- Clinical Cardiac Electrophysiology
Board Certification: American Board of Internal Medicine, Clinical Cardiac Electrophysiology (2021)
Fellowship: Stanford University Clinical Cardiac Electrophysiology Fellowship (2021) CA
Board Certification: American Board of Internal Medicine, Cardiovascular Disease (2019)
Fellowship: Medical College Of Wisconsin (2019) WI
Board Certification: American Board of Internal Medicine, Internal Medicine (2016)
Residency: Medical College of Wisconsin Internal Medicine Residency (2016) WI
Medical Education: Rosalind Franklin University The Chicago Medical School (2013) IL
Atrial Fibrillation Ablation Outcome Prediction with a Machine Learning Fusion Framework Incorporating Cardiac Computed Tomography.
Journal of cardiovascular electrophysiology
BACKGROUND: Structural changes in the left atrium (LA) modestly predict outcomes in patients undergoing catheter ablation for atrial fibrillation (AF). Machine learning (ML) is a promising approach to personalize AF management strategies and improve predictive risk models after catheter ablation by integrating atrial geometry from cardiac computed tomography (CT) scans and patient-specific clinical data. We hypothesized that ML approaches based on a patient's specific data can identify responders to AF ablation.METHODS: Consecutive patients undergoing AF ablation, who had preprocedural CT scans, demographics, and 1-year follow-up data, were included in the study for a retrospective analysis. The inputs of models were CT-derived morphological features from left atrial segmentation (including the shape, volume of the LA, LA appendage, and pulmonary vein ostia) along with deep features learned directly from raw CT images, and clinical data. These were merged intelligently in a framework to learn their individual importance and produce the optimal classification.RESULTS: 321 patients (64.2 + 10.6 years, 69% male, 40% paroxysmal AF) were analyzed. Post 10-fold nested cross-validation, the model trained to intelligently merge and learn appropriate weights for clinical, morphological, and imaging data (AUC 0.821) outperformed those trained solely on clinical data (AUC 0.626), morphological (AUC 0.659) or imaging data (AUC 0.764).CONCLUSION: Our machine learning approach provides an end-to-end automated technique to predict AF ablation outcomes using deep learning from CT images, derived structural properties of LA, augmented by incorporation of clinical data in a merged ML framework. This can help develop personalized strategies for patient selection in invasive management of AF. This article is protected by copyright. All rights reserved.
View details for DOI 10.1111/jce.15890
View details for PubMedID 36934383
Tyrosine kinase inhibitor-associated ventricular arrhythmias: a case series and review of literature.
Journal of interventional cardiac electrophysiology : an international journal of arrhythmias and pacing
BACKGROUND: Tyrosine kinase inhibitors (TKIs) have been increasingly used as first-line therapy in hematologic and solid-organ malignancies. Multiple TKIs have been linked with the development of cardiovascular complications, especially atrial arrhythmias, but data on ventricular arrhythmias (VAs) is scarce.METHODS: Herein we describe five detailed cases of VAs related to TKI use in patients with varied baseline cardiovascular risk factors between 2019 and 2022 at three centers. Individual chart review was conducted retrospectively.RESULTS: Patient ages ranged from 43 to 83years. Three patients were on Bruton's TKI (2 ibrutinib and 1 zanubrutinib) at the time of VAs; other TKIs involved were afatinib and dasatinib. Three patients had a high burden of non-sustained ventricular tachycardia (NSVT) requiring interventions, whereas two patients had sustained VAs. While all patients in our case series had significant improvement in VA burden after TKI cessation, two patients required new long-term antiarrhythmic drug therapy, and one had an implantable defibrillator cardioverter (ICD) placed due to persistent VAs after cessation of TKI therapy. One patient reinitiated TKI therapy after control of arrhythmia was achieved with antiarrhythmic drug therapy.CONCLUSIONS: Given the expanding long-term use of TKIs among a growing population of cancer patients, it is critical to acknowledge the association of TKIs with cardiovascular complications such as VAs, to characterize those at risk, and deploy preventive and therapeutic measures to avoid such complications and interference with oncologic therapy. Further efforts are warranted to develop monitoring protocols and optimal treatment strategies for TKI-induced VAs.
View details for DOI 10.1007/s10840-022-01400-z
View details for PubMedID 36411365
Machine Learning-Enabled Multimodal Fusion of Intra-Atrial and Body Surface Signals in Prediction of Atrial Fibrillation Ablation Outcomes.
Circulation. Arrhythmia and electrophysiology
BACKGROUND: Machine learning is a promising approach to personalize atrial fibrillation management strategies for patients after catheter ablation. Prior atrial fibrillation ablation outcome prediction studies applied classical machine learning methods to hand-crafted clinical scores, and none have leveraged intracardiac electrograms or 12-lead surface electrocardiograms for outcome prediction. We hypothesized that (1) machine learning models trained on electrograms or ECG signals can perform better at predicting patient outcomes after atrial fibrillation ablation than existing clinical scores and (2) multimodal fusion of electrogram, ECG, and clinical features can further improve the prediction of patient outcomes.METHODS: Consecutive patients who underwent catheter ablation between 2015 and 2017 with panoramic left atrial electrogram before ablation and clinical follow-up for at least 1 year following ablation were included. Convolutional neural network and a novel multimodal fusion framework were developed for predicting 1-year atrial fibrillation recurrence after catheter ablation from electrogram, ECG signals, and clinical features. The models were trained and validated using 10-fold cross-validation on patient-level splits.RESULTS: One hundred fifty-six patients (64.5±10.5 years, 74% male, 42% paroxysmal) were analyzed. Using electrogram signals alone, the convolutional neural network achieved an area under the receiver operating characteristics curve of 0.731, outperforming the existing APPLE scores (area under the receiver operating characteristics curve=0.644) and CHA2DS2-VASc scores (area under the receiver operating characteristics curve=0.650). Similarly using 12-lead ECG alone, the convolutional neural network achieved an AUROC of 0.767. Combining electrogram, ECG, and clinical features, the fusion model achieved an AUROC of 0.859, outperforming single and dual modality models.CONCLUSIONS: Deep neural networks trained on electrogram or ECG signals improved the prediction of catheter ablation outcome compared with existing clinical scores, and fusion of electrogram, ECG, and clinical features further improved the prediction. This suggests the promise of using machine learning to help treatment planning for patients after catheter ablation.
View details for DOI 10.1161/CIRCEP.122.010850
View details for PubMedID 35867397
Mapping Atrial Fibrillation After Surgical Therapy to Guide Endocardial Ablation.
Circulation. Arrhythmia and electrophysiology
Surgical ablation for atrial fibrillation (AF) can be effective, yet has mixed results. It is important to improve the success of AF surgery, yet unclear which endocardial lesions will best augment surgical lesion sets in individual patients. We addressed this question by systematically mapping AF endocardially after surgical ablation and relating findings to early recurrence.We studied 81 consecutive patients undergoing epicardial surgical ablation (stage 1 hybrid), of whom 64 proceeded to endocardial catheter mapping and ablation (stage 2). Stage 2 comprised high-density mapping of pulmonary vein (PV) or posterior wall (PW) reconnections, low-voltage zones (LVZs), and potential localized AF drivers. We related findings to postsurgical recurrence of AF.Mapping at stage 2 revealed PW isolation reconnection in 59.4%, PV isolation reconnection in 28.1%, and LVZ in 42.2% of patients. Postsurgical recurrence of AF occurred in 36 patients (56.3%), particularly those with long-standing persistent AF (P=0.017), but had no relationship to reconnection of PVs (P=0.53) or PW isolation (P=0.75) when compared with those without postsurgical recurrence of AF. LVZs were more common in patients with postsurgical recurrence of AF (P=0.002), long-standing persistent AF (P=0.002), advanced age (P=0.03), and elevated CHA2DS2-VASc (P=0.046). AF mapping revealed 4.4±2.7 localized focal/rotational sites near and also remote from PV or PW reconnection. After ablation at patient-specific targets, arrhythmia freedom at 1 year was 81.0% including and 73.0% excluding previously ineffective antiarrhythmic medications.After surgical ablation, AF may recur by several modes including recovery of PW or PV isolation, mechanisms related to localized LVZ, or other sustaining mechanisms. LVZs are more common in patients at high clinical risk for recurrence. Patient-specific targeting of these mechanisms yields excellent long-term outcomes from hybrid ablation.
View details for DOI 10.1161/CIRCEP.121.010502
View details for PubMedID 35622437
- Ibrutinib-associated atrial fibrillation treatment with catheter ablation. HeartRhythm case reports 2021; 7 (11): 713-716
Antiarrhythmic drug loading at home using remote monitoring: a virtual feasibility study during COVID-19 social distancing.
European heart journal. Digital health
2021; 2 (2): 259-262
The epidemiological necessity for distancing during the COVID-19 pandemic has resulted in postponement of non-emergent hospitalizations and increase use of telemedicine. The feasibility of virtual antiarrhythmic drug (AAD) loading specifically with digital QTc electrocardiographic monitoring (EM) in conjunction with telemedicine video visits is not well established. We tested the hypothesis that existing digital health technologies and virtual communication platforms could provide EM and support medically guided AAD loading for patients with symptomatic tachyarrhythmia in the ambulatory setting, while reducing physical contact between patient and healthcare system. A prospective pilot, case series was approved by the institutional ethics committee, entailing three subjects with symptomatic arrhythmia during the COVID-19 pandemic who were enrolled for virtual AAD loading at home. Clinicians met with participants twice daily via video visits conducted after QTc analysis (Kardia 6L mobile sensor) and telemetry review (Mobile Cardiac Outpatient Telemetry of silent arrhythmias). Participants received direct instruction to either terminate the study or proceed with the next single dose of AAD. All participants completed contactless loading of five AAD doses, without untoward event. Scheduled video visits allowed dialogue and participant counselling where decision-making was guided by remote review of EM. Participant adherence with transmissions and scheduled visits was 98.3%; a single electrocardiogram was delayed beyond the 2 hours of post-dose schedule. This virtual approach reduced overall expenditures based on retrospective comparison with previous AAD load hospitalizations. We found that a 'virtual hospitalization' for AAD loading with remote EM and twice-daily virtual rounding is feasible using existing digital health technologies.
View details for DOI 10.1093/ehjdh/ztab034
View details for PubMedID 37155657
View details for PubMedCentralID PMC8083679
Arrhythmia Patterns in Patients on Ibrutinib.
Frontiers in cardiovascular medicine
1800; 8: 792310
Introduction: Ibrutinib, a Bruton's tyrosine kinase inhibitor (TKI) used primarily in the treatment of hematologic malignancies, has been associated with increased incidence of atrial fibrillation (AF), with limited data on its association with other tachyarrhythmias. There are limited reports that comprehensively analyze atrial and ventricular arrhythmia (VA) burden in patients on ibrutinib. We hypothesized that long-term event monitors could reveal a high burden of atrial and VAs in patients on ibrutinib. Methods: A retrospective data analysis at a single center using electronic medical records database search tools and individual chart review was conducted to identify consecutive patients who had event monitors while on ibrutinib therapy. Results: Seventy-two patients were included in the analysis with a mean age of 76.9 ± 9.9 years and 13 patients (18%) had a diagnosis of AF prior to the ibrutinib therapy. During ibrutinib therapy, most common arrhythmias documented were non-AF supraventricular tachycardia (n = 32, 44.4%), AF (n = 32, 44%), and non-sustained ventricular tachycardia (n = 31, 43%). Thirteen (18%) patients had >1% premature atrial contraction burden; 16 (22.2%) patients had >1% premature ventricular contraction burden. In 25% of the patients, ibrutinib was held because of arrhythmias. Overall 8.3% of patients were started on antiarrhythmic drugs during ibrutinib therapy to manage these arrhythmias. Conclusions: In this large dataset of ambulatory cardiac monitors on patients treated with ibrutinib, we report a high prevalence of atrial and VAs, with a high incidence of treatment interruption secondary to arrhythmias and related symptoms. Further research is warranted to optimize strategies to diagnose, monitor, and manage ibrutinib-related arrhythmias.
View details for DOI 10.3389/fcvm.2021.792310
View details for PubMedID 35047578
Antiarrhythmic Drug Loading at Home Using Remote Monitoring: A Virtual Feasibility Study During COVID-19 Social Distancing
European Heart Journal Digital Health
View details for DOI 10.1093/ehjdh/ztab034
- Deformation of stylet-driven leads & helix unraveling during acute explant after conduction system pacing. Indian pacing and electrophysiology journal 2021
- Tick-Borne Illness and Infective Endocarditis: A Rare Case of Tularemia. CASE (Philadelphia, Pa.) 2020; 4 (2): 78–81
Tachyarrhythmia Discriminator for Implantable Cardioverter-Defibrillators in Bundle Branch Block.
Inaccurate arrhythmia classification by implantable cardioverter-defibrillators (ICD) contributes to inappropriate shocks and increased healthcare utilization.This study sought to evaluate the ability of a novel discriminator using far-field (FF) and near-field (NF) right ventricular lead electrocardiograms (EGMs), to differentiate ventricular tachycardia (VT) from supraventricular tachycardia (SVT) in patients with underlying conducted narrow QRS, right bundle branch block (RBBB) and left bundle branch block (LBBB).ICD interrogations were reviewed, identifying subjects with tachycardia events at least 5 beats in duration with stable morphology and cycle length. FF to NF EGM intervals during tachycardia and baseline conducted rhythm were measured using digital calipers. Events with uncertain tachycardia rhythm mechanism were excluded.Ninety-five subjects were included. Mean FF to NF interval during tachycardia was significantly lower during SVT than VT (25.8 ± 12.0 ms vs. 91.0 ± 37.2 ms, p < 0.001).with LBBB (n=22) and RBBB (n=21) had significantly lower mean FF to NF intervals during SVT compared with VT (LBBB 25.6 ± 7.26 ms vs. 93.1 ± 41.5 ms, p<0.001); (RBBB 30.0 ± 16.6 ms vs. 101.7 ± 34.3 ms, p<0.001). In this cohort, FF to NF interval cutoff of 100 ms (Caldwell et al, 2018) was 100% specific for VT discrimination regardless of underlying QRS morphology, with a sensitivity of 46%, 50%, and 38% for LBBB, RBBB, and narrow QRS, respectively.Prolonged FF to NF interval on intra-cardiac EGM during tachycardia is a highly specific discriminator for VT, regardless of baseline QRS morphology.
View details for DOI 10.1016/j.hrthm.2020.04.031
View details for PubMedID 32353586