Machine learning identifies esophageal luminal temperature patterns associated with thermal injury in catheter ablation for atrial fibrillation.

INTRODUCTION: Luminal esophageal temperature (LET) monitoring during atrial fibrillation (AF) ablation is widely used to reduce the incidence of endoscopically detected esophageal lesion (EDEL). We sought to assess whether specific patterns of LET variation are associated with EDEL. METHODS: A high-fidelity multisensor probe was used to record LET in AF patients undergoing radiofrequency ablation (RFA) or cryoballoon ablation (CBA). Explainable machine learning and SHapley Additive exPlanations (SHAP) analysis were used to predict EDEL and assess feature importance. RESULTS: A total of 94 patients (38.3% persistent AF, 71.3% male, 72 RFA, and 22 CBA) were included. EDEL was detected in 11 patients (10 RFA and one CBA). In the RFA group, the highest LET recorded was similar between patients with and without EDEL (40.6 [40.1-41]°C vs. 40.2 [39.1-40.9]°C; p = .313), however, the rate of LET rise for the highest recorded peak was higher (0.08 [0.03-0.12]°C/s vs. 0.02 [0.01-0.05]°C/s; p = .033), and the area under the curve (AUC) for the highest peak was smaller (412.5 [206.8-634.1] vs. 588.6 [380.4-861.1]; p = .047) in patients who had EDEL. In case of CBA, the patient with EDEL had a faster LET decline (0.12 vs. 0.07 [0.02-0.14]°C/s), and a smaller AUC for the lowest trough (2491.3 vs. 2629.3 [1712.6-5283.2]). SHAP analysis revealed that a rate of LET change higher than 0.05°C/s and an AUC less than 600 were more predictive of EDEL in RFA. CONCLUSION: The rate of LET change and AUC for the recorded temperature predicted EDEL, whereas absolute peak temperatures did not.

Personalized biomechanical insights in atrial fibrillation: opportunities & challenges.

INTRODUCTION: Atrial fibrillation (AF) is an increasingly prevalent and significant worldwide health problem. Manifested as an irregular atrial electrophysiological activation, it is associated with many serious health complications. AF affects the biomechanical function of the heart as contraction follows the electrical activation, subsequently leading to reduced blood flow. The underlying mechanisms behind AF are not fully understood, but it is known that AF is highly correlated with the presence of atrial fibrosis, and with a manifold increase in risk of stroke. AREAS COVERED: In this review, we focus on biomechanical aspects in atrial fibrillation, current and emerging use of clinical images, and personalized computational models. We also discuss how these can be used to provide patient-specific care. EXPERT OPINION: Understanding the connection betweenatrial fibrillation and atrial remodeling might lead to valuable understanding of stroke and heart failure pathophysiology. Established and emerging imaging modalities can bring us closer to this understanding, especially with continued advancements in processing accuracy, reproducibility, and clinical relevance of the associated technologies. Computational models of cardiac electromechanics can be used to glean additional insights on the roles of AF and remodeling in heart function.

People with atrial fibrillation (AF) experience a fast, chaotic heartbeat. AF greatly increases the risk of stroke. The hearts of AF patients often have an accumulation of fibrous tissue (fibrosis). Fibrosis patterns can be detected via medical imaging scans, like MRI. These images can be used to build patient-specific digital representations. These models can be used to explore how fibrosis might cause AF, stroke, and other health risks. Insights from imaging and modeling are becoming more and more useful as tools for personalizing AF treatment.

Comparing Inducibility of Re-Entrant Arrhythmia in Patient-Specific Computational Models to Clinical Atrial Fibrillation Phenotypes.

BACKGROUND: Computational models of fibrosis-mediated, re-entrant left atrial (LA) arrhythmia can identify possible substrate for persistent atrial fibrillation (AF) ablation. Contemporary models use a 1-size-fits-all approach to represent electrophysiological properties, limiting agreement between simulations and patient outcomes. OBJECTIVES: The goal of this study was to test the hypothesis that conduction velocity (Ï´) modulation in persistent AF models can improve simulation agreement with clinical arrhythmias. METHODS: Patients with persistent AF (n = 37) underwent ablation and were followed up for ≥2 years to determine post-ablation outcomes: AF, atrial flutter (AFL), or no recurrence. Patient-specific LA models (n = 74) were constructed using pre-ablation and ≥90 days' post-ablation magnetic resonance imaging data. Simulated pacing gauged in silico arrhythmia inducibility due to AF-like rotors or AFL-like macro re-entrant tachycardias. A physiologically plausible range of Ï´ values (±10 or 20% vs. baseline) was tested, and model/clinical agreement was assessed. RESULTS: Fifteen (41%) patients had a recurrence with AF and 6 (16%) with AFL. Arrhythmia was induced in 1,078 of 5,550 simulations. Using baseline Ï´, model/clinical agreement was 46% (34 of 74 models), improving to 65% (48 of 74) when any possible Ï´ value was used (McNemar's test, P = 0.014). Ï´ modulation improved model/clinical agreement in both pre-ablation and post-ablation models. Pre-ablation model/clinical agreement was significantly greater for patients with extensive LA fibrosis (>17.2%) and an elevated body mass index (>32.0 kg/m2). CONCLUSIONS: Simulations in persistent AF models show a 41% relative improvement in model/clinical agreement when Ï´ is modulated. Patient-specific calibration of Ï´ values could improve model/clinical agreement and model usefulness, especially in patients with higher body mass index or LA fibrosis burden. This could ultimately facilitate better personalized modeling, with immediate clinical implications.

Machine Learning and the Conundrum of Stroke Risk Prediction.

Stroke is a leading cause of death worldwide. With escalating healthcare costs, early non-invasive stroke risk stratification is vital. The current paradigm of stroke risk assessment and mitigation is focused on clinical risk factors and comorbidities. Standard algorithms predict risk using regression-based statistical associations, which, while useful and easy to use, have moderate predictive accuracy. This review summarises recent efforts to deploy machine learning (ML) to predict stroke risk and enrich the understanding of the mechanisms underlying stroke. The surveyed body of literature includes studies comparing ML algorithms with conventional statistical models for predicting cardiovascular disease and, in particular, different stroke subtypes. Another avenue of research explored is ML as a means of enriching multiscale computational modelling, which holds great promise for revealing thrombogenesis mechanisms. Overall, ML offers a new approach to stroke risk stratification that accounts for subtle physiologic variants between patients, potentially leading to more reliable and personalised predictions than standard regression-based statistical associations.

Esophageal luminal temperature monitoring using a multi-sensor probe lowers the risk of esophageal injury in cryo and radiofrequency catheter ablation for atrial fibrillation.

BACKGROUND: Esophageal luminal temperature monitoring is a commonly used strategy to reduce esophageal thermal injury in catheter ablation for atrial fibrillation (AFib). OBJECTIVES: We sought to compare the incidence of endoscopically detected esophageal lesions (EDEL) between two commonly used esophageal luminal temperature probes. METHODS: Consecutive patients undergoing ablation with esophageal luminal temperature monitoring and upper endoscopy within 24 h after ablation were included. RESULTS: Four hundred forty-five patients (64 ± 10 years, 44% female) were included. Esophageal temperature monitoring was done with a single-sensor probe in 213 (48%) and multi-sensor probe in 232 (52%). Cryoballoon (CB) ablation was performed in 118 (27%) and radiofrequency (RF) ablation in 327 (73%) of patients. EDEL was present in 94 (22.9%) of which 85 were mild, 8 were moderate, and 1 was severe, and none progressed to atrial-esophageal fistula. The use of the multi-sensor probe during CB ablation was associated with a reduction in EDEL compared to single sensor (6.8% vs 24.3%; P = 0.016). Similarly, in the RF ablation group, EDEL was present in 19.5% of the multi-sensor group vs 32.8% in the single-sensor group (P = 0.001). Logistic regression showed that multi-sensor probe use was associated with reduction in EDEL with an odds ratio of 0.23 in CB ablation (P = 0.024) and 0.44 for RF ablation (P = 0.001). CONCLUSIONS: Esophageal luminal temperature monitoring during AFib ablation using a multi-sensor probe was associated with a significant reduction in EDEL compared to a single-sensor probe.

Cryoballoon temperature parameters during cryoballoon ablation predict pulmonary vein reconnection and atrial fibrillation recurrence.

BACKGROUND: Cryoballoon ablation (CBA) is an established approach for rhythm management of atrial fibrillation (AF). We sought to assess balloon temperature (BT) parameters as predictors of pulmonary vein (PV) reconnection within the index procedure and AF recurrence following CBA. METHODS: BT was monitored in 119 AF patients undergoing CBA. PVs were assessed for reconnection during the procedure and patients were followed for arrhythmia recurrence. RESULTS: PV reconnection was identified in 39 (8.3%) of 471 PVs. BT was significantly colder in the absence of PV reconnection (30 s: - 33.5 °C [- 36; - 30] vs - 29.5 °C [- 35; - 25.5], p = 0.001; 60 s: - 41 °C [- 44; - 37] vs - 36.5 °C [- 42; - 33.5], p < 0.001; nadir: - 47 °C [- 52; - 43] vs - 41.5 °C [- 47; - 38], p < 0.001). PV reconnection was associated with significantly longer time to reach - 15 °C and - 40 °C (14.5 s [11.5-18.5] vs 12 s [10-15.5], p = 0.023; and 75 s [40-95.5] vs 46 s [37-66.75], p = 0.005) and shorter rewarming time (5.75 s [4.75-8.5] vs 7 s [6-9], p = 0.012). ROC analysis of these procedural parameters had an AUC = 0.71 in predicting PV reconnection. AF recurrence occurred in 51 (42.8%) patients. Kaplan-Meier analysis showed better arrhythmia-free survival for patients in whom BT decreased below - 40 °C in all PVs and patients who had no early PV reconnections, compared to patients in whom BT below - 40 °C was not achieved in at least one PV (log rank = 6.3, p = 0.012) and patients who had PV reconnections (log rank = 4.1, p = 0.043). CONCLUSIONS: Slower BT decline, warmer BT nadir, and faster rewarming time predict early PV reconnection. Absence of early PV reconnections and BT dropping below - 40 °C in all PVs during CBA are associated with lower rates of AF recurrence.

MRI-quantified left atrial epicardial adipose tissue predicts atrial fibrillation recurrence following catheter ablation.

Background: Epicardial adipose tissue (EAT) plays a significant role in promoting atrial fibrillation (AF) due to its proinflammatory properties and anatomic proximity to the myocardium. We sought to assess whether left atrial (LA) EAT volume is associated with AF recurrence following catheter ablation. Methods: EAT was assessed via the 3D MRI Dixon sequence in 101 patients undergoing AF ablation. Patients were followed for arrhythmia recurrence. Results: During an average follow-up period of 1 year, post-ablation AF recurrence occurred in 31 (30.7%) patients. LA EAT index was higher in those with compared to without recurrence (20.7 [16.9, 30.4] vs. 13.7 [10.5, 20.1] mL/m2, p < 0.001), and so was LA volume index (66 [52.6, 77.5] vs. 49.9 [37.7, 61.8] mL/m2, p = 0.001). Cox regression analysis showed LA EAT (HR = 1.089; 95% CI: [1.049-1.131], p < 0.001) to be an independent predictor of post-ablation AF recurrence. The ROC curve for LA EAT index in the prediction of AF recurrence had an AUC of 0.77 (95% CI 0.68-0.86, p < 0.001) and showed an optimal cutoff value of 14.29 mL/m2 to identify patients at risk of post-ablation AF recurrence. Integrating LA EAT with clinical risk factors improved prediction of AF recurrence (AUC increased from 0.65 to 0.79, DeLong test p = 0.044). Kaplan-Meier analysis for recurrence-free survival showed a significant difference between two groups of patients identified by the optimal LA EAT index cutoff of 14.29 mL/m2 (log rank = 14.79; p < 0.001). Conclusion: EAT quantified using cardiac MRI, a reproducible and widely accessible imaging parameter, is a strong and independent predictor of post-ablation AF recurrence.

Epicardial adipose tissue is associated with left atrial volume and fibrosis in patients with atrial fibrillation.

Background: Obesity is a risk factor for atrial fibrillation (AF) and strongly influences the response to treatment. Atrial fibrosis shows similar associations. Epicardial adipose tissue (EAT) may be a link between these associations. We sought to assess whether EAT is associated with body mass index (BMI), left atrial (LA) fibrosis and volume. Methods: LA fibrosis and EAT were assessed using late gadolinium enhancement, and Dixon MRI sequences, respectively. We derived 3D models incorporating fibrosis and EAT, then measured the distance of fibrotic and non-fibrotic areas to the nearest EAT to assess spatial colocalization. Results: One hundred and three AF patients (64% paroxysmal, 27% female) were analyzed. LA volume index was 54.9 (41.2, 69.7) mL/m2, LA EAT index was 17.4 (12.7, 22.9) mL/m2, and LA fibrosis was 17.1 (12.4, 23.1)%. LA EAT was significantly correlated with BMI (R = 0.557, p < 0.001); as well as with LA volume and LA fibrosis after BSA adjustment (R = 0.579 and R = 0.432, respectively, p < 0.001 for both). Multivariable analysis showed LA EAT to be independently associated with LA volume and fibrosis. 3D registration of fat and fibrosis around the LA showed no clear spatial overlap between EAT and fibrotic LA regions. Conclusion: LA EAT is associated with obesity (BMI) as well as LA volume and fibrosis. Regions of LA EAT did not colocalize with fibrotic areas, suggesting a systemic or paracrine mechanism rather than EAT infiltration of fibrotic areas.

Predictors of generic and burn-specific quality of life among adult burn patients admitted to a Lebanese burn care center: a cross-sectional single-center study.

Burn injuries carry significant implications on short- and long-term quality of health. The present study undertook the first attempt to characterize generic and burn-specific quality of life and their predictors among adult burn patients admitted to a Lebanese burn care center. 130 adult patients admitted to the Lebanese Geitaoui Hospital burn center between 2013 and 2019 willingly answered Arabic versions of RAND's 36-Item Short Form Survey (SF-36), and the Burn-Specific Health Scale-Brief (BSHS-B). Results showed that burn patients continue to exhibit impairments on various generic and burn-specific quality of life subdomains. Education, pain and total body surface area (TBSA) burned were consistently and significantly correlated with both BSHS-B and SF-36 component scores, while inhalation injury exhibited an association with total BSHS-B score. Education and pain emerged as independent predictors of SF-36 components as well as total BSHS-B score. The latter was additionally associated with BMI and burn degree, while TBSA burned negatively correlated with SF-36 physical component scores. Correlates of impaired quality of life among Lebanese adult burn patients should therefore be taken into account and existing burn management practices and rehabilitation programs should be revised accordingly in order to ensure optimal long-term patient outcomes.