Sacubitril/valsartan for the treatment of non-obstructive hypertrophic cardiomyopathy: An open label randomized controlled trial (SILICOFCM).

AIM: Sacubitril/valsartan treatment reduces mortality and hospitalizations in heart failure with reduced ejection fraction but has limited application in hypertrophic cardiomyopathy (HCM). The aim of this study was to evaluate the effect of sacubitril/valsartan on peak oxygen consumption (VO2) in patients with non-obstructive HCM. METHODS AND RESULTS: This is a phase II, randomized, open-label multicentre study that enrolled adult patients with symptomatic non-obstructive HCM (New York Heart Association class I-III) who were randomly assigned (2:1) to receive sacubitril/valsartan (target dose 97/103 mg) or control for 16 weeks. The primary endpoint was a change in peak VO2. Secondary endpoints included echocardiographic measures of cardiac structure and function, natriuretic peptides and other cardiac biomarkers, and Minnesota Living with Heart Failure quality of life. Between May 2018 and October 2021, 354 patients were screened for eligibility, 115 patients (mean age 58 years, 37% female) met the study inclusion criteria and were randomly assigned to sacubitril/valsartan (n = 79) or control (n = 36). At 16 weeks, there was no significant change in peak VO2 from baseline in the sacubitril/valsartan (15.3 [4.3] vs. 15.9 [4.3] ml/kg/min, p = 0.13) or control group (p = 0.47). No clinically significant changes were found in blood pressure, cardiac structure and function, plasma biomarkers, or quality of life. CONCLUSION: In patients with HCM, a 16-week treatment with sacubitril/valsartan was well tolerated but had no effect on exercise capacity, cardiac structure, or function.

A "smart" Imputation Approach for Effective Quality Control Across Complex Clinical Data Structures.

The overwhelming need to improve the quality of complex data structures in healthcare is more important than ever. Although data quality has been the point of interest in many studies, none of them has focused on the development of quantitative and explainable methods for data imputation. In this work, we propose a "smart" imputation workflow to address missing data across complex data structures in the context of in silico clinical trials. AI algorithms were utilized to produce high-quality virtual patient profiles. A search algorithm was then developed to extract the best virtual patient profiles through the definition of a profile matching score (PMS). A case study was conducted, where the real dataset was randomly contaminated with multiple missing values (e.g., 10 to 50%). In total, 10000 virtual patient profiles with less than 0.02 Kullback-Leibler (KL) divergence were produced to estimate the PMS distribution. The best generator achieved the lowest average squared absolute difference (0.4) and average correlation difference (0.02) with the real dataset highlighting its increased effectiveness for data imputation across complex clinical data structures.

The friend within? The implantable cardioverter defibrillator between saving lives and chronically impairing them.

This article considers the way in which a medical technology, the implantable cardioverter defibrillator (ICD), by preventing fatal outcomes, in this case sudden death, deriving from cardiac diseases, and specifically hypertrophic cardiomyopathy, contributes to the development of a particular type of chronicity. While biomedicine celebrates technological advances in treatments and naturalises chronicity, focussing on life expectancy as a victory over the 'acute' aspects of the disease, the way in which patients live with the disease is left unquestioned. The article follows Smith-Morris's (2010) perspective in seeing chronicity as the never-ending process of identifying with one's disease, adding a focus on the role played by an embodied technology in relation to it. Based on participant observation in a clinical setting and interviews with clinicians, the article interrogates three key themes in the chronicity of cardiac patients implanted with an ICD: risk, quality of life and choice. The data shows a constant tension between managing a one-off potentially fatal 'acute' risk and life with serious disruptions due to the limitations imposed by the implanted device. The article argues that patients' resources for facing the life and identity disrupted by the disease are limited by ideas of what living a diseased body is, which acritically follow discourses of 'patient choice' and a 'technological imperative' to avoid risk.

Gender Related Differences in the Clinical Presentation of Hypertrophic Cardiomyopathy-An Analysis from the SILICOFCM Database.

Background and Objectives: Hypertrophic cardiomyopathy (HCM) is the most common inherited cardiac disease that affects approximately 1 in 500 people. Due to an incomplete disease penetrance associated with numerous factors, HCM is not manifested in all carriers of genetic mutation. Although about two-thirds of patients are male, it seems that female gender is associated with more severe disease phenotype and worse prognosis. The objective of this study was to evaluate the gender related differences in HCM presentation. Materials and Methods: This study was conducted as a part of the international multidisciplinary SILICOFCM project. Clinical information, laboratory analyses, electrocardiography, echocardiography, and genetic testing data were collected for 362 HCM patients from four clinical centers (Florence, Newcastle, Novi Sad, and Regensburg). There were 33% female patients, and 67% male patients. Results: Female patients were older than males (64.5 vs. 53.5 years, p < 0.0005). The male predominance was present across all age groups until the age of 70, when gender distribution became comparable. Females had higher number of symptomatic individuals then males (69% vs. 52%, p = 0.003), most frequently complaining of dyspnea (50% vs. 30%), followed by chest pain (30% vs. 17%), fatigue (26% vs. 13%), palpitations (22% vs. 13%), and syncope (13% vs. 8%). The most common rhythm disorder was atrial fibrillation which was present in a similar number of females and males (19% vs. 13%, p = 0.218). Levels of N-terminal pro-brain natriuretic peptide were comparable between the genders (571 vs. 794 ng/L, p = 0.244). Echocardiography showed similar thickness of interventricular septum (18 vs. 16 mm, p = 0.121) and posterolateral wall (13 vs. 12 mm, p = 0.656), however, females had a lower number of systolic anterior motion (8% vs. 16%, p = 0.020) and other mitral valve abnormalities. Conclusions: Female patients are underrepresented but seem to have a more pronounced clinical presentation of HCM. Therefore, establishing gender specific diagnostic criteria for HCM should be considered.

Disease Progression of Hypertrophic Cardiomyopathy: Modeling Using Machine Learning.

BACKGROUND: Cardiovascular disorders in general are responsible for 30% of deaths worldwide. Among them, hypertrophic cardiomyopathy (HCM) is a genetic cardiac disease that is present in about 1 of 500 young adults and can cause sudden cardiac death (SCD). OBJECTIVE: Although the current state-of-the-art methods model the risk of SCD for patients, to the best of our knowledge, no methods are available for modeling the patient's clinical status up to 10 years ahead. In this paper, we propose a novel machine learning (ML)-based tool for predicting disease progression for patients diagnosed with HCM in terms of adverse remodeling of the heart during a 10-year period. METHODS: The method consisted of 6 predictive regression models that independently predict future values of 6 clinical characteristics: left atrial size, left atrial volume, left ventricular ejection fraction, New York Heart Association functional classification, left ventricular internal diastolic diameter, and left ventricular internal systolic diameter. We supplemented each prediction with the explanation that is generated using the Shapley additive explanation method. RESULTS: The final experiments showed that predictive error is lower on 5 of the 6 constructed models in comparison to experts (on average, by 0.34) or a consortium of experts (on average, by 0.22). The experiments revealed that semisupervised learning and the artificial data from virtual patients help improve predictive accuracies. The best-performing random forest model improved R2 from 0.3 to 0.6. CONCLUSIONS: By engaging medical experts to provide interpretation and validation of the results, we determined the models' favorable performance compared to the performance of experts for 5 of 6 targets.

Bayesian Inference-Based Gaussian Mixture Models With Optimal Components Estimation Towards Large-Scale Synthetic Data Generation for In Silico Clinical Trials.

Goal: To develop a computationally efficient and unbiased synthetic data generator for large-scale in silico clinical trials (CTs). Methods: We propose the BGMM-OCE, an extension of the conventional BGMM (Bayesian Gaussian Mixture Models) algorithm to provide unbiased estimations regarding the optimal number of Gaussian components and yield high-quality, large-scale synthetic data at reduced computational complexity. Spectral clustering with efficient eigenvalue decomposition is applied to estimate the hyperparameters of the generator. A case study is conducted to compare the performance of BGMM-OCE against four straightforward synthetic data generators for in silico CTs in hypertrophic cardiomyopathy (HCM). Results: The BGMM-OCE generated 30000 virtual patient profiles having the lowest coefficient-of-variation (0.046), inter- and intra-correlation differences (0.017, and 0.016, respectively) with the real ones in reduced execution time. Conclusions: BGMM-OCE overcomes the lack of population size in HCM which obscures the development of targeted therapies and robust risk stratification models.

Variational Gaussian Mixture Models with robust Dirichlet concentration priors for virtual population generation in hypertrophic cardiomyopathy: a comparison study.

Nowadays, there is a growing need for the development of computationally efficient virtual population generators for large-scale in-silico clinical trials. In this work, we utilize the Gaussian Mixture Models (GMM) with variational Bayesian inference (BGMM) using robust estimations of Dirichlet concentration priors for the generation of virtual populations. The estimations were based on an exponential transformation of the number of Gaussian components. The proposed method was compared against state-of-the-art virtual data generators, such as, the Bayesian networks, the supervised tree ensembles (STE), the unsupervised tree ensembles (UTE), and the artificial neural networks (ANN) towards the generation of 20000 virtual patients with hypertrophic cardiomyopathy (HCM). Our results suggest that the proposed BGMM can yield virtual distributions with small inter- and intra-correlation difference (0.013 and 0.012), in lower execution time (4.321 sec) than STE which achieved the second-best performance.

A machine learning-based risk stratification model for ventricular tachycardia and heart failure in hypertrophic cardiomyopathy.

BACKGROUND: Machine learning (ML) and artificial intelligence are emerging as important components of precision medicine that enhance diagnosis and risk stratification. Risk stratification tools for hypertrophic cardiomyopathy (HCM) exist, but they are based on traditional statistical methods. The aim was to develop a novel machine learning risk stratification tool for the prediction of 5-year risk in HCM. The goal was to determine if its predictive accuracy is higher than the accuracy of the state-of-the-art tools. METHOD: Data from a total of 2302 patients were used. The data were comprised of demographic characteristics, genetic data, clinical investigations, medications, and disease-related events. Four classification models were applied to model the risk level, and their decisions were explained using the SHAP (SHapley Additive exPlanations) method. Unwanted cardiac events were defined as sustained ventricular tachycardia occurrence (VT), heart failure (HF), ICD activation, sudden cardiac death (SCD), cardiac death, and all-cause death. RESULTS: The proposed machine learning approach outperformed the similar existing risk-stratification models for SCD, cardiac death, and all-cause death risk-stratification: it achieved higher AUC by 17%, 9%, and 1%, respectively. The boosted trees achieved the best performing AUC of 0.82. The resulting model most accurately predicts VT, HF, and ICD with AUCs of 0.90, 0.88, and 0.87, respectively. CONCLUSIONS: The proposed risk-stratification model demonstrates high accuracy in predicting events in patients with hypertrophic cardiomyopathy. The use of a machine-learning risk stratification model may improve patient management, clinical practice, and outcomes in general.

A computational pipeline for data augmentation towards the improvement of disease classification and risk stratification models: A case study in two clinical domains.

Virtual population generation is an emerging field in data science with numerous applications in healthcare towards the augmentation of clinical research databases with significant lack of population size. However, the impact of data augmentation on the development of AI (artificial intelligence) models to address clinical unmet needs has not yet been investigated. In this work, we assess whether the aggregation of real with virtual patient data can improve the performance of the existing risk stratification and disease classification models in two rare clinical domains, namely the primary Sjögren's Syndrome (pSS) and the hypertrophic cardiomyopathy (HCM), for the first time in the literature. To do so, multivariate approaches, such as, the multivariate normal distribution (MVND), and straightforward ones, such as, the Bayesian networks, the artificial neural networks (ANNs), and the tree ensembles are compared against their performance towards the generation of high-quality virtual data. Both boosting and bagging algorithms, such as, the Gradient boosting trees (XGBoost), the AdaBoost and the Random Forests (RFs) were trained on the augmented data to evaluate the performance improvement for lymphoma classification and HCM risk stratification. Our results revealed the favorable performance of the tree ensemble generators, in both domains, yielding virtual data with goodness-of-fit 0.021 and KL-divergence 0.029 in pSS and 0.029, 0.027 in HCM, respectively. The application of the XGBoost on the augmented data revealed an increase by 10.9% in accuracy, 10.7% in sensitivity, 11.5% in specificity for lymphoma classification and 16.1% in accuracy, 16.9% in sensitivity, 13.7% in specificity in HCM risk stratification.

Genetic determinants of clinical phenotype in hypertrophic cardiomyopathy.

BACKGROUND: Hypertrophic cardiomyopathy (HCM) is the most common inherited cardiovascular disease that affects approximately one in 500 people. HCM is a recognized genetic disorder most often caused by mutations involving myosin-binding protein C (MYBPC3) and ß-myosin heavy chain (MYH7) which are responsible for approximately three-quarters of the identified mutations. METHODS: As a part of the international multidisciplinary SILICOFCM project ( www.silicofcm.eu ) the present study evaluated the association between underlying genetic mutations and clinical phenotype in patients with HCM. Only patients with confirmed single pathogenic mutations in either MYBPC3 or MYH7 genes were included in the study and divided into two groups accordingly. The MYBPC3 group was comprised of 48 patients (76%), while the MYH7 group included 15 patients (24%). Each patient underwent clinical examination and echocardiography. RESULTS: The most prevalent symptom in patients with MYBPC3 was dyspnea (44%), whereas in patients with MYH7 it was palpitations (33%). The MYBPC3 group had a significantly higher number of patients with a positive family history of HCM (46% vs. 7%; p = 0.014). There was a numerically higher prevalence of atrial fibrillation in the MYH7 group (60% vs. 35%, p = 0.085). Laboratory analyses revealed normal levels of creatinine (85.5 ± 18.3 vs. 81.3 ± 16.4 µmol/l; p = 0.487) and blood urea nitrogen (10.2 ± 15.6 vs. 6.9 ± 3.9 mmol/l; p = 0.472) which were similar in both groups. The systolic anterior motion presence was significantly more frequent in patients carrying MYH7 mutation (33% vs. 10%; p = 0.025), as well as mitral leaflet abnormalities (40% vs. 19%; p = 0.039). Calcifications of mitral annulus were registered only in MYH7 patients (20% vs. 0%; p = 0.001). The difference in diastolic function, i.e. E/e' ratio between the two groups was also noted (MYBPC3 8.8 ± 3.3, MYH7 13.9 ± 6.9, p = 0.079). CONCLUSIONS: Major findings of the present study corroborate the notion that MYH7 gene mutation patients are presented with more pronounced disease severity than those with MYBPC3.

Generation of virtual patient data for in-silico cardiomyopathies drug development using tree ensembles: a comparative study.

In-silico clinical platforms have been recently used as a new revolutionary path for virtual patients (VP) generation and further analysis, such as, drug development. Advanced individualized models have been developed to enhance flexibility and reliability of the virtual patient cohorts. This study focuses on the implementation and comparison of three different methodologies for generating virtual data for in-silico clinical trials. Towards this direction, three computational methods, namely: (i) the multivariate log-normal distribution (log- MVND), (ii) the supervised tree ensembles, and (iii) the unsupervised tree ensembles are deployed and evaluated against their performance towards the generation of high-quality virtual data using the goodness of fit (gof) and the dataset correlation matrix as performance evaluation measures. Our results reveal the dominance of the tree ensembles towards the generation of virtual data with similar distributions (gof values less than 0.2) and correlation patterns (average difference less than 0.03).

Doctor-patient care relationship in genetic cardiomyopathies: An exploratory study on clinical consultations.

BACKGROUND: The present study aims to explore the setting of consultation and communication between physicians and patients affected by genetic cardiomyopathies, investigating how the two parts of the therapeutic relationship participate and share information. METHODS AND RESULTS: 45 adult patients affected by various cardiomyopathies took part in a prospective case study while attending consultations at a cardiologic outpatient clinic constituting an Italian referral centre for cardiomyopathies. A researcher observed the consultations, which were audio-recorded and transcribed. Transcripts were coded and an analysis of setting, type of communication implemented and participation of doctors and patients in terms of word-count and type of questions/answers was carried out. Overall word-count was significantly higher for physicians than for patients (t(44) = 9,506; p<0.001). Doctors were prone to ask closed questions (t(44) = -11,90; p<0.001) while patients preferred open answers (t(44) = 5.58; p<0.001), enriched with subjective issues related to their illness experience. Partial correlation highlights a significant positive relation between doctors' closed question and patients' open answers (r = .838; p<0.001). CONCLUSIONS: Findings emphasize patients' need for adequate time and space to share their subjective illness experience with the physician, within an approach informed by the insights and recommendations of Narrative Medicine. These findings are instrumental to improving the specific clinical setting for individuals with genetic cardiomyopathies.

Design of the SILICOFCM study: Effect of sacubitril/valsartan vs lifestyle intervention on functional capacity in patients with hypertrophic cardiomyopathy.

BACKGROUND: Hypertrophic cardiomyopathy (HCM) is the most common genetic cardiovascular disease with a broad spectrum of disease severity. HCM ranges from a benign course to a progressive disorder characterized by angina, heart failure, malignant arrhythmia, syncope, or sudden cardiac death. So far, no medical treatment has reliably shown to halt or reverse progression of HCM or to alleviate its symptoms. While the angiotensin receptor neprilysin inhibitor sacubitril/valsartan has shown to reduce mortality and hospitalization in heart failure with reduced ejection fraction, data on its effect on HCM are sparse. HYPOTHESIS: A 4-month pharmacological (sacubitril/valsartan) or lifestyle intervention will significantly improve exercise tolerance (ie, peak oxygen consumption) in patients with nonobstructive HCM compared to the optimal standard therapy (control group). METHODS: SILICOFCM is a prospective, multicenter, open-label, randomized, controlled, three-arm clinical trial (NCT03832660) that will recruit 240 adult patients with a confirmed diagnosis of nonobstructive HCM. Eligible patients are randomized to sacubitril/valsartan, lifestyle intervention (physical activity and dietary supplementation with inorganic nitrate), or optimal standard therapy alone (control group). The primary endpoint is the change in functional capacity (ie, peak oxygen consumption). Secondary endpoints include: (a) Change in cardiac structure and function as assessed by transthoracic echocardiography and cardiac magnetic resonance (MRI imaging), (b) change in biomarkers (ie, CK, CKMB, and NT-proBNP), (c) physical activity, and (d) quality of life. RESULTS: Until December 2019, a total of 41 patients were recruited into the ongoing SILICOFCM study and were allocated to the study groups and the control group. There was no significant difference in key baseline characteristics between the three groups. CONCLUSION: The SILICOFCM study will provide novel evidence about the effect of sacubitril/valsartan or lifestyle intervention on functional capacity, clinical phenotype, injury and stretch activation markers, physical activity, and quality of life in patients with nonobstructive HCM.

Defining the diagnostic effectiveness of genes for inclusion in panels: the experience of two decades of genetic testing for hypertrophic cardiomyopathy at a single center.

PURPOSE: Genetic testing in hypertrophic cardiomyopathy (HCM) has long relied on Sanger sequencing of sarcomeric genes. The advent of next-generation sequencing (NGS) has catalyzed routine testing of additional genes of dubious HCM-causing potential. We used 19 years of genetic testing results to define a reliable set of genes implicated in Mendelian HCM and assess the value of expanded NGS panels. METHODS: We dissected genetic testing results from 1,198 single-center HCM probands and devised a widely applicable score to identify which genes yield effective results in the diagnostic setting. RESULTS: Compared with early panels targeting only fully validated sarcomeric HCM genes, expanded NGS panels allow the prompt recognition of probands with HCM-mimicking diseases. Scoring by "diagnostic effectiveness" highlighted that PLN should also be routinely screened besides historically validated genes for HCM and its mimics. CONCLUSION: The additive value of expanded panels in HCM genetic testing lies in the systematic screening of genes associated with HCM mimics, requiring different patient management. Only variants in a limited set of genes are highly actionable and interpretable in the clinic, suggesting that larger panels offer limited additional sensitivity. A score estimating the relative effectiveness of a given gene's inclusion in diagnostic panels is proposed.