Although mild PVS was frequently observed after RFCA in this large cohort, incidence of severe PVS was <1% and incidence of symptomatic PVS necessitating intervention was negligible. Based on these findings, it seems appropriate to only screen for PVS in patients with suggestive symptoms.
BACKGROUND
The correct interpretation of the
ECG
is pivotal for the accurate diagnosis of many cardiac abnormalities, and conventional computerized interpretation has not been able to reach physician‐level accuracy in detecting (acute) cardiac abnormalities. This study aims to develop and validate a deep neural network for comprehensive automated
ECG
triage in daily practice.
METHODS AND RESULTS
We developed a 37‐layer convolutional residual deep neural network on a data set of free‐text physician‐annotated 12‐lead
ECG
s. The deep neural network was trained on a data set with 336.835 recordings from 142.040 patients and validated on an independent validation data set (n=984), annotated by a panel of 5 cardiologists electrophysiologists. The 12‐lead
ECG
s were acquired in all noncardiology departments of the University Medical Center Utrecht. The algorithm learned to classify these
ECG
s into the following 4 triage categories: normal, abnormal not acute, subacute, and acute. Discriminative performance is presented with overall and category‐specific concordance statistics, polytomous discrimination indexes, sensitivities, specificities, and positive and negative predictive values. The patients in the validation data set had a mean age of 60.4 years and 54.3% were men. The deep neural network showed excellent overall discrimination with an overall concordance statistic of 0.93 (95%
CI
, 0.92–0.95) and a polytomous discriminatory index of 0.83 (95%
CI
, 0.79–0.87).
CONCLUSIONS
This study demonstrates that an end‐to‐end deep neural network can be accurately trained on unstructured free‐text physician annotations and used to consistently triage 12‐lead
ECG
s. When further fine‐tuned with other clinical outcomes and externally validated in clinical practice, the demonstrated deep learning–based
ECG
interpretation can potentially improve time to treatment and decrease healthcare burden.
Although homocysteine is generally considered the aminothiol of interest with respect to cardiovascular disease, in our prospective study, only cysteine and glutathione appeared independently associated with recurrent atherothrombotic events. Moreover, we showed that an imbalance in the combination of aminothiols could be of more importance than investigating the individual metabolites.
Aspirin prevents thrombotic events by inhibiting platelet cyclooxygenase-1 (COX-1), thus reducing thromboxane A2 formation and platelet aggregation. The C50T polymorphism of COX-1 is associated with an impaired inhibition of both thromboxane production and in-vitro platelet aggregation by aspirin. We studied whether this polymorphism is also associated with the risk of clinical thrombotic events in patients using aspirin. We included 496 patients admitted to our Coronary Care Unit for various indications treated with aspirin 80 mg daily. Genotyping for the C50T polymorphism demonstrated that 86.7% of the patients had the common genotype, and 13.3% had the variant (12.5% heterozygous, 0.8% homozygous). Baseline variables were well balanced, except that patients with the common genotype more frequently used aspirin prior to admission compared to those patients with the variant genotype. The composite primary endpoint of myocardial infarction, stroke, and/or cardiovascular death occurred in 98 patients (19.8%). Myocardial infarction occurred in 9.6% of patients, stroke in 1.6%, and cardiovascular death in 12.1%. The unadjusted hazard ratio (95% CI) for the primary endpoint for patients with the variant versus the common genotype was 1.07 (0.62-1.85), p = 0.8. The adjusted hazard ratio was 0.86 (0.49-1.50), p = 0.6. In prior laboratory studies the COX-1 C50T polymorphism was associated with an impaired inhibitory effect of aspirin on thromboxane production and platelet function. However, in this cohort of patients using low-dose aspirin for secondary prevention the polymorphism was not associated with a higher risk of atherothrombotic events.
We demonstrate that the in vitro addition of even a subtherapeutic dose of cangrelor to the PRP of clopidogrel-pretreated patients results in an additional reduction of ADP-induced platelet aggregation. Moreover, cangrelor was able to diminish the interindividual variation observed in clopidogrel-inhibited platelet aggregation. (Neth Heart J 2009;17:195-8.).
Adenosine testing immediately after PVAI does not reliably exclude later spontaneous or adenosine-induced PV reconnection. Adenosine testing should be performed after an appropriate observation period to reduce risk of PV reconnection.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.