Key result
Deep learning ECG detects moderate to severe renal impairment with ~0.91 AUC.
Why the study?
Renal failure is a major global healthcare burden requiring early diagnosis to prevent irreversible progression, but an adequate, reliable, noninvasive, and economical screening tool for renal impairment does not exist.
Does a deep learning model using electrocardiography accurately detect and predict moderate to severe renal impairment?
Cohort (n=115,361)
Yes
Does a deep learning model using electrocardiography accurately detect and predict moderate to severe renal impairment?
An interpretable deep learning model can accurately detect and predict moderate to severe renal impairment using standard 12-lead, 6-lead, or single-lead ECGs, offering a potential non-invasive screening tool.
May support ECG-based renal impairment screening; hypothesis-generating and requires prospective trials before clinical use.
Purpose Although renal failure is a major healthcare burden globally and the cornerstone for preventing its irreversible progression is an early diagnosis, an adequate and noninvasive tool to screen renal impairment (RI) reliably and economically does not exist. We developed an interpretable deep learning model (DLM) using electrocardiography (ECG) and validated its performance. Methods This retrospective cohort study included two hospitals. We included 115,361 patients who had at least one ECG taken with an estimated glomerular filtration rate measurement within 30 min of the index ECG. A DLM was developed using 96,549 ECGs of 55,222 patients. The internal validation included 22,949 ECGs of 22,949 patients. Furthermore, we conducted an external validation with 37,190 ECGs of 37,190 patients from another hospital. The endpoint was to detect a moderate to severe RI (estimated glomerular filtration rate < 45 ml/min/1.73m 2 ). Results The area under the receiver operating characteristic curve (AUC) of a DLM using a 12-lead ECG for detecting RI during the internal and external validation was 0.858 (95% confidence interval 0.851–0.866) and 0.906 (0.900–0.912), respectively. In the initial evaluation of 25,536 individuals without RI patients whose DLM was defined as having a higher risk had a significantly higher chance of developing RI than those in the low-risk group (17.2% vs. 2.4%, p < 0.001). The sensitivity map indicated that the DLM focused on the QRS complex and T-wave for detecting RI. Conclusion The DLM demonstrated high performance for RI detection and prediction using 12-, 6-, single-lead ECGs.
No takes yet. Share an insight, caveat, or question.
Kwon et al. (2022) conducted a cohort in Renal impairment (n=115,361). Deep learning model using 12-lead electrocardiography was evaluated on Detection of moderate to severe renal impairment (eGFR < 45 ml/min/1.73m2) (AUC 0.906, 95% CI 0.900-0.912). A deep learning model using 12-lead electrocardiography detected moderate to severe renal impairment with an area under the receiver operating characteristic curve of 0.906 in external validation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: