The prognostic value of artificial intelligence to predict cardiac amyloidosis in patients with severe aortic stenosis undergoing transcatheter aortic valve replacement.

Aims: Cardiac amyloidosis (CA) is common in patients with severe aortic stenosis (AS) undergoing transcatheter aortic valve replacement (TAVR). Cardiac amyloidosis has poor outcomes, and its assessment in all TAVR patients is costly and challenging. Electrocardiogram (ECG) artificial intelligence (AI) algorithms that screen for CA may be useful to identify at-risk patients. Methods and results: In this retrospective analysis of our institutional National Cardiovascular Disease Registry (NCDR)-TAVR database, patients undergoing TAVR between January 2012 and December 2018 were included. Pre-TAVR CA probability was analysed by an ECG AI predictive model, with >50% risk defined as high probability for CA. Univariable and propensity score covariate adjustment analyses using Cox regression were performed to compare clinical outcomes between patients with high CA probability vs. those with low probability at 1-year follow-up after TAVR. Of 1426 patients who underwent TAVR (mean age 81.0 ± 8.5 years, 57.6% male), 349 (24.4%) had high CA probability on pre-procedure ECG. Only 17 (1.2%) had a clinical diagnosis of CA. After multivariable adjustment, high probability of CA by ECG AI algorithm was significantly associated with increased all-cause mortality [hazard ratio (HR) 1.40, 95% confidence interval (CI) 1.01-1.96, P = 0.046] and higher rates of major adverse cardiovascular events (transient ischaemic attack (TIA)/stroke, myocardial infarction, and heart failure hospitalizations] (HR 1.36, 95% CI 1.01-1.82, P = 0.041), driven primarily by heart failure hospitalizations (HR 1.58, 95% CI 1.13-2.20, P = 0.008) at 1-year follow-up. There were no significant differences in TIA/stroke or myocardial infarction. Conclusion: Artificial intelligence applied to pre-TAVR ECGs identifies a subgroup at higher risk of clinical events. These targeted patients may benefit from further diagnostic evaluation for CA.

Effect of long-term tafamidis treatment on health-related quality of life in patients with transthyretin amyloid cardiomyopathy.

AIMS: To evaluate the effect of long-term tafamidis treatment on health-related quality of life (HRQoL) in patients with transthyretin amyloid cardiomyopathy (ATTR-CM) enrolled in the Tafamidis in Transthyretin Cardiomyopathy Clinical Trial (ATTR-ACT) and long-term extension (LTE) study. METHODS AND RESULTS: We examined change from baseline in Kansas City Cardiomyopathy Questionnaire overall summary (KCCQ-OS) and clinical summary (KCCQ-CS) scores in patients who received tafamidis meglumine 80 mg for 30 months in ATTR-ACT and tafamidis (meglumine 80 mg or bioequivalent free acid 61 mg) for 30 months in the LTE study, and in patients who received placebo for 30 months in ATTR-ACT and tafamidis for 30 months in the LTE study. In ATTR-ACT, 176 and 177 patients were randomized to tafamidis 80 mg and placebo, respectively. Patients who continuously received tafamidis had a 6- to 7-point reduction in least squares (LS) mean (standard error) KCCQ-OS and KCCQ-CS scores at month 30 (-6.25 [1.53] and -7.48 [1.39]), with little or no further decline over the next 30 months (-5.92 [1.77] and -9.21 [1.88] at month 60). Patients who received placebo in ATTR-ACT had a 20-point reduction in LS mean KCCQ-OS and KCCQ-CS scores at month 30 (-19.60 [1.94] and -19.90 [2.01]), but the decline slowed after initiating tafamidis (-24.70 [3.04] and -25.30 [3.36] at month 60). CONCLUSION: Tafamidis reduced HRQoL decline in patients with ATTR-CM. Patients continuously treated with tafamidis for 60 months demonstrated stabilized HRQoL. In patients who initially received placebo in ATTR-ACT, tafamidis reduced the decline in HRQoL during the LTE study.

Histological Typing in Patients With Cardiac Amyloidosis: JACC Review Topic of the Week.

Cardiac amyloidosis is increasingly recognized as a treatable form of heart failure. Highly effective specific therapies have recently become available for the 2 most frequent forms of cardiac amyloidosis: immunoglobulin light chain amyloidosis and transthyretin (ATTR) amyloidosis. Nevertheless, initiation of specific therapies requires recognition of cardiac amyloidosis and appropriate characterization of the amyloid type. Although noninvasive diagnosis is possible for ATTR cardiac amyloidosis, histological demonstration and typing of amyloid deposits is still required for a substantial number of patients with ATTR and in all patients with light chain amyloidosis and other rarer forms of cardiac amyloidosis. Amyloid histological typing can be performed using different techniques: mass spectrometry, immunohistochemistry, and immunoelectron microscopy. This review describes which patients require histological confirmation of cardiac amyloidosis along with when and how to type amyloid deposits in histologic specimens. Furthermore, it covers the characteristics and limitations of the different typing methods that are available in clinical practice.

Impact of vutrisiran on exploratory cardiac parameters in hereditary transthyretin-mediated amyloidosis with polyneuropathy.

AIMS: HELIOS-A was a Phase 3, open-label study of vutrisiran, an RNA interference therapeutic, in patients with hereditary transthyretin (ATTRv) amyloidosis with polyneuropathy. This analysis evaluated vutrisiran's impact on exploratory cardiac endpoints in HELIOS-A patients. METHODS AND RESULTS: Patients were randomized 3:1 to subcutaneous vutrisiran 25 mg every 3 months or intravenous patisiran 0.3 mg/kg every 3 weeks (reference group) for 18 months. Exploratory cardiac endpoints included change from baseline in N-terminal prohormone of brain-type natriuretic peptide (NT-proBNP) and echocardiographic parameters versus external placebo (APOLLO study). The modified intent-to-treat (mITT) population comprised randomized patients receiving any study drug (n = 122). A cardiac subpopulation with evidence of cardiac amyloid involvement (n = 40) was prespecified. 99mTc scintigraphy exploratory assessments in a planned vutrisiran-treated cohort at select sites were compared with baseline. At Month 18, vutrisiran demonstrated beneficial effects on NT-proBNP versus external placebo in the mITT and cardiac subpopulations (adjusted geometric mean fold change ratio [95% confidence interval] 0.480 [0.383-0.600], p = 9.606 × 10-10 and 0.491 [0.337-0.716], p = 0.0004, respectively). Benefits or trends towards benefit in echocardiographic parameters versus external placebo were observed for both populations. In 99mTc scintigraphy assessments, 32/47 (68.1%) and 31/48 (64.6%) patients exhibited reduced normalized left ventricular total uptake and heart-to-contralateral lung ratio, respectively. Perugini grade was reduced or unchanged versus baseline in 55/57 (96.5%) evaluable patients. No increase in cardiac adverse events was observed with vutrisiran versus external placebo. CONCLUSIONS: Vutrisiran demonstrated evidence of potential benefit on cardiac manifestations in patients with ATTRv amyloidosis with polyneuropathy, with an acceptable safety profile.

Efficacy and Safety of Acoramidis in Transthyretin Amyloid Cardiomyopathy.

BACKGROUND: Transthyretin amyloid cardiomyopathy is characterized by the deposition of misfolded monomeric transthyretin (TTR) in the heart. Acoramidis is a high-affinity TTR stabilizer that acts to inhibit dissociation of tetrameric TTR and leads to more than 90% stabilization across the dosing interval as measured ex vivo. METHODS: In this phase 3, double-blind trial, we randomly assigned patients with transthyretin amyloid cardiomyopathy in a 2:1 ratio to receive acoramidis hydrochloride at a dose of 800 mg twice daily or matching placebo for 30 months. Efficacy was assessed in the patients who had an estimated glomerular filtration rate of at least 30 ml per minute per 1.73 m2 of body-surface area. The four-step primary hierarchical analysis included death from any cause, cardiovascular-related hospitalization, the change from baseline in the N-terminal pro-B-type natriuretic peptide (NT-proBNP) level, and the change from baseline in the 6-minute walk distance. We used the Finkelstein-Schoenfeld method to compare all potential pairs of patients within strata to generate a P value. Key secondary outcomes were death from any cause, the 6-minute walk distance, the score on the Kansas City Cardiomyopathy Questionnaire-Overall Summary, and the serum TTR level. RESULTS: A total of 632 patients underwent randomization. The primary analysis favored acoramidis over placebo (P<0.001); the corresponding win ratio was 1.8 (95% confidence interval [CI], 1.4 to 2.2), with 63.7% of pairwise comparisons favoring acoramidis and 35.9% favoring placebo. Together, death from any cause and cardiovascular-related hospitalization contributed more than half the wins and losses to the win ratio (58% of all pairwise comparisons); NT-proBNP pairwise comparisons yielded the highest ratio of wins to losses (23.3% vs. 7.0%). The overall incidence of adverse events was similar in the acoramidis group and the placebo group (98.1% and 97.6%, respectively); serious adverse events were reported in 54.6% and 64.9% of the patients. CONCLUSIONS: In patients with transthyretin amyloid cardiomyopathy, the receipt of acoramidis resulted in a significantly better four-step primary hierarchical outcome containing components of mortality, morbidity, and function than placebo. Adverse events were similar in the two groups. (Funded by BridgeBio Pharma; ATTRibute-CM ClinicalTrials.gov number, NCT03860935.).

Phenotypic characteristics of F64L, I68L, I107V, and S77Y ATTRv genotypes from the Transthyretin Amyloidosis Outcomes Survey (THAOS).

Transthyretin amyloidosis (ATTR amyloidosis) is a progressive, multi-systemic disease with wild-type (ATTRwt) and hereditary (ATTRv) forms. Over 130 variants associated with ATTRv amyloidosis have been identified, although little is known about the majority of these genotypes. This analysis examined phenotypic characteristics of symptomatic patients with ATTRv amyloidosis enrolled in the Transthyretin Amyloidosis Outcomes Survey (THAOS) with four less frequently reported pathogenic genotypes: F64L (c.250T>C, p.F84L), I68L (c.262A>T, p.I88L), I107V (c.379A>G; p.I127V), and S77Y (c.290C>A; p.S97Y). THAOS is the largest ongoing, global, longitudinal observational study of patients with ATTR amyloidosis, including both ATTRwt and ATTRv amyloidosis. This analysis describes the baseline demographic and clinical characteristics of untreated symptomatic patients with the F64L, I68L, I107V, or S77Y genotypes at enrollment in THAOS (data cutoff date: January 4, 2022). There were 141 symptomatic patients with F64L (n = 46), I68L (n = 45), I107V (n = 21), or S77Y (n = 29) variants at the data cutoff. Most patients were male and median age at enrollment was in the sixth decade for S77Y patients and the seventh decade for the others. A predominantly neurologic phenotype was associated with F64L, I107V, and S77Y genotypes, whereas patients with the I68L genotype presented with more pronounced cardiac involvement. However, a mixed phenotype was also reported in a considerable proportion of patients in each variant subgroup. This analysis from THAOS represents the largest study of ATTRv symptomatic patients with the F64L, I68L, I107V, and S77Y genotypes. These data add to the limited knowledge on the clinical profile of patients with specific ATTRv variants and emphasize the importance of comprehensive assessment of all patients. Trial registration ClinicalTrials.gov: NCT00628745.

Echocardiography-Based Deep Learning Model to Differentiate Constrictive Pericarditis and Restrictive Cardiomyopathy.

BACKGROUND: Constrictive pericarditis (CP) is an uncommon but reversible cause of diastolic heart failure if appropriately identified and treated. However, its diagnosis remains a challenge for clinicians. Artificial intelligence may enhance the identification of CP. OBJECTIVES: The authors proposed a deep learning approach based on transthoracic echocardiography to differentiate CP from restrictive cardiomyopathy. METHODS: Patients with a confirmed diagnosis of CP and cardiac amyloidosis (CA) (as the representative disease of restrictive cardiomyopathy) at Mayo Clinic Rochester from January 2003 to December 2021 were identified to extract baseline demographics. The apical 4-chamber view from transthoracic echocardiography studies was used as input data. The patients were split into a 60:20:20 ratio for training, validation, and held-out test sets of the ResNet50 deep learning model. The model performance (differentiating CP and CA) was evaluated in the test set with the area under the curve. GradCAM was used for model interpretation. RESULTS: A total of 381 patients were identified, including 184 (48.3%) CP, and 197 (51.7%) CA cases. The mean age was 68.7 ± 11.4 years, and 72.8% were male. ResNet50 had a performance with an area under the curve of 0.97 to differentiate the 2-class classification task (CP vs CA). The GradCAM heatmap showed activation around the ventricular septal area. CONCLUSIONS: With a standard apical 4-chamber view, our artificial intelligence model provides a platform to facilitate the detection of CP, allowing for improved workflow efficiency and prompt referral for more advanced evaluation and intervention of CP.

Emerging Role of Scintigraphy Using Bone-Seeking Tracers for Diagnosis of Cardiac Amyloidosis: AJR Expert Panel Narrative Review.

Amyloidoses are a complex group of clinical diseases that result from progressive organ dysfunction due to extracellular protein misfolding and deposition. The two most common types of cardiac amyloidosis are transthyretin amyloidosis (ATTR) and light-chain (AL) amyloidosis. Diagnosis of ATTR cardiomyopathy (ATTR-CM) is challenging owing to its phenotypic similarity to other more common cardiac conditions, the perceived rarity of the disease, and unfamiliarity with its diagnostic algorithms; endomyocardial biopsy was historically required for diagnosis. However, myocardial scintigraphy using bone-seeking tracers has shown high accuracy for detection of ATTR-CM and has become a key noninvasive diagnostic test for the condition, receiving support from professional society guidelines and transforming prior diagnostic paradigms. This AJR Expert Panel Narrative Review describes the role of myocardial scintigraphy using bone-seeking tracers in the diagnosis of ATTR-CM. The article summarizes available tracers, acquisition techniques, interpretation and reporting considerations, diagnostic pitfalls, and gaps in the current literature. The critical need for monoclonal testing of patients with positive scintigraphy results to differentiate ATTR-CM from AL cardiac amyloidosis is highlighted. Recent updates in guideline recommendations that emphasize the importance of a qualitative visual assessment are also discussed.

Outcomes of transcatheter aortic valve replacement in patients with and without amyloidosis: A nationwide analysis from the United States.

BACKGROUND: Amyloidosis is a common comorbidity in elderly patients with aortic stenosis (AS) referred for transcatheter aortic valve replacement (TAVR). This study aims to assess the impact of amyloidosis on the clinical outcomes of TAVR. METHODS: This is a retrospective study of the National Inpatient Sample database that identified adult patients (≥18 years) with AS hospitalized for TAVR from 2016 through 2020 to compare outcomes in those with versus without amyloidosis. Our primary outcome was in-hospital mortality. Secondary outcomes included procedural complications, hospital length of stay (LOS), and total costs. TAVR trends in both cohorts were also evaluated. RESULTS: The total cohort included 304,710 patients with AS undergoing TAVR, of whom 410 had amyloidosis. Over the study period, TAVR trends increased significantly in patients with and without amyloidosis (both ptrend < 0.01). Patients with amyloidosis were more likely to be older males with atrial fibrillation/flutter, congestive heart failure, renal disease, and dementia compared to non-amyloidosis patients. After adjustment for baseline characteristics, patients with amyloidosis had similar odds of in-hospital mortality (adjusted odds ratio [aOR] 1.66, 95 % confidence interval [CI] 0.34-3.63), heart block (aOR 1.33, 95 % CI 0.84-2.10), permanent pacemaker insertion (aOR 0.67, 95 % CI 0.27-1.66), stroke (aOR 0.90, 95 % CI 0.32-3.13), acute kidney injury, major bleeding, blood transfusion, vascular complications, in addition to similar LOS (p = 0.21) and total costs (p = 0.18) compared to patients without amyloidosis. CONCLUSION: In patients with AS undergoing TAVR, comorbid amyloidosis is associated with similar in-hospital mortality and procedural complications compared to patients without amyloidosis.

Clinical and Genotype Characteristics and Symptom Migration in Patients With Mixed Phenotype Transthyretin Amyloidosis from the Transthyretin Amyloidosis Outcomes Survey.

INTRODUCTION: Transthyretin amyloidosis (ATTR amyloidosis) is primarily associated with a cardiac or neurologic phenotype, but a mixed phenotype is increasingly described. METHODS: This study describes the mixed phenotype cohort in the Transthyretin Amyloidosis Outcomes Survey (THAOS). THAOS is an ongoing, longitudinal, observational survey of patients with ATTR amyloidosis, including both hereditary (ATTRv) and wild-type disease, and asymptomatic carriers of pathogenic transthyretin variants. Baseline characteristics of patients with a mixed phenotype (at enrollment or reclassified during follow-up) are described (data cutoff: January 4, 2022). RESULTS: Approximately one-third of symptomatic patients (n = 1185/3542; 33.5%) were classified at enrollment or follow-up as mixed phenotype (median age, 66.5 years). Of those, 344 (29.0%) were reclassified to mixed phenotype within a median 1-2 years of follow-up. Most patients with mixed phenotype had ATTRv amyloidosis (75.7%). The most frequent genotypes were V30M (38.9%) and wild type (24.3%). CONCLUSIONS: These THAOS data represent the largest analysis of a real-world mixed phenotype ATTR amyloidosis population to date and suggest that a mixed phenotype may be more prevalent than previously thought. Patients may also migrate from a primarily neurologic or cardiologic presentation to a mixed phenotype over time. These data reinforce the need for multidisciplinary evaluation at initial assessment and follow-up of all patients with ATTR amyloidosis. TRIAL REGISTRATION: ClinicalTrials.gov: NCT00628745.

A 15-year consolidated overview of data in over 6000 patients from the Transthyretin Amyloidosis Outcomes Survey (THAOS).

BACKGROUND: Transthyretin amyloidosis (ATTR amyloidosis) is a progressive, multisystemic, life-threatening disease resulting from the deposition of variant or wild-type (ATTRwt amyloidosis) transthyretin amyloid fibrils in various tissues and organs. METHODS: Established in 2007, the Transthyretin Amyloidosis Outcomes Survey (THAOS) is the largest ongoing, global, longitudinal, observational study of patients with ATTR amyloidosis, including both hereditary and wild-type disease, and asymptomatic carriers of pathogenic TTR mutations. This analysis describes the baseline characteristics of symptomatic patients and asymptomatic gene carriers enrolled in THAOS since its inception in 2007 (data cutoff: August 1, 2022), providing a consolidated overview of 15-year data from the THAOS registry. RESULTS: This analysis included 4428 symptomatic patients and 1707 asymptomatic gene carriers. The majority of symptomatic patients were male (70.8%) with a mean (standard deviation [SD]) age at symptom onset of 56.6 (17.9) years. Compared with the 14-year analysis, V30M remained the most prevalent genotype in Europe (62.2%), South America (78.6%), and Japan (74.2%) and ATTRwt remained most common in North America (56.2%). Relative to the 14-year analysis, there was an increase of mixed phenotype (from 16.6 to 24.5%) and a reduction of predominantly cardiac phenotype (from 40.7 to 31.9%). The proportion of patients with predominantly neurologic phenotype remained stable (from 40.1 to 38.7%). Asymptomatic gene carriers were 58.5% female with a mean age at enrollment of 41.9 years (SD 15.5). CONCLUSIONS: This overview of > 6000 patients enrolled over 15 years in THAOS represents the largest registry analysis of ATTR amyloidosis to date and continues to emphasize the genotypic and phenotypic heterogeneity of the disease. Nearly a quarter of the symptomatic population within THAOS was mixed phenotype, underscoring the need for multidisciplinary management of ATTR amyloidosis. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT00628745.

Identification of amyloidosis of the urinary tract and prostate: Opportunities for early diagnosis & intervention in systemic disease.

OBJECTIVES: To determine the prevalence of different amyloid types and frequency of associated systemic amyloidosis in the urinary tract/prostate. METHODS: We studied Congo red-positive prostate (n = 150) and urinary tract (n = 767) specimens typed by a proteomics-based method between 2008 and 2020. Clinical follow up was available for a subset (urinary tract, n = 111; prostate, n = 17). Amyloid types were correlated with various clinicopathologic features. For patients with clinical follow up, chart review was performed to establish localized versus systemic disease, frequency of initial diagnosis of amyloidosis on urinary tract/prostate specimens, presence of cardiac disease, and death from disease-related complications. RESULTS: The most common amyloid types were AL/AH in urinary tract (479/767, 62 %) and localized ASem1 in prostate (64/150, 43 %). Urinary tract AL/AH amyloid was usually localized, but systemic AL amyloidosis occurred in both sites (urinary tract: 5/71, 7 %; prostate: 2/2, 100 %). ATTR amyloidosis was seen in over a third of cases (urinary tract: 286/767, 37 %; prostate: 55/150, 37 %). Urinary tract/prostate was the site of the initial ATTR amyloidosis diagnosis in 44/48 patients (92 %), and 38/48 (79 %) were subsequently found to have cardiac involvement. Seminal vesicle/ejaculatory duct involvement was pathognomonic for ASem1-type amyloidosis (39/39, 100 %). CONCLUSIONS: Over 40 % of patients had systemic amyloidosis, with urinary tract/prostate often the first site in which amyloid was identified. Since early recognition of systemic amyloidosis is critical for optimal patient outcomes, there should be a low threshold to perform Congo red stain. Proteomics-based amyloid typing is recommended since treatment depends on correctly identifying the amyloid type.

Challenges and solutions of echocardiography generalization for deep learning: a study in patients with constrictive pericarditis.

Purpose: The inherent characteristics of transthoracic echocardiography (TTE) images such as low signal-to-noise ratio and acquisition variations can limit the direct use of TTE images in the development and generalization of deep learning models. As such, we propose an innovative automated framework to address the common challenges in the process of echocardiography deep learning model generalization on the challenging task of constrictive pericarditis (CP) and cardiac amyloidosis (CA) differentiation. Approach: Patients with a confirmed diagnosis of CP or CA and normal cases from Mayo Clinic Rochester and Arizona were identified to extract baseline demographics and the apical 4 chamber view from TTE studies. We proposed an innovative preprocessing and image generalization framework to process the images for training the ResNet50, ResNeXt101, and EfficientNetB2 models. Ablation studies were conducted to justify the effect of each proposed processing step in the final classification performance. Results: The models were initially trained and validated on 720 unique TTE studies from Mayo Rochester and further validated on 225 studies from Mayo Arizona. With our proposed generalization framework, EfficientNetB2 generalized the best with an average area under the curve (AUC) of 0.96 (±0.01) and 0.83 (±0.03) on the Rochester and Arizona test sets, respectively. Conclusions: Leveraging the proposed generalization techniques, we successfully developed an echocardiography-based deep learning model that can accurately differentiate CP from CA and normal cases and applied the model to images from two sites. The proposed framework can be further extended for the development of echocardiography-based deep learning models.

Patisiran Treatment in Patients with Transthyretin Cardiac Amyloidosis.

BACKGROUND: Transthyretin amyloidosis, also called ATTR amyloidosis, is associated with accumulation of ATTR amyloid deposits in the heart and commonly manifests as progressive cardiomyopathy. Patisiran, an RNA interference therapeutic agent, inhibits the production of hepatic transthyretin. METHODS: In this phase 3, double-blind, randomized trial, we assigned patients with hereditary, also known as variant, or wild-type ATTR cardiac amyloidosis, in a 1:1 ratio, to receive patisiran (0.3 mg per kilogram of body weight) or placebo once every 3 weeks for 12 months. A hierarchical procedure was used to test the primary and three secondary end points. The primary end point was the change from baseline in the distance covered on the 6-minute walk test at 12 months. The first secondary end point was the change from baseline to month 12 in the Kansas City Cardiomyopathy Questionnaire-Overall Summary (KCCQ-OS) score (with higher scores indicating better health status). The second secondary end point was a composite of death from any cause, cardiovascular events, and change from baseline in the 6-minute walk test distance over 12 months. The third secondary end point was a composite of death from any cause, hospitalizations for any cause, and urgent heart failure visits over 12 months. RESULTS: A total of 360 patients were randomly assigned to receive patisiran (181 patients) or placebo (179 patients). At month 12, the decline in the 6-minute walk distance was lower in the patisiran group than in the placebo group (Hodges-Lehmann estimate of median difference, 14.69 m; 95% confidence interval [CI], 0.69 to 28.69; P = 0.02); the KCCQ-OS score increased in the patisiran group and declined in the placebo group (least-squares mean difference, 3.7 points; 95% CI, 0.2 to 7.2; P = 0.04). Significant benefits were not observed for the second secondary end point. Infusion-related reactions, arthralgia, and muscle spasms occurred more often among patients in the patisiran group than among those in the placebo group. CONCLUSIONS: In this trial, administration of patisiran over a period of 12 months resulted in preserved functional capacity in patients with ATTR cardiac amyloidosis. (Funded by Alnylam Pharmaceuticals; APOLLO-B ClinicalTrials.gov number, NCT03997383.).

Trends in the Prevalence of Infiltrative Cardiomyopathy Among Patients With in-Hospital Cardiac Arrest.

Sarcoidosis, amyloidosis, hemochromatosis and scleroderma are the most forms of infiltrative/nonischemic cardiomyopathy (NICM) associated with sudden cardiac death. In patients who undergo in-hospital cardiac arrest, a high index of suspicion is required to rule out NICM as an underlying contributor. We aimed to analyze the prevalence of NICM among patients with in-hospital cardiac arrest and identify factors associated with increased mortality. We analyzed data from the National Inpatient Sample, and identified patients who were hospitalized across 10 years from 2010 to 2019 with a diagnosis of cardiac arrest and NICM. The total number of patients with in-hospital cardiac arrest was 19,34,260. The total number with NICM was 14,803 (0.77%). Mean age was 63 years. Overall prevalence of NICM across the years ranged between 0.75% to 0.9%, with a significant temporal increase (P < 0.01). Incidence of in-hospital mortality ranged between 61% to 76% for females and 30% to 38% for males. The following comorbidities were more prevalent in patients with NICM than those without: heart failure, chronic obstructive pulmonary disease (COPD), chronic kidney disease, anemia, malignancy, coagulopathy, ventricular tachycardia, acute kidney injury and stroke. The following factors were independent predictors of in-hospital mortality-age, female gender, Hispanic race, history of COPD and presence of malignancy (P = 0.042). The prevalence of infiltrative cardiomyopathy in patients with in-hospital cardiac arrest is increasing. Females, older patients and Hispanic population are at an increased risk of mortality. Sex and race-based disparities in the prevalence of NICM in patients with in-hospital cardiac arrest is an area of further research.

Developing an Echocardiography-Based, Automatic Deep Learning Framework for the Differentiation of Increased Left Ventricular Wall Thickness Etiologies.

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.