Detecting Digoxin Toxicity by Artificial Intelligence-Assisted Electrocardiography

Abstract

Although digoxin is important in heart rate control, the utilization of digoxin is declining due to its narrow therapeutic window. Misdiagnosis or delayed diagnosis of digoxin toxicity is common due to the lack of awareness and the time-consuming laboratory work that is involved. Electrocardiography (ECG) may be able to detect potential digoxin toxicity based on characteristic presentations. Our study attempted to develop a deep learning model to detect digoxin toxicity based on ECG manifestations. This study included 61 ECGs from patients with digoxin toxicity and 177,066 ECGs from patients in the emergency room from November 2011 to February 2019. The deep learning algorithm was trained using approximately 80% of ECGs. The other 20% of ECGs were used to validate the performance of the Artificial Intelligence (AI) system and to conduct a human-machine competition. Area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were used to evaluate the performance of ECG interpretation between humans and our deep learning system. The AUCs of our deep learning system for identifying digoxin toxicity were 0.912 and 0.929 in the validation cohort and the human-machine competition, respectively, which reached 84.6% of sensitivity and 94.6% of specificity. Interestingly, the deep learning system using only lead I (AUC = 0.960) was not worse than using complete 12 leads (0.912). Stratified analysis showed that our deep learning system was more applicable to patients with heart failure (HF) and without atrial fibrillation (AF) than those without HF and with AF. Our ECG-based deep learning system provides a high-accuracy, economical, rapid, and accessible way to detect digoxin toxicity, which can be applied as a promising decision supportive system for diagnosing digoxin toxicity in clinical practice.

Electrocardiogram-Based Heart Age Estimation by a Deep Learning Model Provides More Information on the Incidence of Cardiovascular Disorders

“…We used the corresponding International Classification of Diseases, Ninth Revision and Tenth Revision (ICD-9 and ICD-10) to define certain CVD-related outcomes. The detail codes were described as previously study ( 10 , 13 , 20 , 27 ). For each CVD-related outcome, patients with ICD-9 or ICD-10 with corresponding diagnosis codes before the first-exam ECG collected in the physical examination center were excluded.…”

“…We have developed a DLM, ECG12Net, with 82-layer convolutional layers and an attention mechanism for potassium concentration estimation. The technology details, such as the model architecture, data augmentation, and model visualization, were described previously ( 10 , 13 , 27 ). We used the same architecture to train a new DLM for linking the ECG and the chronological age.…”

Artificial Intelligence-Enabled Electrocardiography Predicts Left Ventricular Dysfunction and Future Cardiovascular Outcomes: A Retrospective Analysis

“…Electrocardiography (ECG) is an inexpensive, noninvasive and widely used tool for multiple chronic cardiac disease screenings and evaluations. With the rapid progression of deep learning models (DLMs) on ECG [ 19 ], these models have expanded to multiple applications and achieved human-level performance, effectively detecting cardiac diseases with large annotated ECG datasets, including arrhythmia detection [ 20 ], dyskalemia [ 21 , 22 , 23 ], myocardial infarction [ 24 , 25 , 26 ], aortic dissection [ 27 ], thyrotoxic periodic paralysis [ 28 ], and digoxin toxicity [ 29 ]. Interestingly, current studies have started to use DLM to interpret chronic changes in ECGs, such as anemia [ 30 ], diabetes [ 31 ], conduction abnormality [ 32 ], future atrial fibrillation [ 33 ], and mortality prediction [ 34 ].…”

Deep Learning Algorithm for Management of Diabetes Mellitus via Electrocardiogram-Based Glycated Hemoglobin (ECG-HbA1c): A Retrospective Cohort Study

“…The DLM architecture with an attention mechanism was used to estimate HbA1c, which was based on our previous study [ 21 , 22 , 26 , 37 ]. Figure 2 A shows the architecture of our DLM.…”

“…In the past, many studies have attempted to obtain more information about the prognosis or disease diagnosis from electrocardiograms (ECG), and have successively helped to clarify the relationship between the ECG and the prognosis, but this method has not become popular because it is difficult to judge the waveform and requires other mathematical analyses. The current revolution in artificial intelligence (AI) based on deep learning models (DLMs) is a data-driven technique to learn useful features in an automated fashion [ 20 ], which is powerful for detecting myocardial infarction [ 21 ], digoxin toxicity [ 22 ], arrhythmia [ 23 , 24 ], hyperkalemia [ 25 , 26 ], left ventricular dysfunction [ 27 , 28 ], mitral regurgitation [ 29 ], aortic stenosis [ 30 ], and hypoglycemic events [ 31 ]. Therefore, we attempted to employ DLM to apply ECG to DM management, which may combine unstructured data to identify additional information.…”