つです。これらの疾患は一度発症すると軽快と増悪を繰り返しながら進行しQOLの低下のみならず介護・医療費の増大を招き社会全体に大きな負担増をもたらします。疾患発症前の予測・予防（簡便で精度の高いリスク予測モデル）、またハイリスク患者の早期同定（新たなバイオマーカーの応用と計測）のため人工知能を用いた新たな手法開発を行いました。

Research Products

• [Journal Article] Clinical application of artificial intelligence algorithm for prediction of one-year mortality in heart failure patients. (2023)
  • Author(s): Takahama H, Nishimura K, Ahsan B, Hamatani Y, Makino Y, Nakagawa S, Irie Y, Moriuchi K, Amano M, Okada A, Kitai T, Amaki M, Kanzaki H, Noguchi T, Kusano K, Akao M, Yasuda S, Izumi C.
  • Journal Title: Heart Vessels. Volume: Feb 20 Issue: 6 Pages: 36802023-36802023
  • DOI: 10.1007/s00380-023-02237-w
  • Peer Reviewed / Open Access
• [Journal Article] Machine learning approach to stratify complex heterogeneity of chronic heart failure: A report from the CHART‐2 study (2023)
  • Author(s): Nakano Kenji、Nochioka Kotaro、Yasuda Satoshi、Tamori Daito、Shiroto Takashi、Sato Yudai、Takaya Eichi、Miyata Satoshi、Kawakami Eiryo、Ishikawa Tetsuo、Ueda Takuya、Shimokawa Hiroaki
  • Journal Title: ESC Heart Failure Volume: Early View Issue: 3 Pages: 1-8
  • DOI: 10.1002/ehf2.14288
  • Peer Reviewed / Open Access
• [Journal Article] Age- dependent association of discharge heart-failure medications with clinical outcomes in a super-aged society. (2022)
  • Author(s): Nakai M, Iwanaga Y, Kanaoka K, Sumita Y, Nishioka Y, Myojin T, Kubo S, Okada K, Soeda T, Noda T, Sakata Y, Imamura T, Saito Y, Yasuda S, Miyamoto Y.
  • Journal Title: Biomed Pharmacother. Volume: Oct 3. Pages: 36271549-36271549
  • DOI: 10.1016/j.biopha.2022.113761
  • Peer Reviewed / Open Access
• [Journal Article] Improvements of predictive power of B-type natriuretic peptide on admission by mathematically estimating its discharge levels in hospitalised patients with acute heart failure. (2021)
  • Author(s): Anegawa E, Takahama H, Nishimura K, Onozuka D, Irie Y, Moriuchi K, Amano M, Okada A, Amaki M, Kanzaki H, Noguchi T, Kusano K, Yasuda S, Izumi C.
  • Journal Title: Open Heart. Volume: 8(1) Issue: 1 Pages: 1-6
  • DOI: 10.1136/openhrt-2021-001603
  • Peer Reviewed / Open Access
• [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
• [Journal Article] Cardiac outcomes in patients with acute coronary syndrome attributable to calcified nodule (2021)
  • Author(s): Sugane Hiroki、Kataoka Yu、Otsuka Fumiyuki、Nakaoku Yuriko、Nishimura Kunihiro、Nakano Hiroki、Murai Kota、Honda Satoshi、Hosoda Hayato、Matama Hideo、Doi Takahito、Nakashima Takahiro、Fujino Masashi、Nakao Kazuhiro、Yoneda Shuichi、Tahara Yoshio、Asaumi Yasuhide、Noguchi Teruo、Kawai Kazuya、Yasuda Satoshi
  • Journal Title: Atherosclerosis Volume: 318 Pages: 70-75
  • DOI: 10.1016/j.atherosclerosis.2020.11.005
  • Peer Reviewed / Open Access
• [Journal Article] Predicting Parameters for Successful Weaning from Veno‐Arterial Extracorporeal Membrane Oxygenation in Cardiogenic Shock (2020)
  • Author(s): Sawada Kenichiro、Kawakami Shoji、Murata Shunsuke、Nishimura Kunihiro、Tahara Yoshio、Hosoda Hayato、Nakashima Takahiro、Kataoka Yu、Asaumi Yasuhide、Noguchi Teruo、Sugimachi Masaru、Fujita Tomoyuki、Kobayashi Junjiro、Yasuda Satoshi
  • Journal Title: ESC Heart Failure Volume: 8 Issue: 1 Pages: 471-480
  • DOI: 10.1002/ehf2.13097
  • Peer Reviewed / Open Access
• [Presentation] Current status of Potentially Inappropriate Use of Madications for Hospitalized Patients with Cardiovascular DIsease; Nationwide Survey from JROAD-DPC (2023)
  • Author(s): Kazuhiro Nakano. Satoshi Yasuda
  • Organizer: The 87th Annual Ascientific Meeting of the JCS 2023
• [Presentation] How to Utilize Multi-Demensional Clinical Big Data -From Our Experience of the CHART-2 STudy and Its Omics Cohort (2023)
  • Author(s): Takashi Shiroto. Satoshi Yasuda
  • Organizer: The 87th Annual Ascientific Meeting of the JCS 2023
• [Presentation] JROAD, JAMIR: insights from Japan (2022)
  • Author(s): Yasuda S.
  • Organizer: Asian Pacific Society of Cardiology Congress 2022 (APSC2022).
  • Int'l Joint Research