EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

An electrocardiogram-based AI algorithm for early detection of pulmonary hypertension

Hilary M DuBrock iD, Tyler E Wagner iD, Katherine Carlson iD, Corinne L Carpenter, Samir Awasthi iD, Zachi I Attia iD, Robert P Frantz iD, Paul A Friedman, Suraj Kapa, Jeffrey Annis iD, Evan L Brittain, Anna R Hemnes iD und 12 weitere

European Respiratory Journal · 2024-07 · 64 (1) · 2400192

DOI: 10.1183/13993003.00192-2024 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Respiratory Journal, online erschienen am 27.06.2024. Verfasst von Hilary M DuBrock und 23 weiteren Autor:innen. Beteiligte Einrichtung: Division of Pulmonary and Critical Care Medicine, Mayo Clinic, Rochester, MN, USA dubrock.hilary@mayo.edu. Hauptthemen laut MEDLINE: Hypertension, Pulmonary, Electrocardiography, Algorithms, Early Diagnosis. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: nference, Inc, Janssen Research and Development.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Early diagnosis of pulmonary hypertension (PH) is critical for effective treatment and management. We aimed to develop and externally validate an artificial intelligence algorithm that could serve as a PH screening tool, based on analysis of a standard 12-lead ECG.

Methods

The PH Early Detection Algorithm (PH-EDA) is a convolutional neural network developed using retrospective ECG voltage–time data, with patients classified as “PH-likely” or “PH-unlikely” (controls) based on right heart catheterisation or echocardiography. In total, 39 823 PH-likely patients and 219 404 control patients from Mayo Clinic were randomly split into training (48%), validation (12%) and test (40%) sets. ECGs taken within 1 month of PH diagnosis (diagnostic dataset) were used to train the PH-EDA at Mayo Clinic. Performance was tested on diagnostic ECGs within the test sets from Mayo Clinic (n=16 175/87 998 PH-likely/controls) and Vanderbilt University Medical Center (VUMC; n=6045/24 256 PH-likely/controls). In addition, performance was tested on ECGs taken 6–18 months (pre-emptive dataset), and up to 5 years prior to a PH diagnosis at both sites.

Results

Performance testing yielded an area under the receiver operating characteristic curve (AUC) of 0.92 and 0.88 in the diagnostic test sets at Mayo Clinic and VUMC, respectively, and 0.86 and 0.81, respectively, in the pre-emptive test sets. The AUC remained a minimum of 0.79 at Mayo Clinic and 0.73 at VUMC up to 5 years before diagnosis.

Conclusion

The PH-EDA can detect PH at diagnosis and 6–18 months prior, demonstrating the potential to accelerate diagnosis and management of this debilitating disease.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Hypertension, PulmonaryElectrocardiographyAlgorithmsEarly DiagnosisHumansFemaleMaleMiddle AgedRetrospective StudiesAgedArtificial IntelligenceROC CurveEchocardiographyAdultNeural Networks, ComputerCardiac Catheterization

Autor:innen und Institutionen

  • Division of Pulmonary and Critical Care Medicine, Mayo Clinic, Rochester, MN, USA dubrock.hilary@mayo.edu.
  • Co-first authors.
  • nference, Cambridge, MA, USA.
  • Anumana, Cambridge, MA, USA.
  • Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA.
  • Division of Cardiovascular Medicine, Vanderbilt University Medical Center, Nashville, TN, USA.

ORCID-Profile: Hilary M DuBrock, Tyler E Wagner, Katherine Carlson, Samir Awasthi, Zachi I Attia, Robert P Frantz, Jeffrey Annis, Anna R Hemnes, Venky Soundararajan

Förderung

  • nference, Inc
  • Janssen Research and Development

Zitieren

APA

DuBrock, H. M., Wagner, T. E., Carlson, K., Carpenter, C. L., Awasthi, S., Attia, Z. I., Frantz, R. P., Friedman, P. A., Kapa, S., Annis, J., Brittain, E. L., Hemnes, A. R., Asirvatham, S. J., Babu, M., Prasad, A., Yoo, U., Barve, R., Selej, M., Agron, P., …, & Soundararajan, V. (2024). An electrocardiogram-based AI algorithm for early detection of pulmonary hypertension. European Respiratory Journal, 64(1), 2400192. https://doi.org/10.1183/13993003.00192-2024

Vancouver

DuBrock HM, Wagner TE, Carlson K, Carpenter CL, Awasthi S, Attia ZI, et al. An electrocardiogram-based AI algorithm for early detection of pulmonary hypertension. European Respiratory Journal. 2024;64(1):2400192. doi:10.1183/13993003.00192-2024

BibTeX
@article{DuBrock2024,
  author = {DuBrock, Hilary M and Wagner, Tyler E and Carlson, Katherine and Carpenter, Corinne L and Awasthi, Samir and Attia, Zachi I and Frantz, Robert P and Friedman, Paul A and Kapa, Suraj and Annis, Jeffrey and Brittain, Evan L and Hemnes, Anna R and Asirvatham, Samuel J and Babu, Melwin and Prasad, Ashim and Yoo, Unice and Barve, Rakesh and Selej, Mona and Agron, Peter and Kogan, Emily and Quinn, Deborah and Dunnmon, Preston and Khan, Najat and Soundararajan, Venky},
  title = {An electrocardiogram-based AI algorithm for early detection of pulmonary hypertension},
  journal = {European Respiratory Journal},
  year = {2024},
  volume = {64},
  number = {1},
  pages = {2400192},
  doi = {10.1183/13993003.00192-2024}
}
Kostenlos starten →