Physiological Age by Artificial Intelligence-Enhanced Electrograms as a Novel Biomarker of Mortality in Kidney Transplant Candidates
Mayo Clinic, Rochester, MN
Meeting: 2022 American Transplant Congress
Abstract number: 25
Keywords: Adverse effects, Age factors, Outcome, Waiting lists
Topic: Clinical Science » Kidney » 35 - Kidney: Cardiovascular and Metabolic Complications
Session Information
Session Name: Kidney: Cardiovascular and Metabolic Complications I
Session Type: Rapid Fire Oral Abstract
Date: Sunday, June 5, 2022
Session Time: 3:30pm-5:00pm
Presentation Time: 3:50pm-4:00pm
Location: Hynes Veterans Auditorium
*Purpose: Assessing mortality risk prior to kidney transplantation is challenging. Age-Gap, which is the difference between physiological age determined by artificial intelligence-enhanced electrocardiograms (ECG) and chronological age, has been associated with risk of mortality in non-transplant populations. The aim of this study was to determine whether Age-Gap is also associated with mortality in kidney transplant candidates.
*Methods: We applied a previously developed convolutional neural network to the ECGs of patients who underwent kidney transplant evaluation at our center between 2014 and 2019 to determine physiological age. All patients underwent ECG assessment during kidney transplant evaluation at our center. We used a Cox proportional hazard model to examine whether Age-Gap was associated with mortality among waitlisted candidates. We adjusted for chronological age and Charlson comorbidity index. Patients were censored at the time of kidney transplantation.
*Results: Of the 2,213 patients evaluated, 59.1% were male, 33.9% had diabetes, and 81.3% were Caucasian. Over a mean follow-up time of 1.7 ± 1.4 years, 11.3% of patients died. Mean ECG-predicted physiological age was 58.6 ± 12.5 years, while mean chronological age at ECG was 52.7 ± 14.4 years (R2 = 0.6, p < 0.001). The mean Age-Gap was 5.9 ± 9.3 years. Patients with an Age-Gap > 1 standard deviation (SD) older than their chronological age were significantly more likely to experience waitlist mortality than patients with an Age-Gap ≤ 1 SD (HR = 1.8; 95% CI 1.1-2.8; p = 0.013) after adjusting for chronological age and Charlson comorbidity index.
*Conclusions: The ECG-predicted physiological age is a biomarker of waitlist mortality in kidney transplant candidates after adjusting for chronological age and prognostic comorbidities. Determining ECG-predicted physiological age through artificial intelligence may help guide risk-benefit assessment when evaluating and approving candidates for kidney transplantation.
To cite this abstract in AMA style:
Lorenz E, Zaniletti I, Johnson B, Petterson T, Kremers W, Schinstock C, Amer H, Cheville A, LeBrasseur N, Baez-Suarez A, Attia Z, Lopez-Jimenez F, Friedman P, Kennedy C, Rule A. Physiological Age by Artificial Intelligence-Enhanced Electrograms as a Novel Biomarker of Mortality in Kidney Transplant Candidates [abstract]. Am J Transplant. 2022; 22 (suppl 3). https://atcmeetingabstracts.com/abstract/physiological-age-by-artificial-intelligence-enhanced-electrograms-as-a-novel-biomarker-of-mortality-in-kidney-transplant-candidates/. Accessed May 30, 2025.« Back to 2022 American Transplant Congress