Critical appraisal of artificial intelligence-based prediction models for cardiovascular disease

被引:87
作者
van Smeden, Maarten [1 ]
Heinze, Georg [2 ]
Van Calster, Ben [3 ,4 ,5 ]
Asselbergs, Folkert W. [6 ,7 ,8 ,9 ]
Vardas, Panos E. [10 ,11 ]
Bruining, Nico [12 ]
de Jaegere, Peter [12 ]
Moore, Jason H. [13 ]
Denaxas, Spiros [8 ,9 ,14 ]
Boulesteix, Anne-Laure [15 ]
Moons, Karel G. M. [1 ]
机构
[1] Univ Utrecht, Univ Med Ctr Utrecht, Julius Ctr Hlth Sci & Primary Care, Univ Weg 100, NL-3584 CG Utrecht, Netherlands
[2] Med Univ Vienna, Sect Clin Biometr, Ctr Med Stat Informat & Intelligent Syst, Vienna, Austria
[3] Katholieke Univ Leuven, Dept Dev & Regenerat, Leuven, Belgium
[4] Katholieke Univ Leuven, EPI Ctr, Leuven, Belgium
[5] Leiden Univ, Dept Biomed Data Sci, Med Ctr, Leiden, Netherlands
[6] Univ Utrecht, Univ Med Ctr Utrecht, Div Heart & Lungs, Dept Cardiol, Utrecht, Netherlands
[7] UCL, Inst Cardiovasc Sci, Fac Populat Hlth Sci, London, England
[8] UCL, Hlth Data Res UK, London, England
[9] UCL, Inst Hlth Informat, London, England
[10] Herakl Univ Hosp, Dept Cardiol, Iraklion, Greece
[11] Hygeia Hosp Grp, Heart Sect, Athens, Greece
[12] Erasmus MC, Thorax Ctr, Dept Cardiol, Rotterdam, Netherlands
[13] Cedars Sinai Med Ctr, Dept Computat Biomed, Los Angeles, CA 90048 USA
[14] Alan Turing Inst, London, England
[15] Ludwig Maximilians Univ Munchen, Inst Med Informat Proc Biometry & Epidemiol, Munich, Germany
基金
美国国家卫生研究院;
关键词
Digital health; Artificial intelligence; Machine learning; Diagnosis; Prognosis; Prediction; RISK; PERFORMANCE; VALIDATION; DIAGNOSIS; HEALTH; IMPACT; CARE;
D O I
10.1093/eurheartj/ehac238
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
The medical field has seen a rapid increase in the development of artificial intelligence (AI)-based prediction models. With the introduction of such AI-based prediction model tools and software in cardiovascular patient care, the cardiovascular researcher and healthcare professional are challenged to understand the opportunities as well as the limitations of the AI-based predictions. In this article, we present 12 critical questions for cardiovascular health professionals to ask when confronted with an AI-based prediction model. We aim to support medical professionals to distinguish the AI-based prediction models that can add value to patient care from the AI that does not.
引用
收藏
页码:2921 / 2930
页数:10
相关论文
共 78 条
[61]   Assessing the Performance of Prediction Models A Framework for Traditional and Novel Measures [J].
Steyerberg, Ewout W. ;
Vickers, Andrew J. ;
Cook, Nancy R. ;
Gerds, Thomas ;
Gonen, Mithat ;
Obuchowski, Nancy ;
Pencina, Michael J. ;
Kattan, Michael W. .
EPIDEMIOLOGY, 2010, 21 (01) :128-138
[62]   Machine learning-based mortality prediction of patients undergoing cardiac resynchronization therapy: the SEMMELWEIS-CRT score [J].
Tokodi, Marton ;
Schwertner, Walter Richard ;
Kovacs, Attila ;
Toser, Zoltan ;
Staub, Levente ;
Sarkany, Andras ;
Lakatos, Balint Karoly ;
Behon, Anett ;
Boros, Andras Mihaly ;
Perge, Peter ;
Kutyifa, Valentina ;
Szeplaki, Gabor ;
Geller, Laszlo ;
Merkely, Bela ;
Kosztin, Annamaria .
EUROPEAN HEART JOURNAL, 2020, 41 (18) :1747-1756
[63]   High-performance medicine: the convergence of human and artificial intelligence [J].
Topol, Eric J. .
NATURE MEDICINE, 2019, 25 (01) :44-56
[64]   Calibration: the Achilles heel of predictive analytics [J].
van Calster, Ben ;
McLernon, David J. ;
van Smeden, Maarten ;
Wynants, Laure ;
Steyerberg, Ewout W. .
BMC MEDICINE, 2019, 17 (01)
[65]   Predictive analytics in health care: how can we know it works? [J].
Van Calster, Ben ;
Wynants, Laure ;
Timmerman, Dirk ;
Steyerberg, Ewout W. ;
Collins, Gary S. .
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2019, 26 (12) :1651-1654
[66]   Calibration of Risk Prediction Models: Impact on Decision-Analytic Performance [J].
Van Calster, Ben ;
Vickers, Andrew J. .
MEDICAL DECISION MAKING, 2015, 35 (02) :162-169
[67]   Clinical prediction models: diagnosis versus prognosis [J].
van Smeden, Maarten ;
Reitsma, Johannes B. ;
Riley, Richard D. ;
Collins, Gary S. ;
Moons, Karel G. M. .
JOURNAL OF CLINICAL EPIDEMIOLOGY, 2021, 132 :142-145
[68]   Sample size for binary logistic prediction models: Beyond events per variable criteria [J].
van Smeden, Maarten ;
Moons, Karel G. M. ;
de Groot, Joris A. H. ;
Collins, Gary S. ;
Altman, Douglas G. ;
Eijkemans, Marinus J. C. ;
Reitsma, Johannes B. .
STATISTICAL METHODS IN MEDICAL RESEARCH, 2019, 28 (08) :2455-2474
[69]   Machine Learning Compared With Pathologist Assessment [J].
van Smeden, Maarten ;
van Calster, Ben ;
Groenwold, Rolf H. H. .
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2018, 319 (16) :1725-1726
[70]   A simple, step-by-step guide to interpreting decision curve analysis [J].
Andrew J. Vickers ;
Ben van Calster ;
Ewout W. Steyerberg .
Diagnostic and Prognostic Research, 3 (1)