Artificial Intelligence in Cardiology

被引：663

作者：

Johnson, Kipp W. ^{[1
,2
]}

Soto, Jessica Torres ^{[3
,4
,5
,6
,7
]}

Glicksberg, Benjamin S. ^{[1
,2
,8
]}

Shameer, Khader ^{[9
]}

Miotto, Riccardo ^{[1
,2
]}

Ali, Mohsin ^{[1
,2
]}

Ashley, Euan ^{[3
,4
,5
,6
,7
]}

Dudley, Joel T. ^{[1
,2
]}

机构：

[1] Mt Sinai Hlth Syst, Inst Next Generat Healthcare, New York, NY 10029 USA

[2] Icahn Sch Med Mt Sinai, Dept Genet & Genom Sci, New York, NY 10029 USA

[3] Stanford Univ, Div Cardiovasc Med, Palo Alto, CA 94304 USA

[4] Stanford Univ, Dept Med, Palo Alto, CA 94304 USA

[5] Stanford Univ, Dept Genet, Palo Alto, CA 94304 USA

[6] Stanford Univ, Dept Biomed Data Sci, Palo Alto, CA 94304 USA

[7] Stanford Univ, Ctr Inherited Cardiovasc Dis, Palo Alto, CA 94304 USA

[8] Univ Calif San Francisco, Inst Computat Hlth Sci, San Francisco, CA 94143 USA

[9] Northwell Hlth, Ctr Res Informat & Innovat, Dept Informat Serv, New Hyde Pk, NY USA

来源：

JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY | 2018年 / 71卷 / 23期

基金：

美国国家卫生研究院;

关键词：

artificial intelligence; cardiology; machine learning; precision medicine; HEART-FAILURE; PRECISION MEDICINE; PREDICTION MODEL; CLASSIFICATION; PATIENT; IDENTIFICATION; REGRESSION; RISK; CARE;

D O I：

10.1016/j.jacc.2018.03.521

中图分类号：

R5 [内科学];

学科分类号：

1002 ; 100201 ;

摘要：

Artificial intelligence and machine learning are poised to influence nearly every aspect of the human condition, and cardiology is not an exception to this trend. This paper provides a guide for clinicians on relevant aspects of artificial intelligence and machine learning, reviews selected applications of these methods in cardiology to date, and identifies how cardiovascular medicine could incorporate artificial intelligence in the future. In particular, the paper first reviews predictive modeling concepts relevant to cardiology such as feature selection and frequent pitfalls such as improper dichotomization. Second, it discusses common algorithms used in supervised learning and reviews selected applications in cardiology and related disciplines. Third, it describes the advent of deep learning and related methods collectively called unsupervised learning, provides contextual examples both in general medicine and in cardiovascular medicine, and then explains how these methods could be applied to enable precision cardiology and improve patient outcomes. (C) 2018 The Authors. Published by Elsevier on behalf of the American College of Cardiology Foundation.

引用

页码：2668 / 2679

页数：12

共 53 条

[31]

Muse ED, 2017, LANCET, V389, P358, DOI 10.1016/S0140-6736(17)30154-X

[32] REPLY: Deep Learning With Unsupervised Feature in Echocardiographic Imaging [J].

Narula, Sukrit ;

Shameer, Khader ;

Omar, Alaa Mabrouk Salem ;

Dudley, Joel T. ;

Sengupta, Partho P. .

JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY, 2017, 69 (16) :2101-2102

[33] Machine-Learning Algorithms to Automate Morphological and Functional Assessments in 2D Echocardiography [J].

Narula, Sukrit ;

Shameer, Khader ;

Omar, Alaa Mabrouk Salem ;

Dudley, Joel T. ;

Sengupta, Partho P. .

JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY, 2016, 68 (21) :2287-2295

[34]

Niculescu-Mizil A., 2005, P 22 INT C MACH LEAR, P625, DOI 10.1145/1102351.1102430

[35]

ORITZ J, 1995, J AM COLL CARDIOL, V26, P1586

[36] How to develop a more accurate risk prediction model when there are few events [J].

Pavlou, Menelaos ;

Ambler, Gareth ;

Seaman, Shaun R. ;

Guttmann, Oliver ;

Elliott, Perry ;

King, Michael ;

Omar, Rumana Z. .

BMJ-BRITISH MEDICAL JOURNAL, 2015, 351

[37]

Prasad N, 2017, ARXIV E PRINTS

[38] THE PERCEPTRON - A PROBABILISTIC MODEL FOR INFORMATION-STORAGE AND ORGANIZATION IN THE BRAIN [J].

ROSENBLATT, F .

PSYCHOLOGICAL REVIEW, 1958, 65 (06) :386-408

[39]

Salem Omar AM, 2017, JACC-CARDIOVASC IMAG, pS1936

[40]

Senn S, 2005, 55 SESS INT STAT I S

← 1 2 3 4 5 6 →