Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Editorial
. 2023 Nov-Dec:81:292-294.
doi: 10.1016/j.jelectrocard.2023.08.006. Epub 2023 Aug 15.

Explainable-by-design: Challenges, pitfalls, and opportunities for the clinical adoption of AI-enabled ECG

Salah S Al-Zaiti  1 , Raymond R Bond  2
Affiliations
Editorial

Explainable-by-design: Challenges, pitfalls, and opportunities for the clinical adoption of AI-enabled ECG

Salah S Al-Zaiti et al. J Electrocardiol. 2023 Nov-Dec.
No abstract available

PubMed Disclaimer

Conflict of interest statement

Declaration of Competing Interest None.

Figures

Fig. 1.
Fig. 1.. Reasons and benefits of explainable AI-ECG.
This figure describes the four reasons why AI-ECG models should be explainable. When model predictions are well justified, are exploited to improve performance, and are used to unravel new rules and insights, then clinicians would have the ability to control and override algorithmic decisions. This would allow clinical adoption, accountability, and auditability.
Fig. 2.
Fig. 2.. Probability density plot of a two-class classification problem.
This figure shows the density distribution of model probabilities of those with disease (red) and no disease (blue). The plot marks 4 areas of certainty distribution that should be manually annotated by visually inspecting corresponding ECGs.
See this image and copyright information in PMC

Comment on

References

    1. Kligfield P, et al. AHA/ACC/HRS SCIENTIFIC STATEMENTS: recommendations for the standardization and interpretation of the electrocardiogram part I: the electrocardiogram and its technology. A Scientific statement from the American Heart Association electrocardiography and arrhythmias committee, council on clinical cardiology; the American College of Cardiology Foundation; and the Heart Rhythm Society endorsed by the International Society for Computerized Electrocardiology. J Am Coll Cardiol 2007;49(10):1110 (1129). - PubMed
    1. Al-Zaiti SS, et al. A clinician’s guide to understanding and critically appraising machine learning studies: a checklist for ruling out Bias using standard tools in machine learning (ROBUST-ML). Eur Heart J Digital Health 2022;3(2):125–40. - PMC - PubMed
    1. Siontis KC, et al. Saliency maps provide insights into artificial intelligence-based electrocardiography models for detecting hypertrophic cardiomyopathy. J Electrocardiol 2023. - PubMed
    1. Tarakji KG, et al. Digital health and the Care of the Patient with Arrhythmia. Circ Arrhythm Electrophysiol 2020;13(11):e007953. - PubMed
    1. Adadi A, Berrada M. Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 2018;6:52138–60.

LinkOut - more resources