Key result
A two-stream deep learning model using 12-lead ECG and six artificial features detected hypokalemia with an AVC of 0.82 and recognition accuracy of 75.91% on the test set.
Why the study?
Detection of hypokalemia mainly relies on serum potassium concentration, but characteristic ECG changes occur as potassium decreases, prompting exploration of intelligent ECG-based detection.
Can a two-stream deep learning model based on 12-lead ECG accurately detect hypokalemia?
Can a two-stream deep learning model based on 12-lead ECG accurately detect hypokalemia?
A two-stream deep learning model utilizing 12-lead ECG and extracted time-domain features can detect hypokalemia with an AUC of 0.82 and accuracy of 75.91%.
Model accuracy insufficient for clinical use; leaves open need for prospective validation before adoption.
Hypokalemia is one of the most common electrolyte disorders in clinic. The detection of hypokalemia mainly depends on the detection of serum potassium concentration. Previous studies have shown that with the decrease of serum potassium ion concentration, ECG will show corresponding characteristics. In this paper, 12-lead ECG is used for intelligent detection of hypokalemia. After six artificial features based on ECG are extracted, a two-stream deep learning model is trained by using these features and 12-lead ECG to detect hypokalemia. The AVC of the two-stream model on the verification set is 0.84, and the AVC on the test set is 0.82. After taking the best working point, on the verification set, the sensitivity is 81.45%, the specificity is 74.21 %, and the recognition accuracy is 77.82%, while on the test set, the sensitivity is 77.54%, the specificity is 74.28%, and the recognition accuracy is 75.91 %. The results show that these time-domain features can significantly improve the recognition accuracy of hypokalemia.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2022) studied Hypokalemia. Two-stream deep learning model based on 12-lead ECG was evaluated on Detection of hypokalemia (AVC 0.82). A two-stream deep learning model using 12-lead ECG and six artificial features detected hypokalemia with an AVC of 0.82 and recognition accuracy of 75.91% on the test set.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: