Non-invasive detection of cardiac allograft rejection among heart transplant recipients using an electrocardiogram based deep learning model

Demilade Adedinsewo, Heather D. Hardway, Andrea Carolina Morales-Lara, Mikolaj A. Wieczorek, Patrick W. Johnson, Erika J. Douglass, Bryan J. Dangott, Raouf E. Nakhleh, Tathagat Narula, Parag C. Patel, Rohan M. Goswami, Melissa A. Lyle, Alexander J. Heckman, Juan C. Leoni-Moreno, D. Eric Steidley, Reza Arsanjani, Brian Hardaway, Mohsin Abbas, Atta Behfar, Zachi I. AttiaFrancisco Lopez-Jimenez, Peter A. Noseworthy, Paul Friedman, Rickey E. Carter, Mohamad Yamani

Research output: Contribution to journalArticlepeer-review


Aims: Current non-invasive screening methods for cardiac allograft rejection have shown limited discrimination and are yet to be broadly integrated into heart transplant care. Given electrocardiogram (ECG) changes have been reported with severe cardiac allograft rejection, this study aimed to develop a deep-learning model, a form of artificial intelligence, to detect allograft rejection using the 12-lead ECG (AI-ECG). Methods and results: Heart transplant recipients were identified across three Mayo Clinic sites between 1998 and 2021. Twelve-lead digital ECG data and endomyocardial biopsy results were extracted from medical records. Allograft rejection was defined as moderate or severe acute cellular rejection (ACR) based on International Society for Heart and Lung Transplantation guidelines. The extracted data (7590 unique ECG-biopsy pairs, belonging to 1427 patients) was partitioned into training (80%), validation (10%), and test sets (10%) such that each patient was included in only one partition. Model performance metrics were based on the test set (n = 140 patients; 758 ECG-biopsy pairs). The AI-ECG detected ACR with an area under the receiver operating curve (AUC) of 0.84 [95% confidence interval (CI): 0.78-0.90] and 95% (19/20; 95% CI: 75-100%) sensitivity. A prospective proof-of-concept screening study (n = 56; 97 ECG-biopsy pairs) showed the AI-ECG detected ACR with AUC = 0.78 (95% CI: 0.61-0.96) and 100% (2/2; 95% CI: 16-100%) sensitivity. Conclusion: An AI-ECG model is effective for detection of moderate-to-severe ACR in heart transplant recipients. Our findings could improve transplant care by providing a rapid, non-invasive, and potentially remote screening option for cardiac allograft function.

Original languageEnglish (US)
Pages (from-to)71-80
Number of pages10
JournalEuropean Heart Journal - Digital Health
Issue number2
StatePublished - Mar 1 2023


  • Artificial intelligence
  • Cardiac allograft rejection
  • Deep learning
  • Electrocardiography
  • Heart transplantation

ASJC Scopus subject areas

  • Cardiology and Cardiovascular Medicine


Dive into the research topics of 'Non-invasive detection of cardiac allograft rejection among heart transplant recipients using an electrocardiogram based deep learning model'. Together they form a unique fingerprint.

Cite this