Artificial Intelligence-Driven Algorithm for Drug Effect Prediction on Atrial Fibrillation: An in silico Population of Models Approach

Background: Antiarrhythmic drugs are the first-line treatment for atrial fibrillation (AF), but their effect is highly dependent on the characteristics of the patient. Moreover, anatomical variability, and specifically atrial size, have also a strong influence on AF recurrence.Objective: We performed a proof-of-concept study using artificial intelligence (AI) that enabled us to identify proarrhythmic profiles based on pattern identification from in silico simulations.Methods: A population of models consisting of 127 electrophysiological profiles with a variation of nine electrophysiological variables (GNa, INaK, GK1, GCaL, GKur, IKCa, [Na]ext, and [K]ext and diffusion) was simulated using the Koivumaki atrial model on square planes corresponding to a normal (16 cm2) and dilated (22.5 cm2) atrium. The simple pore channel equation was used for drug implementation including three drugs (isoproterenol, flecainide, and verapamil). We analyzed the effect of every ionic channel combination to evaluate arrhythmia induction. A Random Forest algorithm was trained using the population of models and AF inducibility as input and output, respectively. The algorithm was trained with 80% of the data (N = 832) and 20% of the data was used for testing with a k-fold cross-validation (k = 5).Results: We found two electrophysiological patterns derived from the AI algorithm that was associated with proarrhythmic behavior in most of the profiles, where GK1 was identified as the most important current for classifying the proarrhythmicity of a given profile. Additionally, we found different effects of the drugs depending on the electrophysiological profile and a higher tendency of the dilated tissue to fibrillate (Small tissue: 80 profiles vs Dilated tissue: 87 profiles).Conclusion: Artificial intelligence algorithms appear as a novel tool for electrophysiological pattern identification and analysis of the effect of antiarrhythmic drugs on a heterogeneous population of patients with AF.

Computational modeling of atrial fibrillation

With the aging society, the prevalence of atrial fibrillation (AF) continues to increase. Nevertheless, there are still limitations in antiarrhythmic drugs (AAD) or catheter interventions for AF. If it is possible to predict the outcome of AF management according to various AADs or ablation lesion sets through computational modeling, it will be of great clinical help. AF computational modeling has been utilized for in-silico arrhythmia research and enabled high-density entire chamber mapping, reproducible condition control, virtual intervention, not possible clinically or experimentally, in-depth mechanistic research. With the recent development of computer science and technology, more sophisticated and faster computational modeling has become available for clinical application. In particular, it can be applied to determine the extra-PV target of persistent AF catheter ablation or to select the AAD with the best effect. AF computational modeling combined with artificial intelligence is expected to contribute to precision medicine for more diverse uses in the future. Therefore, in this review, we will deal with the history, development, and various applications of computation modeling.

Attenuation and Structural Transformation of Crassicauline A During Sand Frying Process and Antiarrhythmic Effects of its Transformed Products

To ensure safety and efficacy, most Aconitum herbs should be processed before clinical application. The processing methods include boiling, steaming, and sand frying. Among these methods, the transformation pathways of diterpenoid alkaloids in the process of sand frying are more complicated. Therefore, crassicauline A, a natural product with two ester bonds, was chosen as the experimental object. Consequently, a known alkaloid, together with three new alkaloids, was derived from crassicauline A. Meanwhile, the cardiotoxicity of converted products was reduced compared with their parent compound. Interestingly, some diterpenoid alkaloids have similar structures but opposite effects, such as arrhythmia and antiarrhythmic. Considering the converted products are structural analogues of crassicauline A, herein, the antiarrhythmic activity of the transformed products was further investigated. In a rat aconitine-induced arrhythmia assay, the three transformed products, which could dose-dependently delay the ventricular premature beat (VPB) incubation period, reduce the incidence of ventricular tachycardia (VT), combined with the increasing arrhythmia inhibition rate, exhibited prominent antiarrhythmic activities. Our experiments speculated that there might be at least two transformation pathways of crassicauline A during sand frying. The structure-activity data established in this paper constructs the critical pharmacophore of diterpenoid alkaloids as antiarrhythmic agents, which could be helpful in searching for the potential drugs that are equal or more active and with lower toxicity, than currently clinical used antiarrhythmic drugs.

Impact of Catheter Ablation on Stroke, Cognitive Decline and Dementia

AF has been consistently associated with multiple forms of dementia, including idiopathic dementia. Outcomes after catheter ablation for AF are favourable and patients experience a better quality of life, arrhythmia-free survival, and lower rates of hospitalisation compared to patients treated with antiarrhythmic drugs. Catheter ablation is consistently associated with lower rates of stroke compared to AF management without ablation in large national and healthcare system databases. Multiple observational trials have shown that catheter ablation is also associated with a lower risk of cognitive decline, dementia and improved cognitive testing that can be explained through a variety of pathways. Long-term, adequately powered, randomised trials are required to define the role of catheter ablation in the management of AF as a means to lower the risk of cognitive decline, stroke and dementia.

Successful treatment of bepridil-induced intraoperative torsades de pointes by isoproterenol infusion

Background Several types of antiarrhythmic drugs are known to induce QT prolongation and torsades de pointes. Case presentation An 84-year-old man was scheduled for open gastrectomy for residual cancer. He had been prescribed bepridil for atrial fibrillation that converted to sinus rhythm with prolonged QT interval in the operating room. After the surgery was initiated under general and epidural anesthesia, the patient’s heart rate decreased to 50/min and multifocal premature ventricular contractions appeared, followed by several episodes of torsades de pointes, each lasting for 5 to 15 s. Infusion of isoproterenol was started (0.01 μg/kg/min), and the heart rate was maintained at around 80/min. Premature ventricular contractions disappeared, and torsades de pointes did not recur during the surgery. The operation was completed uneventfully. The serum bepridil concentration was found to be extremely high postoperatively. Conclusions Bepridil-induced intraoperative episodes of torsades de pointes were successfully treated by increasing the heart rate with isoproterenol.

Thoracoscopic surgical ablation versus catheter ablation as first-line treatment for long-standing persistent atrial fibrillation: the CASA-AF RCT

Background Standalone thoracoscopic surgical ablation may be more effective than catheter ablation in patients with long-standing persistent atrial fibrillation. Objectives To determine whether or not surgical ablation is clinically superior to catheter ablation as the first-line treatment strategy in long-standing persistent atrial fibrillation. Design This was a prospective, multicentre, randomised control trial. Setting Four NHS tertiary centres in England. Participants Adults with long-standing persistent atrial fibrillation, who had European Heart Rhythm Association symptom scores > 2 and who were naive to previous catheter ablation or thoracic/cardiac surgery. Interventions Minimally invasive thoracoscopic surgical ablation and conventional catheter ablation (control intervention). Main outcome measures The primary outcome was freedom from atrial fibrillation/tachycardia ≥ 30 seconds after a single procedure without antiarrhythmic drugs (class 1C/3) at 1 year, excluding a 3-month blanking period. The secondary outcomes include the intervention-related major complication rate; clinical success (≥ 75% reduction in arrhythmia burden); and changes in symptoms, quality of life and cost-effectiveness. Methods Patients (n = 120) were randomised to surgical ablation (n = 60) or catheter ablation (n = 60). An implanted loop recorder provided continuous cardiac monitoring following ablation. Follow-up visits were at 3, 6, 9 and 12 months. Loop recorder data were reviewed monthly by a physiologist who was blinded to the randomisation outcome. Results The study treatment was received by 55 patients in the surgical ablation arm and 60 patients in the catheter ablation arm; five patients withdrew from surgical ablation before treatment. Data from randomised and treated patients were analysed as per intention to treat. Patients had a mean age of 62.3 (standard deviation 9.6) years, were predominantly male (74%), had a mean left atrial diameter of 44.6 mm (standard deviation 6 mm) and were in continuous atrial fibrillation for 22 months (range 16–31 months). At 12 months, 26% of patients in the surgical ablation arm (14/54) and 28% of patients in the catheter ablation arm (17/60) were free from atrial arrhythmias after a single procedure without antiarrhythmic drugs (odds ratio 1.13, 95% confidence interval 0.46 to 2.83; p = 0.84). An arrhythmia burden reduction of ≥ 75% was seen in 36 out of 54 (67%) patients in the surgical ablation arm, compared with 46 out of 60 (77%) patients in the catheter ablation arm (odds ratio 1.64, 95% confidence interval 0.67 to 4.08; p = 0.3). Procedure-related serious complications within 30 days of the intervention occurred in 15% (8/55) of patients in the surgical ablation arm (including one death) compared with 10% (6/60) of patients in the catheter ablation arm (p = 0.46). Surgical ablation was associated with significantly higher costs (£23,221 vs. £18,186; p = 0.02) and fewer quality-adjusted life-years than catheter ablation (0.76 vs. 0.83; p = 0.02). Limitations This study was conducted in four highly specialised cardiology centres that have substantial experience in both treatment modalities; therefore, the results may not be widely generalisable. The study was not powered to detect small differences in efficacy. Conclusions We found no evidence to suggest that standalone thoracoscopic surgical ablation outcomes were superior to catheter ablation outcomes in achieving freedom from atrial arrhythmia after a single procedure without antiarrhythmic drugs. Moreover, surgical ablation is associated with a longer hospital stay, smaller improvements in quality of life and higher health-care costs than catheter ablation (standard care therapy). Future work Evaluation of the impact of ablation treatments on sinus rhythm maintenance and quality of life with extended follow-up to 3 years. Model-based economic analysis to estimate long-term benefits, harms and costs of surgical and catheter ablation compared with antiarrhythmic drug therapy in long-standing persistent atrial fibrillation patients. Trial registration Current Controlled Trials ISRCTN18250790 and ClinicalTrials.gov NCT02755688. Funding This project was funded by the Efficacy and Mechanism Evaluation (EME) programme, a Medical Research Council (MRC) and National Institute for Health Research (NIHR) partnership. This study was supported by the UK Clinical Research Collaboration-registered King’s Clinical Trials Unit at King’s Health Partners, which is part funded by the NIHR Biomedical Research Centre for Mental Health at South London and Maudsley NHS Foundation Trust and King’s College London and the NIHR Evaluation, Trials and Studies Coordinating Centre. This will be published in full in Efficacy and Mechanism Evaluation; Vol. 8, No. 18. See the NIHR Journals Library website for further project information.