You are here

Article Text

Article menu
Download PDFPDF
PostScript
Correspondence
Statistics in cardiovascular medicine: there is still gold in the old
  1. Edwin R van den Heuvel1,
  2. Ramachandran S Vasan2
  1. 1Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, The Netherlands
  2. 2Department of School of Medicine, Boston University Medical Center, Boston, Massachusetts, USA
  1. Correspondence to Professor Edwin R van den Heuvel, Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven 5612 AZ, The Netherlands; e.r.v.d.heuvel{at}tue.nl

https://doi.org/10.1136/heartjnl-2018-313303

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    The authors discuss opportunities, challenges and limitations of machine learning (ML) in cardiovascular medicine1 and they classified ML as being part of artificial intelligence (AI). AI was defined as the set of analytical algorithms that can find structures or patterns in data without explicitly being programmed where to look. We fully support the quest of the authors to increase the use of algorithms in medicine, but we argue that the role of statistics as part of data science could be acknowledged and positioned better.

    Statistics has been defined in similar terms as data science,2 but due to algorithms like support vector machines and decision trees, statistics is undeniably a subset of …

    View Full Text

    Footnotes

    • Funding This work was supported by the National Heart, Lung and Blood Institute (contracts NO1-HC-25195 and HHSN268201500001I; both to RSV); Evans Scholar award and Jay and Louise Coffman endowment, Department of Medicine, Boston University School of Medicine (RSV).

    • Competing interests None declared.

    • Patient consent Not required.

    • Provenance and peer review Not commissioned; internally peer reviewed.

    Linked Articles