人工知能AIが拓く循環器医療の未来

1)

2)

3)

4)

5)

6)

7)

8)

9)

10)

11)

12)

13)

Choi E, Schuetz A, Stewart WF and Sun J : Using recurrent neural network models for early detection of heart

failure onset. J Am Med Informatics Assoc. 24 : 361-370, 2017.

Ide T, Kaku H, Matsushima S, Tohyama T, Enzan N, Funakoshi K, Sumita Y, Nakai M, Nishimura K,

Miyamoto Y, Tsuchihashi-Makaya M, Hatano M, Komuro I and Tsutsui H : JROADHF Investigators. Clinical

Characteristics and Outcomes of Hospitalized Patients With Heart Failure From the Large-Scale Japanese

Registry Of Acute Decompensated Heart Failure (JROADHF). Circ J. 85 : 1438-1450, 2021.

Tohyama T, Ide T, Ikeda M, Kaku H, Enzan N, Matsushima S, Funakoshi K, Kishimoto J, Todaka K and

Tsutsui H : Machine learning-based model for predicting 1 year mortality of hospitalized patients with heart

failure. ESC Heart Fail. 8 : 4077-4085, 2021.

Bazoukis G, Stavrakis S, Zhou J, Bollepalli SC, Tse G, Zhang Q, Singh JP and Armoundas AA : Machine

learning versus conventional clinical methods in guiding management of heart failure patients̶a systematic

review. Heart Fail Rev. 26 : 23-34, 2021.

Koshy AN, Hamilton G, Theuerle J, Teh AW, Han H-C, Gow PJ, Lim HS, Thijs V and Farouque O :

Postoperative atrial fibrillation following noncardiac surgery increases risk of stroke. Am J Med. 133 :

311-322. e5, 2020.

Hravnak M, Hoffman LA, Saul MI, Zullo TG and Whitman GR : Resource utilization related to atrial fibrillation

after coronary artery bypass grafting. Am J Crit Care. 11 : 228-238, 2022.

Tohyama T, Ide T, Ikeda M, Nagata T, Tagawa K, Hirose M, Funakoshi K, Sakamoto K, Kishimoto J, Todaka

K, Nakashima N and Tsutsui H : Deep Learning of ECG for the Prediction of Postoperative Atrial Fibrillation.

Circ Arrhythm Electrophysiol. 16 : e011579, 2023.

Barth JH, Misra S, Aakre K, Langlois MR, Watine J, Twomey PJ and Oosterhuis WP : Why are clinical

practice guidelines not followed? : The European Federation of Clinical Chemistry and Laboratory Medicine

and European Union of Medical Specialists joint working group on Guidelines. Clin Chem Lab Med. 54 :

1133-1139, 2016.

Chen Z, Cherukuri A, Das SR, Amin A, Tamil LS and Gupta G : Toward a Clinical Point of Care Tool for

Managing Heart Failure. AMIA Jt Summits Transl Sci proceedings AMIA Jt Summits Transl Sci. 2019 :

819-828, 2019.

Chen Z, Salazar E, Marple K, Das SR, Amin A, Cheeran D, Tamil LS and Gupta G : An AI-Based Heart Failure

Treatment Adviser System. IEEE J Transl Eng Heal Med. 6 : 1-10, 2018.

Taylor AI, Thomas EE, Snoswell CL, Smith AC and Caffery LJ : Does remote patient monitoring reduce acute

care use? A systematic review. BMJ Open. 2021 ; 11.

Nagatomi Y, Ide T, Higuchi T, Nezu T, Fujino T, Tohyama T, Nagata T, Higo T, Hashimoto T, Matsushima S,

Shinohara K, Yokoyama T, Eguchi A, Ogusu A, Ikeda M, Ishikawa Y, Yamashita F, Kinugawa S and Tsutsui

H : Home-based cardiac rehabilitation using information and communication technology for heart failure

patients with frailty. ESC Heart Fail. 9 : 2407-2418, 2022.

Yokota T, Fukushima A, Tsuchihashi-Makaya M, Abe T, Takada S, Furihata T, Ishimori N, Fujino T,

Kinugawa S, Ohta M, Kakinoki S, Yokota I, Endoh A, Yoshino Y and Tsutsui H : The AppCare-HF

人工知能 AI が拓く循環器医療の未来

89

randomized clinical trial : a feasibility study of a novel self-care support mobile app for individuals with

chronic heart failure. Eur Heart J Digital Health. 4 : 325-336, 2023.

14) Luštrek M, Bohanec M, Barca CC, Ciancarelli MC, Clays E, Dawodu AA, Derboven J, Smedt D De, Dovgan E,

Lampe J, Marino F, Mlakar M, Pioggia G, Puddu PE, Rodriguez JM, Schiariti M, Slapnicar G, Slegers K,

Tartarisco G. Valic J and Vodopija A : A personal health system for self-management of congestive heart

failure (HeartMan) : Development, technical evaluation, and proof-of-concept randomized controlled trial.

JMIR Med Informatics. 9 : 1-19, 2021.

15) Barrett M, Boyne J, Brandts J, Brunner-La Rocca HP, De Maesschalck L, De Wit K, Dixon L, Eurlings C,

Fitzsimons D, Golubnitschaja O, Hageman A, Heemskerk F, Hintzen A, Helms TM, Hill L, Hoedemakers T,

Marx N, McDonald K, Mertens M, Müller-Wieland, Palant A, Piesk J, Pomazanskyi A, Ramaekers J, Ruff P,

Schütt K, Shekhawat Y, Ski C, Thompson D, Tsirkin A, van der Mierden K, Watson CJ and Zippel-Schultz B :

Artificial intelligence supported patient self-care in chronic heart failure : a paradigm shift from reactive to

predictive, preventive and personalised care. EPMA J. 10 : 445-464, 2019.

（特に重要な文献については，番号をゴシック体で表記している．）

著者プロフィール

筒井 裕之（つつい ひろゆき）

国際医療福祉大学 副学長（医学部 教授・大学院 教授）．九州大学 名誉教授．医学博士

◆略歴 1982 年九州大学医学部卒業．1990 年米国サウスカロライナ医科大学留学．1994 年九州大

学医学部循環器内科助手．2000 年同講師．2004 年北海道大学大学院医学研究科循環病態

内科学教授．2008〜12 年北海道大学病院卒後臨床研修センター長（併任）．2012〜13 年北

海道大学病院病院長補佐（併任）．2013〜15 年北海道大学病院副病院長（併任）．2016〜23

年九州大学大学院医学研究院循環器内科学教授．2016 年より北海道大学産学・地域協働推

進機構客員教授．2023 年より現職．

◆研究テーマ 心血管病の基盤病態の解明と新規治療の開発をテーマとしています．質の高い高度

かつ安心の診療を基本としながら，基礎・臨床・疫学・開発研究まで幅広く研究を展開し，

そのなかで次世代を担う医師・医学研究者ならびに幅広い医療専門職の育成を目指してお

ります．

90

ほか２名

Future of Cardiovascular Medicine in Collaboration

with Artificial Intelligence

Hiroyuki TSUTSUI1)4), Takeshi TOHYAMA2)3), Tomomi IDE3)

1)

School of Medicine and Graduate School, International University of Health and Welfare

2)

Center for Advanced Medical Open Innovation, Kyushu University

3)

Department of Cardiovascular Medicine, Faculty of Medical Sciences, Kyushu University

4)

Professor Emeritus, Kyushu University

Abstract

The technological innovation of artificial intelligence (AI) in the medical field is rapidly progressing

not only in the area of diagnostic imaging, which is already in practical use, but also in a wide range of

areas such as natural language processing and medical care support. Diagnostic imaging is one of the

areas among various medical fields where the utilization of AI is most expected, however, recent

advancement in AI technology can be applied for various areas other than imaging. Such examples of

AI applications include the prediction of the prognosis of cardiovascular disease, medical support that

can propose treatment strategies, and virtual doctors that support remote management of patients.

In a super-aging society, the number of patients with heart failure and atrial fibrillation is increasing,

while the declining birthrate is leading to a serious shortage of medical professionals, making it difficult

to maintain the existing medical care system. Under these circumstances, cardiovascular medicine in

collaboration with AI can realize effective, efficient and optimal heart failure treatment for both

patients and medical staff. AI can provide a wide range of support including treatment strategies and

remote management. Technological innovation in AI has the potential to revolutionize cardiovascular

medical care, and its introduction will lead to the establishment of next-generation health care systems

useful for both patients and medical professionals.

Keywords：Cardiovascular disease, artificial intelligence, prognosis prediction, medical support,

telemedicine

...