應用心電圖快速偵測鉀離子異常之方法及其系統

專利類型

發明

專利國別 (專利申請國家)

中華民國

專利申請案號

109108808

專利證號

I 732489

專利獲證名稱

應用心電圖快速偵測鉀離子異常之方法及其系統

專利所屬機關 (申請機關)

國防醫學院

獲證日期

2021/07/01

技術說明

【中文】檢測低血鉀症和高鉀血症目前取決於實驗室測試。但由於心臟對血鉀異常非常敏感，心電圖可能能夠在實驗室檢測結果出來之前發現臨床上重要的血鉀異常。我們的研究旨在開發深度學習模型ECG12Net，以基於心電圖檢測血鉀異常。從2011年5月至2016年12月，我們從急診中的40,180名患者中獲得66,321份心電圖記錄及相應的血清鉀濃度。 ECG12Net是一個82層卷積神經網絡，可估算血清鉀濃度。六名臨床醫師（三名急診醫師和三名心臟科醫師）參加了人機比賽。敏感度、特異性等用於評估ECG12Net與這些醫師的表現。在包括300個不同血清鉀濃度的ECG人機競賽中，ECG12Net在檢測低血鉀和高血鉀的曲線下面積分別為0.926和0.958，明顯優於我們最好的臨床醫生。此外檢測低鉀血症和高鉀血症的敏感性和特異性分別為96.7％/83.3％與93.3％/97.8％。在後續包括13,222個ECG的測試集資料中，ECG12Net具有相同的表現，對嚴重低鉀血症/高鉀血症的敏感性分別達到95.6％和84.5％，平均絕對誤差僅為0.531。檢測低鉀血症和高鉀血症的特異性分別為81.6％和96.0％。基於心電圖的深度學習模型可以幫助醫生迅速識別嚴重的血鉀異常，從而減少心源性猝死事件。【英文】 Detection of dyskalemias (hypo- and hyperkalemia) currently depends on laboratory tests. Since cardiac tissue is very sensitive to dyskalemias, electrocardiography (ECG) may be able to uncover clinically important dyskalemias before laboratory results. Our study aimed to develop a deep learning model, ECG12Net, to detect dyskalemias based on ECG presentation and to evaluate the logic and performance of this model. 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, which estimates serum K+ concentration. Six clinicians (three emergency physicians and three cardiologists) participated a human-machine competition. Sensitivity, specificity and balance accuracy were used to evaluate the performance of ECG12Net with these physicians. In a human-machine competition including 300 ECGs of different serum K+ concentrations, the area under curve in detecting hypo- and hyperkalemia by ECG12Net was 0.926 and 0.958, respectively, which was significantly better than that of our best clinicians. Moreover, the sensitivities and specificities of detecting hypokalemia and hyperkalemia were 96.7% and 83.3%, and 93.3% and 97.8%, respectively. In the test set including 13,222 ECGs, ECG12Net had the same performance with sensitivities for severe hypokalemia/hyperkalemia achieving 95.6% and 84.5%, respectively with the mean absolute error of 0.531. The specificities of detecting hypokalemia and hyperkalemia were 81.6% and 96.0%, respectively. A deep learning model based on 12-lead ECG may help physicians to promptly recognize severe dyskalemias and thereby reduce cardiac events.

備註

連絡單位 (專責單位/部門名稱)

研究發展室

連絡電話

(02)8792-3100分機18079