Steidley, Eric

Background. Liver transplant recipients face high risks of cardiometabolic events after transplant, driven by posttransplant weight gain, diabetes, hypertension, as well as immunosuppression-related side effects. Glucagon-like peptide-1 receptor agonists (GLP1RAs) improve metabolic and cardiorenal outcomes in nontransplant populations, but their role in liver transplant recipients remains understudied. Methods. This retrospective cohort study used TriNetX data (January 2010–December 2023) to compare outcomes in liver transplant recipients prescribed GLP1RAs (semaglutide, dulaglutide, liraglutide) within 1-mo posttransplant (n = 546) versus nonusers (n = 37 153). Propensity score matching (1:1) balanced demographics, comorbidities, and medications (n = 541 per group). Outcomes included mortality, hospitalizations, cardiovascular/renal/respiratory events, and graft outcomes. Results. Over a mean follow-up 838.5 d (SD 291.9) in the GLP1RA cohort and 884.3 d (SD 313.7) in the non-GLP1RA group, GLP1RA use was associated with a 43% lower all-cause mortality (7.0% versus 12.9%; hazard ratio [HR], 0.566; 95% confidence interval [CI], 0.381-0.841) and 39% fewer hospitalizations (60.4% versus 74.5%; HR, 0.613; 95% CI, 0.530-0.710). Acute heart failure (HR, 0.386; 95% CI, 0.285-0.524), renal failure/dialysis (HR, 0.489; 95% CI, 0.413-0.579), and respiratory failure (HR, 0.484; 95% CI, 354-0.662) risks were significantly reduced. No differences were observed in graft failure/rejection, myocardial infarction, stroke, atrial fibrillation/flutter, ventricular tachycardia, or ischemic optic neuropathy. Conclusions. Early GLP1RA initiation in liver transplant recipients was associated with reduced mortality, hospitalizations, respiratory, and cardiorenal complications without compromising graft safety. These findings support GLP1RAs as a promising adjunct therapy, warranting prospective trials to confirm benefits in this high-risk population.

Aims Increased LV wall thickness is frequently encountered in transthoracic echocardiography (TTE). While accurate and early diagnosis is clinically important, given the differences in available therapeutic options and prognosis, an extensive workup is often required to establish the diagnosis. We propose the first echo-based, automated deep learning model with a fusion architecture to facilitate the evaluation and diagnosis of increased left ventricular (LV) wall thickness. Methods and Results Patients with an established diagnosis of increased LV wall thickness (hypertrophic cardiomyopathy (HCM), cardiac amyloidosis (CA), and hypertensive heart disease (HTN)/others) between 1/2015 to 11/2019 at Mayo Clinic Arizona were identified. The cohort was divided into 80%/10%/10% for training, validation, and testing sets, respectively. Six baseline TTE views were used to optimize a pre-trained InceptionResnetV2 model. Each model output was used to train a meta-learner under a fusion architecture. Model performance was assessed by multiclass area under the receiver operating characteristic curve (AUROC). A total of 586 patients were used for the final analysis (194 HCM, 201 CA, and 191 HTN/others). The mean age was 55.0 years, and 57.8% were male. Among the individual view-dependent models, the apical 4 chamber model had the best performance (AUROC: HCM: 0.94, CA: 0.73, and HTN/other: 0.87). The final fusion model outperformed all the view-dependent models (AUROC: CA: 0.90, HCM: 0.93, and HTN/other: 0.92). Conclusion The echo-based InceptionResnetV2 fusion model can accurately classify the main etiologies of increased LV wall thickness and can facilitate the process of diagnosis and workup.