ABSTRACT
Aims: European and American clinical guidelines for implantable cardioverter defibrillators are insufficiently accurate for ventricular arrhythmia (VA) risk stratification, leading to significant morbidity and mortality. Artificial intelligence offers a novel risk stratification lens through which VA capability can be determined from the electrocardiogram (ECG) in normal cardiac rhythm. The aim of this study was to develop and test a deep neural network for VA risk stratification using routinely collected ambulatory ECGs. Methods and results: A multicentre case-control study was undertaken to assess VA-ResNet-50, our open source ResNet-50-based deep neural network. VA-ResNet-50 was designed to read pyramid samples of three-lead 24â h ambulatory ECGs to decide whether a heart is capable of VA based on the ECG alone. Consecutive adults with VA from East Midlands, UK, who had ambulatory ECGs as part of their NHS care between 2014 and 2022 were recruited and compared with all comer ambulatory electrograms without VA. Of 270 patients, 159 heterogeneous patients had a composite VA outcome. The mean time difference between the ECG and VA was 1.6 years (â ambulatory ECG before VA). The deep neural network was able to classify ECGs for VA capability with an accuracy of 0.76 (95% confidence interval 0.66-0.87), F1 score of 0.79 (0.67-0.90), area under the receiver operator curve of 0.8 (0.67-0.91), and relative risk of 2.87 (1.41-5.81). Conclusion: Ambulatory ECGs confer risk signals for VA risk stratification when analysed using VA-ResNet-50. Pyramid sampling from the ambulatory ECGs is hypothesized to capture autonomic activity. We encourage groups to build on this open-source model. Question: Can artificial intelligence (AI) be used to predict whether a person is at risk of a lethal heart rhythm, based solely on an electrocardiogram (an electrical heart tracing)? Findings: In a study of 270 adults (of which 159 had lethal arrhythmias), the AI was correct in 4 out of every 5 cases. If the AI said a person was at risk, the risk of lethal event was three times higher than normal adults. Meaning: In this study, the AI performed better than current medical guidelines. The AI was able to accurately determine the risk of lethal arrhythmia from standard heart tracings for 80% of cases over a year away-a conceptual shift in what an AI model can see and predict. This method shows promise in better allocating implantable shock box pacemakers (implantable cardioverter defibrillators) that save lives.
ABSTRACT
Background: Vagus nerve stimulation (VNS) is an established therapy for drug-resistant epilepsy and depression. While VNS co-existence with cardiac pacemakers is considered safe, its interaction with implantable cardioverter defibrillators (ICDs) remains poorly understood. The concern revolves around the potential for VNS stimulation to interfere with ICD function, potentially resulting in inappropriate therapy or changes in cardiac pacing. Case summary: We present the case of a 50-year-old woman with drug-resistant epilepsy who underwent VNS device implantation and subsequent transvenous ICD placement for primary prevention post-myocardial infarction. These devices were thoughtfully situated contralaterally, with a minimum 10â cm separation. Comprehensive testing and follow-up demonstrated no interactions during device programming or serial assessments. Simultaneous interrogation of both devices with their respective telemetry wands caused chaotic artefacts in all channels on the ICD, likely due to electromagnetic interference. Importantly, this interference did not affect ICD sensing. Discussion: The co-existence of VNS and ICD in a patient is an emerging scenario with limited previous reports, yet our findings align with prior cases involving VNS and pacemakers. Emphasizing the need for optimal device separation and meticulous evaluation, particularly at maximum VNS output and ICD sensitivity settings, ensures their safe and feasible co-existence. As the use of VNS alongside cardiac implantable electronic devices becomes more common, a diligent evaluation for potential interactions is imperative. Our case highlights the successful co-existence of VNS and ICD, underscoring the importance of careful monitoring and evaluation to guarantee the safe utilization of these two devices.
ABSTRACT
Ischemic preconditioning (IPC) inhibits Ca(2+)-loading during ischemia which contributes to cardioprotection by inhibiting mechanical injury due to hypercontracture and biochemical injury through mitochondrial permeability transition (MPT) pores during reperfusion. However, whether remote-IPC reduced Ca(2+)-loading during ischemia and its subsequent involvement in inhibiting MPT pore formation during reperfusion has not been directly shown. We have developed a cellular model of remote IPC to look at the impact of remote conditioning on Ca(2+)-regulation and MPT pore opening during simulated ischemia and reperfusion, using fluorescence microscopy. Ventricular cardiomyocytes were isolated from control rat hearts, hearts preconditioned with three cycles of ischemia/reperfusion or naïve myocytes remotely conditioned with effluent collected from preconditioned hearts. Both conventional-IPC and remote-IPC reduced the loss of Ca(2+)-homeostasis and contractile function following reenergization of metabolically inhibited cells and protected myocytes against ischemia/reperfusion injury. However, only conventional-IPC reduced the Ca(2+)-loading during metabolic inhibition and this was independent of any change in sarcKATP channel activity but was associated with a reduction in Na(+)-loading, reflecting a decrease in Na/H exchanger activity. Remote-IPC delayed opening of the MPT pores in response to ROS, which was dependent on PKCε and NOS-signaling. These data show that remote-IPC inhibits MPT pore opening to a similar degree as conventional IPC, however, the contribution of MPT pore inhibition to protection against reperfusion injury is independent of Ca(2+)-loading in remote IPC. We suggest that inhibition of the MPT pore and not Ca(2+)-loading is the common link in cardioprotection between conventional and remote IPC.
