Objectives: 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 299431 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%; 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. Conclusions: 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.