Search

Aims:Increased left ventricular (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 and 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: HCM: 0.93, CA: 0.90, 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. [ABSTRACT FROM AUTHOR]

Patients with baseline thrombocytopenia can have increased mortality and morbidity, but are typically excluded from randomized clinical trials studying acute coronary syndromes (ACS). We sought to better define the effect thrombocytopenia on clinical outcomes in ACS patients. Patients identified from the NCDR Chest Pain registry at Mayo Clinic Arizona from Oct 2015 to Sep 2018 were retrospectively classified into two groups: TP (platelet <150 × 103 μL) and control (platelet ≥150 × 103 μL). The groups were analyzed for the clinical outcome (all-cause mortality, major adverse cardiac events (MACE), and bleeding events). The TP group was divided into moderate-severe thrombocytopenia (TP mod ; platelet 50–100 × 103 μL) and mild thrombocytopenia (TP mild ; platelet 100–150 × 103 μL) for further analysis. P -value <0.05 is considered significant. Five hundred and thirty-six patients were identified, and 72 patients (13%) had thrombocytopenia. The median follow-up time was 1.1 years. The TP group was older (TP vs. control: mean age 73 ± 13 years vs. 70 ± 13 years; P = 0.026). In patients discharged on dual-antiplatelet therapy, the TP group had higher all-cause mortality (23% vs. 7.3%; P = 0.007) but not major bleeding events (11% vs. 5.0%; P = 0.123). Only all-cause mortality increased with the severity of thrombocytopenia (TP mod vs. TP mild vs. control: 33% vs. 24% vs. 7.3%; P = 0.007). In patients with ACS, baseline thrombocytopenia is associated with increased all-cause mortality and all bleeding events without net MACE benefit. Further study is needed to identify the optimal antiplatelet strategy in this higher risk population. • Baseline thrombocytopenia in patients with ACS is associated with all-cause mortality and major bleeding events. • Thrombocytopenia should be considered as a surrogate marker of poor prognosis in patients with ACS. • In patients with ACS and thrombocytopenia, further study is needed to identify optimal antiplatelet strategies. [ABSTRACT FROM AUTHOR]