ASN's Mission

To create a world without kidney diseases, the ASN Alliance for Kidney Health elevates care by educating and informing, driving breakthroughs and innovation, and advocating for policies that create transformative changes in kidney medicine throughout the world.

learn more

Contact ASN

1401 H St, NW, Ste 900, Washington, DC 20005

email@asn-online.org

202-640-4660

The Latest on X

Kidney Week

Please note that you are viewing an archived section from 2022 and some content may be unavailable. To unlock all content for 2022, please visit the archives.

Abstract: SA-PO935

Development and Validation of Deep Learning Algorithm for Evaluating Kidney Function Based on Electrocardiogram

Session Information

Category: CKD (Non-Dialysis)

  • 2202 CKD (Non-Dialysis): Clinical‚ Outcomes‚ and Trials

Authors

  • Lee, Dong Hee, Hallym University Sacred Heart Hospital, Anyang, Gyeonggi-do, Korea (the Republic of)
  • An, Jung Nam, Hallym University Sacred Heart Hospital, Anyang, Gyeonggi-do, Korea (the Republic of)
  • Kim, Sungmin, Hallym University Sacred Heart Hospital, Anyang, Gyeonggi-do, Korea (the Republic of)
  • Kim, Jwa-kyung, Hallym University Sacred Heart Hospital, Anyang, Gyeonggi-do, Korea (the Republic of)
  • Kim, Sung Gyun, Hallym University Sacred Heart Hospital, Anyang, Gyeonggi-do, Korea (the Republic of)
Background

Chronic kidney disease (CKD) is a chronic progressive disease; however, there are no symptoms accompanying deterioration of kidney function, so evaluation of kidney function is possible only through periodic blood tests. Therefore, we aimed to detect kidney function through a deep learning-based model using an electrocardiogram (ECG) that is non-invasive and can be quickly measured.

Methods

Among patients who underwent an ECG at least once from 2006 to 2020, patients with blood test results within 24 hours were included. All ECGs were acquired using a GE ECG machine and the raw data (XML datatype) were stored using the MUSE data management system. For model training and evaluation, the ECG-CKD-EPI eGFR pair was separated into train, validation, and test set. We trained two binary classification model using a Convolutional Neural Network. The model input was a standard 10-second, 12-lead ECG and the output being the likelihood of the ECG being from a patient with CKD.

Results

In a total of 299,431 patients, 324,875 ECG-eGFR pairs were analyzed, of which 285,031 cases were in the train set, 13,805 cases in the validation set, and 26,039 cases in the test set. For the detection of eGFR below the 60 mL/min, the sensitivity and specificity of deep learning model were 85.2% and 72.9%; and for eGFR below the 30 mL/min, they were 87.6% and 75.8% in test set. These performances were calculated by using the operating point at Youden J statistics of validation set.

Conclusion

The deep learning model using the 12-lead ECG waveform detected CKD based on CKD-EPI eGFR with high accuracy. In the case of advanced CKD, the diagnostic predictive power is more increased. These results suggest the clinical applicability of AI software for diagnosing kidney function using ECG.