EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Crowdsourced AI Framework for Atrial Fibrillation Detection in Apple Watch and Kardia Mobile ECGs

Ali Bahrami Rad iD, Miguel Kirsch, Qiao Li, Joel Xue, Reza Sameni iD, Dave Albert, Gari D Clifford iD

Sensors · 2024

DOI: 10.3390/s24175708 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Ali Bahrami Rad und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics, Emory University, Atlanta, GA 30322, USA. Hauptthemen laut MEDLINE: Atrial Fibrillation, Algorithms, Crowdsourcing, Electrocardiography. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIBIB NIH HHS, AliveCor, NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Atrial fibrillation (AFib) detection via mobile ECG devices is promising, but algorithms often struggle to generalize across diverse datasets and platforms, limiting their real-world applicability.

Objective

This study aims to develop a robust, generalizable AFib detection approach for mobile ECG devices using crowdsourced algorithms.

Methods

We developed a voting algorithm using random forest, integrating six open-source AFib detection algorithms from the PhysioNet Challenge. The algorithm was trained on an AliveCor dataset and tested on two disjoint AliveCor datasets and one Apple Watch dataset.

Results

The voting algorithm outperformed the base algorithms across all metrics: the average of sensitivity (0.884), specificity (0.988), PPV (0.917), NPV (0.985), and F1-score (0.943) on all datasets. It also demonstrated the least variability among datasets, signifying its highest robustness and effectiveness in diverse data environments. Moreover, it surpassed Apple’s algorithm on all metrics and showed higher specificity but lower sensitivity than AliveCor’s Kardia algorithm.

Conclusions

This study demonstrates the potential of crowdsourced, multi-algorithmic strategies in enhancing AFib detection. Our approach shows robust cross-platform performance, addressing key generalization challenges in AI-enabled cardiac monitoring and underlining the potential for collaborative algorithms in wearable monitoring devices.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Atrial FibrillationAlgorithmsCrowdsourcingElectrocardiographyHumansWearable Electronic Devices

Stichwörter der Autor:innen

AIatrial fibrillationcomposite error–variability indexcross-dataset generalizationcrowdsourcingefficacyreliabilityvoting

Autor:innen und Institutionen

  • Department of Biomedical Informatics, Emory University, Atlanta, GA 30322, USA.
  • AliveCor Inc., Mountain View, CA 94043, USA.
  • Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA.

ORCID-Profile: Ali Bahrami Rad, Reza Sameni, Gari D Clifford

Förderung

  • NIBIB NIH HHS
  • AliveCor
  • NIH HHS
  • National Institute of Biomedical Imaging and Bioengineering (NIBIB)

Zitieren

APA

Bahrami Rad, A., Kirsch, M., Li, Q., Xue, J., Sameni, R., Albert, D., & Clifford, G. D. (2024). A Crowdsourced AI Framework for Atrial Fibrillation Detection in Apple Watch and Kardia Mobile ECGs. Sensors. https://doi.org/10.3390/s24175708

Vancouver

Bahrami Rad A, Kirsch M, Li Q, Xue J, Sameni R, Albert D, et al. A Crowdsourced AI Framework for Atrial Fibrillation Detection in Apple Watch and Kardia Mobile ECGs. Sensors. 2024. doi:10.3390/s24175708

BibTeX
@article{BahramiRad2024,
  author = {Bahrami Rad, Ali and Kirsch, Miguel and Li, Qiao and Xue, Joel and Sameni, Reza and Albert, Dave and Clifford, Gari D},
  title = {A Crowdsourced AI Framework for Atrial Fibrillation Detection in Apple Watch and Kardia Mobile ECGs},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24175708}
}
Kostenlos starten →