Related Experiment Video
Updated: Dec 27, 2025
Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function
Published on: December 11, 2019
A Deep-Learning Algorithm (ECG12Net) for Detecting Hypokalemia and Hyperkalemia by Electrocardiography: Algorithm
Chin-Sheng Lin1, Chin Lin2,3,4, Wen-Hui Fang5
1Division of Cardiology, Department of Medicine, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan.
Insights
A new deep-learning model, ECG12Net, can detect dyskalemias (hypokalemia and hyperkalemia) using electrocardiograms (ECGs), outperforming clinicians in accuracy. This AI tool shows promise for early detection and reducing cardiac events.
Area of Science:
- Cardiology
- Artificial Intelligence
- Medical Diagnostics
Background:
- Current dyskalemia detection relies on laboratory tests.
- Cardiac tissue is highly sensitive to potassium level changes.
- Electrocardiography (ECG) offers potential for early dyskalemia detection.
Purpose of the Study:
- Develop a deep-learning model, ECG12Net, for dyskalemia detection using ECGs.
- Evaluate the performance and logic of the ECG12Net model.
- Compare AI model performance against human clinicians.
Main Methods:
- Utilized 66,321 ECG records from 40,180 emergency department patients.
- Developed an 82-layer convolutional neural network (ECG12Net) to estimate serum potassium.
- Conducted a human-machine competition with six physicians on 300 ECGs.
Main Results:
- ECG12Net demonstrated superior performance in detecting hypokalemia (AUC 0.926) and hyperkalemia (AUC 0.958) compared to clinicians.
- High sensitivities and specificities were achieved for both conditions in human-machine competition and test sets.
- The model showed a mean absolute error of 0.531 for serum potassium estimation.
Conclusions:
- A deep-learning model using 12-lead ECGs can aid prompt recognition of severe dyskalemias.
- ECG12Net has the potential to significantly reduce cardiac events through early detection.
- AI-powered ECG analysis represents a promising advancement in cardiovascular diagnostics.
Background:
The detection of dyskalemias-hypokalemia and hyperkalemia-currently depends on laboratory tests. Since cardiac tissue is very sensitive to dyskalemia, electrocardiography (ECG) may be able to uncover clinically important dyskalemias before laboratory results.
Objective:
Our study aimed to develop a deep-learning model, ECG12Net, to detect dyskalemias based on ECG presentations and to evaluate the logic and performance of this model.
Methods:
Spanning from May 2011 to December 2016, 66,321 ECG records with corresponding serum potassium (K+) concentrations were obtained from 40,180 patients admitted to the emergency department. ECG12Net is an 82-layer convolutional neural network that estimates serum K+ concentration. Six clinicians-three emergency physicians and three cardiologists-participated in human-machine competition. Sensitivity, specificity, and balance accuracy were used to evaluate the performance of ECG12Net with that of these physicians.
Results:
In a human-machine competition including 300 ECGs of different serum K+ concentrations, the area under the curve for detecting hypokalemia and hyperkalemia with ECG12Net was 0.926 and 0.958, respectively, which was significantly better than that of our best clinicians. Moreover, in detecting hypokalemia and hyperkalemia, the sensitivities were 96.7% and 83.3%, respectively, and the specificities were 93.3% and 97.8%, respectively. In a test set including 13,222 ECGs, ECG12Net had a similar performance in terms of sensitivity for severe hypokalemia (95.6%) and severe hyperkalemia (84.5%), with a mean absolute error of 0.531. The specificities for detecting hypokalemia and hyperkalemia were 81.6% and 96.0%, respectively.
Conclusions:
A deep-learning model based on a 12-lead ECG may help physicians promptly recognize severe dyskalemias and thereby potentially reduce cardiac events.
Related Concept Videos
01:29Electrocardiogram
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and...
01:28Electrocardiogram Fundamentals
An electrocardiogram (ECG) is a diagnostic tool for identifying cardiac conditions such as arrhythmias, conduction abnormalities, and myocardial ischemia.
Definition
An electrocardiogram (ECG) visualizes the heart's electrical activity by tracing the electrical movement associated with each heartbeat on a graph or monitor. As the heart beats, an electrical wave passes through it, correlating with the cardiac cycle events.
Parts of an ECG
An ECG utilizes electrodes on the skin...
01:30Dysrhythmias V: Evaluating Dysrhythmias
01:23Holter Monitor: 24-Hour Monitoring
01:30Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...