Luis, Sushil A

Background Pericarditis may be associated with significant morbidity and mortality and can be a clinically challenging entity to diagnose. There is a clinical need for automated artificial intelligence (AI) algorithms to act as a screening aid to assist with the early and accurate detection of pericarditis. Methods We developed p-Cal, a browser-based pericarditis risk calculator that fuses the patient clinical data and 12-lead ECG image to estimate risk for pericarditis. The ECG encoder was designed based on a pretrained MedCLIP Vision Transformer and random forest classifier was used for the clinical tabular data. These two modalities were fused at the decision-level using a meta classifier. Model reasoning for both modalities was assessed using advanced explainable AI techniques—attention maps from the transformer model were used to interpret ECG images, while SHapley Additive exPlanations (SHAP) force plots were applied to analyse the tabular data. Results A total of 6508 patients (mean age 54.8±16.1 years, 50.9% female) were used for training and internal validation of the AI model, of whom 902 patients had a confirmed diagnosis of pericarditis (13.8%) and the remainder were normal controls. On 1302 hold-out test patients, the Fusion Model demonstrated the best discriminatory performance, achieving an area under the curve (AUC) of 0.89, which surpassed the ECG (AUC = 0.85) and the clinical data only models (AUC = 0.74) performance. On external validation in the Medical Information Mart for Intensive Care (MIMIC) Database, the fusion model achieved an AUC of 0.81. Conclusion A late fusion AI model integrating tabular clinical electronic medical record data and ECG signal has robust predictive capability for pericarditis as a screening tool.

Background Recurrent pericarditis may be mediated through inappropriate activation of the NACHT, leucine‐rich repeat, and pyrin domain‐containing protein 3 inflammasome. Pharmaceutically manufactured cannabidiol is an oral formulation that inhibits NACHT, leucine‐rich repeat, and pyrin domain‐containing protein 3 inflammasome activation and development of pericarditis in a preclinical model. Methods This Phase 2, open‐label, multicenter trial included adult patients with symptomatic recurrent pericarditis: pericarditis chest pain ≥4 on an 11‐point numerical rating scale with an elevated C‐reactive protein (≥1 mg/dL) or at least mild pericardial inflammation on cardiac magnetic resonance imaging. At enrollment, patients were on stable doses of non‐steroidal anti‐inflammatory drugs, colchicine, and/or corticosteroids. Cannabidiol was administered during an 8‐week treatment period and an optional 18‐week extension period when background therapy was tapered and discontinued. The primary efficacy end point was change in patient‐reported pericarditis pain. Secondary end points included normalization of C‐reactive protein and percentage of patients with recurrences. Results Among 27 patients (18 women, mean age 53 years), baseline maximal numerical rating scale pain score was 5.8±1.7, and 10 patients had elevated C‐reactive protein. At Week 8, maximal numerical rating scale pain score was 2.1±1.8, and median time to numerical rating scale score ≤2 was 5 days. Among the 10 patients with baseline C‐reactive protein elevation, C‐reactive protein was normal at Week 8 in 8 patients (80%). During the extension period, 17 (71%) of 24 patients remained free of pericarditis recurrence. A serious adverse event leading to cannabidiol discontinuation occurred in 1 patient. Conclusions In symptomatic patients with recurrent pericarditis, pharmaceutically manufactured cannabidiol appears safe and associated with reductions in pericarditis pain and systemic inflammation. Registration URL: clinicaltrials.gov ; Unique Identifier: NCT05494788.

Background Artificial intelligence (AI)–enabled electrocardiography has emerged as a tool for detecting cardiac dysfunction. The prognostic relevance of AI‐enabled electrocardiography–derived diastolic dysfunction (DD) in patients undergoing transcatheter aortic valve replacement had not been assessed. Methods We analyzed 3197 patients undergoing transcatheter aortic valve replacement for severe aortic stenosis between 2010 and 2023 with baseline 12‐lead ECGs processed by a validated AI model to classify diastolic function (grades 0–3). Multivariable Cox models and nested model comparisons assessed associations with all‐cause mortality, including a prespecified analysis in patients with indeterminate echocardiographic grading. Trajectories were defined by change in AI‐enabled electrocardiography DD grade (<2 versus ≥2) from baseline to 30‐day or 1‐year follow‐up. Results At baseline, 21% had grade 3, 57% had grade 2, 8% had grade 1, and 14% had grade 0 AI‐enabled electrocardiography DD. Higher grades were associated with adverse cardiac remodeling and comorbidities. Over a median follow‐up of 3.4 years, grade 3 AI‐enabled electrocardiography DD independently predicted mortality (hazard ratio [HR], 1.80 [95% CI, 1.47–2.20]; P <0.001). AI‐enabled electrocardiography DD improved prognostic discrimination beyond clinical and echocardiographic measures (ΔHarrell concordance statistic, 0.016; Δ χ 2 =57; P <0.001). Among 1259 patients with indeterminate echocardiographic grading, AI‐enabled electrocardiography added prognostic value (ΔHarrell concordance statistic, 0.02; Δ χ 2 =13; P =0.006). Worsening or persistently high‐risk trajectories were associated with increased mortality (HRs, 1.45–1.80; all P <0.05). Conclusions AI‐enabled electrocardiography–derived DD independently predicts mortality after transcatheter aortic valve replacement, adds value beyond echocardiographic grading, and enables dynamic risk stratification through longitudinal tracking.

Abstract Aims In the Phase 3 trial, RHAPSODY, rilonacept effectively resolved active pericarditis recurrences, and long-term treatment led to sustained pericarditis recurrence risk reduction. Prior analysis suggested association between higher late gadolinium enhancement (LGE) at baseline and more rapid recurrence upon rilonacept suspension after 12 weeks of treatment. This subgroup analysis assessed the utility of longitudinal serial cardiac magnetic resonance (CMR) imaging for tracking clinical improvement and predicting post-treatment cessation outcomes to help guide clinical decision-making. Methods and results At an 18-month decision milestone (18MDM) in the RHAPSODY long-term extension, investigators decided if patients would continue rilonacept, suspend rilonacept for off-treatment observation, or discontinue the study. Pericardial thickness, pericardial oedema (T2-short tau inversion recovery, T2-STIR), and LGE were determined at baseline and 18MDM by an imaging core lab blinded to clinical data, and pericarditis recurrence was investigator-assessed. CMR results in patients with data at both baseline and 18MDM (n = 13) showed that pericardial thickness, T2-STIR, and LGE were reduced during rilonacept treatment. Among patients with CMR data who suspended rilonacept at the 18MDM (n = 7), five (71%) had a pericarditis recurrence within 1–4 months of rilonacept suspension, despite all having had none/trace LGE (n = 7) and negative T2-STIR (n = 7) at the 18MDM and two having received prophylactic colchicine. Conclusion Continued clinical improvement during prolonged rilonacept treatment corresponded with improvement on CMR, including reduced pericardial thickness, resolution of pericardial oedema, and resolution of LGE. However, none/trace LGE at 18MDM while on treatment did not predict absence of pericarditis recurrence upon subsequent rilonacept suspension in this size-limited subgroup.

Background Rilonacept, a once‐weekly interleukin‐1 alpha and beta cytokine trap, reduced pericarditis recurrence in the phase 3 study, RHAPSODY (Rilonacept Inhibition of Interleukin‐1 Alpha and Beta for Recurrent Pericarditis: A Pivotal Symptomatology and Outcomes Study). The RHAPSODY long‐term extension further explored recurrent pericarditis natural history and treatment duration decision‐making during 24 additional months of open‐label rilonacept treatment. Methods and Results Seventy‐four patients commenced the long‐term extension, with a median (maximum) total rilonacept duration of 22 (35) months. Individually, 18 months after the most proximal pericarditis recurrence, investigators decided to continue rilonacept on study, suspend rilonacept for off‐treatment observation (rescue allowed), or discontinue the study. The annualized incidence of pericarditis recurrence on rilonacept up to the 18‐month decision milestone was 0.04 events/patient‐year versus 4.4 events/patient‐year prestudy while on oral therapies. At the 18‐month decision milestone, 64% (33/52) continued rilonacept, 15% (8/52) suspended rilonacept for observation, and 21% (11/52) discontinued the study. Among the 33 patients (1/33; 3.0%) continuing rilonacept (median time to recurrence could not be estimated due to too few events), a single recurrence occurred 4 weeks after a treatment interruption. Among patients suspending rilonacept, 75% (6/8) experienced recurrence (median time to recurrence, 11.8 weeks [95% CI, 3.7 weeks to not estimable]). There was a 98% reduction in risk of pericarditis recurrence among patients continuing rilonacept treatment after the 18‐month decision milestone versus those suspending treatment for observation (hazard ratio, 0.02; P <0.0001). Conclusions In the RHAPSODY long‐term extension, continued rilonacept treatment resulted in continued response; treatment suspension at the 18‐month decision milestone was associated with pericarditis recurrence. Registration URL: https://www.clinicaltrials.gov ; Unique identifier: NCT03737110.

Background Recurrent pericarditis is characterized by painful flares and inflammation, which negatively impact health‐related quality of life. RHAPSODY (rilonacept inhibition of interleukin‐1 alpha and beta for recurrent pericarditis: a pivotal symptomatology and outcomes study) evaluated the efficacy and safety of rilonacept (IL‐1α and ‐β cytokine trap) in recurrent pericarditis. A secondary analysis of these data evaluated the patient‐reported outcome questionnaire score change during the trial. Methods and Results Participants completed 5 patient‐reported outcome (PRO) questionnaires assessing pericarditis pain, health‐related quality of life, general health status, sleep impact, and overall symptom severity. PRO score changes during the treatment run‐in period (12 weeks) and the blinded randomized withdrawal period (up to 24 weeks) were evaluated using descriptive statistics and mixed model repeated measures analyses. Participants with PRO data from the run‐in period (n=84) and the randomized withdrawal period (n=61; 30 rilonacept, 31 placebo) were included in analyses. Run‐in baseline PRO scores indicated that pericarditis symptoms during pericarditis recurrence impacted health‐related quality of life. All PRO scores significantly improved ( P <0.001) on rilonacept treatment during the run‐in period. For the randomized withdrawal period, PRO scores were maintained for participants receiving rilonacept. For those receiving placebo and who experienced a recurrence, PRO scores deteriorated at the time of recurrence and then improved following rilonacept bailout. At randomized withdrawal Week 24/End of Study, scores of participants who received bailout rilonacept were similar to those of participants who had continued rilonacept. Conclusions These results demonstrate the burden of pericarditis recurrences and the improved physical and emotional health of patients with recurrent pericarditis while on rilonacept treatment. These findings extend prior rilonacept efficacy results, demonstrating improvements in patient‐reported health‐related quality of life, sleep, pain, and global symptom severity while on treatment. Registration URL: https://www.clinicaltrials.gov ; Unique identifier: NCT03737110.

Abstract Background Approximately one-third of cases of cardiovascular implantable electronic device (CIED) infection present as CIED lead infection. The precise transesophageal echocardiographic (TEE) definition and characterization of “vegetation” associated with CIED lead infection remain unclear. Methods We identified a sample of 25 consecutive cases of CIED lead infection managed at our institution between January 2010 and December 2017. Cases of CIED lead infection were classified using standardized definitions. Similarly, a sample of 25 noninfected patients who underwent TEE that showed a defined lead echodensity during the study period was included as a control group. TEEs were reviewed by 2 independent echocardiologists who were blinded to all linked patient demographic, clinical, and microbiological information. Reported echocardiographic variables of the infected vs noninfected cases were compared, and the overall diagnostic performance was analyzed. Results Descriptions of lead echodensities were variable and there were no significant differences in median echodensity diameter or mobility between infected vs noninfected groups. Among infected cases, blinded echocardiogram reports by either reviewer correctly made a prediction of infection in 6 of 25 (24%). Interechocardiologist agreement was 68%. Sensitivity of blinded TEEs ranged from 31.5% to 37.5%. Conclusions Infectious vs noninfectious lead echodensities could not be reliably distinguished on the basis of size, mobility, and general shape descriptors obtained from a retrospective blinded TEE examination without knowledge of clinical and microbiological parameters. Therefore, a reanalysis of criteria used to support a diagnosis of CIED lead infection may be warranted.