Skip to main content
main-content
Top

Tip

Swipe om te navigeren naar een ander artikel

Gepubliceerd in: Netherlands Heart Journal 9/2019

Open Access 21-08-2019 | Editor's Comment

Artificial intelligence for the general cardiologist

Auteurs: J. Verjans, T. Leiner

Gepubliceerd in: Netherlands Heart Journal | Uitgave 9/2019

share
DELEN

Deel dit onderdeel of sectie (kopieer de link)

  • Optie A:
    Klik op de rechtermuisknop op de link en selecteer de optie “linkadres kopiëren”
  • Optie B:
    Deel de link per e-mail
insite
ZOEKEN
The majority of experts and opinion leaders believe that artificial intelligence (AI) is going to revolutionise many industries, including healthcare [1]. In the short term, the power and potential of AI appear most suitable for complementing human expertise. In other words, machines will help humans do a better job. Consequently, it is anticipated that AI will help with repetitive tasks, in-depth quantification and classification of findings, improved patient and disease phenotyping and, ultimately, with better outcomes for patients, physicians, hospital administrators, insurance companies and governments [2].
Despite these promises, the impact of AI in current clinical practice is still limited. However, this could change in the coming years, as illustrated by the significant increase in papers in AI, machine learning and deep learning in cardiology (Fig. 1). Moreover, multiple applications have gained Federal Drug Administration approval in recent years with significant financial support; these are directly related to daily cardiology practice, including automated interpretation of electrocardiograms, automated segmentation and diagnosis (Tab. 1). Common practice in invasive cardiology will be seriously influenced by AI, for example by predicting the outcome of interventions such as transcatheter aortic valve implantation or AI-based non-invasive estimation of the haemodynamic significance (CT fractional flow reserve) of coronary artery stenosis on CT angiography that is being developed by different companies [35].
Table 1
Federal Drug Administration approvals of artificial intelligence (AI) applications relevant for cardiology practice
Year
Company
AI application
2014
Alivecor
Detection of atrial fibrillation
2016
Lumify
Ultrasound image diagnosis
2017
Arterys
Cardiac MRI ventricle segmentation
2017
Bioflux
Detecting arrhythmias
2017
Cardiologs
ECG analysis
2018
Lepu Medical
ECG analysis
2018
Zebra Medical Vision
Automated coronary artery calcification
2018
Physiq Heart Rhythm Module
Detection of atrial fibrillation
2018
Apple
Detection of atrial fibrillation
2018
Bay Labs
Echocardiogram analysis
2019
Verily
ECG feature on Study Watch
2019
Alivecor
Six-lead smartphone ECG
2019
Zebra Medical Vision
Radiographic diagnosis
2019
Aidoc
Flagging pulmonary embolism
This focus issue of the Netherlands Heart Journal aims to help general cardiologists explore the state of the art of AI in cardiology. It also aims to increase awareness that it is likely that AI is going to influence and even disrupt daily clinical practice and healthcare in general.
The first part of the issue will focus on past, present and future evidence and gives an overview in the form of two reviews on the impact of AI in cardiology and an area of more immediate impact, cardiovascular imaging [6, 7]. In the second part of this issue, several Dutch flagship AI projects are discussed and demonstrate the potential in various areas of AI as discussed above. These efforts not only concern clinical practical problems such as cardiovascular imaging and risk assessment, but also the need for multidisciplinary collaboration [8] and dedicated data platforms to access and analyse the collected data [9, 10].
According to scientists from every decade since the 1960s, human-like AI should have been achieved within 10–20 years. However, mainly due to a lack of computational power, there have been two so-called ‘winters’ for AI around 1980 and 1993, both after a period of increased interest. But with the recent increase in computational power, smarter use of hardware and data, and new strategies such as deep learning, this appears to have changed for good. Artificial intelligence is likely to make its potential come true in the era of complex data, serving as a conduit to insight for doctors in their patient’s data, improving efficiency and reducing errors.
Let’s plan some randomised clinical trials!

Conflict of interest

J. Verjans declares that he has no competing interests. T. Leiner declares: Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: disclosed institutional grant received from Pie Medical B.V.; payments received from Bayer Healthcare and Philips Healthcare for lectures including service on speakers’ bureaus. Other relationships: disclosed that he is coinventor of U.S. patent 10 176 575; this patent is held by Utrecht University Holdings, which manages the terms of any licensing agreement.
Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://​creativecommons.​org/​licenses/​by/​4.​0/​), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
share
DELEN

Deel dit onderdeel of sectie (kopieer de link)

  • Optie A:
    Klik op de rechtermuisknop op de link en selecteer de optie “linkadres kopiëren”
  • Optie B:
    Deel de link per e-mail

Onze productaanbevelingen

Netherlands Heart Journal

Het Netherlands Heart Journal wordt uitgegeven in samenwerking met de Nederlandse Vereniging voor Cardiologie en de Nederlandse Hartstichting. Het tijdschrift is Engelstalig en wordt gratis beschikbaa ...

Literatuur
3.
go back to reference Coenen A, Kim YH, Kruk M, et al. Diagnostic accuracy of a machine-learning approach to coronary computed tomographic angiography-based fractional flow reserve: result from the MACHINE Consortium. Circ Cardiovasc Imaging. 2018;11:e7217. Jun. CrossRefPubMed Coenen A, Kim YH, Kruk M, et al. Diagnostic accuracy of a machine-learning approach to coronary computed tomographic angiography-based fractional flow reserve: result from the MACHINE Consortium. Circ Cardiovasc Imaging. 2018;11:e7217. Jun. CrossRefPubMed
4.
go back to reference Douglas PS, Pontone G, Hlatky MA, et al. Clinical outcomes of fractional flow reserve by computed tomographic angiography-guided diagnostic strategies vs. usual care in patients with suspected coronary artery disease: the prospective longitudinal trial of FFR(CT): outcome and resource impacts study. Eur Heart J. 2015;14;36:3359–67. Dec. CrossRef Douglas PS, Pontone G, Hlatky MA, et al. Clinical outcomes of fractional flow reserve by computed tomographic angiography-guided diagnostic strategies vs. usual care in patients with suspected coronary artery disease: the prospective longitudinal trial of FFR(CT): outcome and resource impacts study. Eur Heart J. 2015;14;36:3359–67. Dec. CrossRef
9.
Metagegevens
Titel
Artificial intelligence for the general cardiologist
Auteurs
J. Verjans
T. Leiner
Publicatiedatum
21-08-2019
Uitgeverij
Bohn Stafleu van Loghum
Gepubliceerd in
Netherlands Heart Journal / Uitgave 9/2019
Print ISSN: 1568-5888
Elektronisch ISSN: 1876-6250
DOI
https://doi.org/10.1007/s12471-019-01327-7