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.

(1) Background: While an artificial intelligence (AI)-based, cardiologist-level, deep-learning model for detecting acute myocardial infarction (AMI), based on a 12-lead electrocardiogram (ECG), has been established to have extraordinary capabilities, its real-world performance and clinical applications are currently unknown. (2) Methods and Results: To set up an artificial intelligence-based alarm strategy (AI-S) for detecting AMI, we assembled a strategy development cohort including 25,002 visits from August 2019 to April 2020 and a prospective validation cohort including 14,296 visits from May to August 2020 at an emergency department. The components of AI-S consisted of chest pain symptoms, a 12-lead ECG, and high-sensitivity troponin I. The primary endpoint was to assess the performance of AI-S in the prospective validation cohort by evaluating F-measure, precision, and recall. The secondary endpoint was to evaluate the impact on door-to-balloon (DtoB) time before and after AI-S implementation in STEMI patients treated with primary percutaneous coronary intervention (PPCI). Patients with STEMI were alerted precisely by AI-S (F-measure = 0.932, precision of 93.2%, recall of 93.2%). Strikingly, in comparison with pre-AI-S (N = 57) and post-AI-S (N = 32) implantation in STEMI protocol, the median ECG-to-cardiac catheterization laboratory activation (EtoCCLA) time was significantly reduced from 6.0 (IQR, 5.0–8.0 min) to 4.0 min (IQR, 3.0–5.0 min) (p < 0.01). The median DtoB time was shortened from 69 (IQR, 61.0–82.0 min) to 61 min (IQR, 56.8–73.2 min) (p = 0.037). (3) Conclusions: AI-S offers front-line physicians a timely and reliable diagnostic decision-support system, thereby significantly reducing EtoCCLA and DtoB time, and facilitating the PPCI process. Nevertheless, large-scale, multi-institute, prospective, or randomized control studies are necessary to further confirm its real-world performance.

Statins constitute the mainstay treatment for atherosclerotic cardiovascular disease, which is associated with the risk of new-onset diabetes mellitus (NODM). However, the effects of individual statins on the risk of NODM remain unclear. We recruited 48,941 patients taking one of the three interested statins in a tertiary hospital between 2006 and 2018. Among them, 8337 non-diabetic patients taking moderate-intensity statins (2 mg/day pitavastatin, 10 mg/day atorvastatin, and 10 mg/day rosuvastatin) were included. The pitavastatin group had a higher probability of being NODM-free than the atorvastatin and rosuvastatin groups during the 4-year follow-up (log-rank test: p = 0.038). A subgroup analysis revealed that rosuvastatin had a significantly higher risk of NODM than pitavastatin among patients with coronary artery disease (CAD) (adjusted HR [aHR], 1.47, 95% confidence interval [CI], 1.05–2.05, p = 0.025), hypertension (aHR, 1.26, 95% CI, 1.00–1.59, p = 0.047), or chronic obstructive pulmonary disease (COPD) (aHR, 1.74, 95% CI, 1.02–2.94, p = 0.04). We concluded that compared with rosuvastatin, reduced diabetogenic effects of pitavastatin were observed among patients treated with moderate-intensity statin who had hypertension, COPD, or CAD. Additional studies are required to prove the effects of different statins on the risk of NODM.

Purpose: In this study, transapical transcatheter mitral valve-in-valve implantation (TAMVI) was compared with surgical redo mitral valve replacement (SRMVR) in terms of clinical outcomes.Methods: We retrospectively identified patients with degenerated mitral bioprosthesis or failed annuloplasty rings who underwent redo SRMVR or TAMVI at our medical center. Clinical outcomes were based on echocardiography results.Results: We retrospectively identified patients with symptomatic mitral bioprosthetic valve dysfunction (n = 58) and failed annuloplasty rings (n = 14) who underwent redo SRMVR (n = 36) or TAMVI (n = 36). The Society of Thoracic Surgeons Predicted Risk of Mortality scores were higher in the TAMVI group (median: 9.52) than in the SRMVR group (median: 5.59) (p-value = 0.02). TAMVI patients were more severe in New York Heart Association (p-value = 0.04). The total procedure time (skin to skin) and length of stay after procedures were significantly shorter in the TAMVI group, and no significant difference in mortality was noted after adjustment for confounding factors (p-value = 0.11). The overall mean mitral valve pressure gradient was lower in the TAMVI group than in the SRMVR group at 24 months (p < 0.01). Both groups presented a decrease in the severity of mitral and tricuspid regurgitation at 3–24 months.Conclusions: In conclusion, the statistical analysis is still not robust enough to make a claim that TAMVI is an appropriate alternative. The outcome of the patient appears only to be related to the patient's pre-operative STS score. Additional multi-center, longitudinal studies are warranted to adequately assess the effect of TAMVI.