Back
For best output, select "Paper Size" as "A4" and "Margin" as "0" or "None".
To save or print to PDF, please select Print Destination > Save as PDF, enable Background Graphics under "More Settings", then click "Save".
During the congress, E-Posters will be accessible to all participants on the congress website 24/7, as well as in the E-poster stations in the congress center.
Preparing your E-Poster
Please review the E-Poster format requirements carefully when preparing your E-Poster. Should your E-Poster not meet the mentioned requirements, it may not be displayed as described above.
E-Poster Submission Deadline
Please prepare and upload your E-Poster no later than March 14, 2026 11.59PM CET. After this date, you will no longer be able to prepare and upload your E-poster and it will not be displayed and accessible on the congress website.
Please follow the instructions below to input your abstract title.
Abstract titles should be brief and reflect the content of the abstract.
Impaired kidney function is often asymptomatic, delaying diagnosis and treatment. The utility of electrocardiography (ECG) in identifying impaired kidney function has not been fully explored. We aimed to develop and validate a deep learning algorithm using ECG data to detect impaired kidney function.
We retrospectively analyzed over 1.3 million ECGs (250 thouand pateints) from two tertiary hospitals in Korea. DeepECG-Kidney30 and DeepECG-Kidney60 models were developed using Vision Transformer architecture to identify individuals with estimated glomerular filtration rate <30 and <60 mL/min/1.73 m², respectively. Model performance was assessed using area under the receiver operating characteristics curve(AUROC) across 12-Lead, Limb-Lead(I, II, III, aVR, aVL, and aVF), and Lead-I ECGs.
The DeepECG-Kidney30 model achieved AUROC values of 0.9126 (12-Lead), 0.8903 (Limb-Lead), and 0.8807 (Lead-I) in the internal test set, and 0.9152, 0.8977, and 0.8869, respectively, in the external validation cohort. DeepECG-Kidney60 demonstrated similar performance with slightly lower AUROC values. Performance was consistent across subgroups, with notably higher accuracy in individuals <65 years and in ECGs without overt abnormalities. Models using reduced lead sets also maintained high accuracy, indicating feasibility for wearable device integration. Pretraining with a masked autoencoder further enhanced model performance.
Our ECG-based deep learning models accurately detected impaired kidney function across various lead configurations, supporting their clinical utility as non-invasive tools for impaired kidney function screening—even in wearable device settings.
