Search Results (42)

Arrhythmogenic cardiomyopathies (ACMs) are a phenotypically and etiologically heterogeneous group of myocardial disorders characterized by fibrotic or fibro-fatty replacement of ventricular myocardium, electrical instability, and an elevated risk of sudden cardiac death. Initially identified as a right ventricular disease, ACMs are now recognized to include biventricular and left-dominant forms. Genetic causes account for a substantial proportion of cases and include desmosomal variants, non-desmosomal variants, and familial gene-elusive forms with no identifiable pathogenic mutation. Nongenetic etiologies, including post-inflammatory, autoimmune, and infiltrative mechanisms, may mimic the phenotype. In many patients, the disease remains idiopathic despite comprehensive evaluation. Cardiac magnetic resonance imaging has emerged as a key tool for identifying non-ischemic scar patterns and for distinguishing arrhythmogenic phenotypes from other cardiomyopathies. Emerging classifications propose the unifying concept of scarring cardiomyopathies based on shared structural substrates, although global consensus is evolving. Risk stratification remains challenging, particularly in patients without overt systolic dysfunction or identifiable genetic markers. Advances in tissue phenotyping, multi-omics, and artificial intelligence hold promise for improved prognostic assessment and individualized therapy. Full article

Heart failure (HF) is a complex clinical syndrome that results from any structural or functional impairment of ventricular filling or ejection of blood. The etiology of heart failure is multifactorial, encompassing ischemic heart disease, hypertension, valvular disorders, cardiomyopathies, and metabolic and infiltrative diseases. Despite advances in pharmacologic and device-based therapies, heart failure continues to carry a substantial burden of morbidity, mortality, and healthcare utilization. With the advancement and increased accessibility of cardiac imaging modalities, the diagnostic accuracy for identifying the underlying etiologies of nonischemic cardiomyopathy has significantly improved, allowing for more precise classification and tailored management strategies. This review aims to provide a comprehensive analysis of the current understanding of heart failure, encompassing epidemiology, etiological factors, with a specific focus on diagnostic imaging modalities including the role of echocardiography and strain imaging, cardiac magnetic resonance imaging (CMR), cardiac computed tomography (CT), and nuclear positron emission tomography (PET) imaging and recent advances in the diagnosis and management of heart failure. Full article

The rise of wearable devices has enabled real-time processing of sensor data for critical health monitoring applications, such as human activity recognition (HAR) and cardiac disorder classification (CDC). However, the limited computational and memory resources of wearables necessitate lightweight yet accurate classification models. While deep neural networks (DNNs), including convolutional neural networks (CNNs) and long short-term memory networks, have shown high accuracy for HAR and CDC, their large parameter sizes hinder deployment on edge devices. On the other hand, various DNN compression techniques have been proposed, but exploiting the combination of various compression techniques with the aim of achieving memory efficient DNN models for HAR and CDC tasks remains under-investigated. This work studies the impact of CNN architecture parameters, focusing on the convolutional and dense layers, to identify configurations that balance accuracy and efficiency. We derive two versions of each model—lean and fat—based on their memory characteristics. Subsequently, we apply three complementary compression techniques: filter-based pruning, low-rank factorization, and dynamic range quantization. Experiments across three diverse DNNs demonstrate that this multi-faceted compression approach can significantly reduce memory and computational requirements while maintaining validation accuracy, leading to DNN models suitable for intelligent health monitoring on resource-constrained wearable devices. Full article

Cardiac computed tomography (CT) has rapidly advanced, becoming an invaluable tool for diagnosing and prognosticating various cardiovascular diseases. While echocardiography and cardiac magnetic resonance imaging (CMR) remain the gold standards for myocardial assessment, modern CT technologies offer enhanced spatial resolution, making it an essential tool in clinical practice. Cardiac CT has expanded beyond coronary artery disease evaluation, now playing a key role in assessing cardiomyopathies and structural heart diseases. Innovations like photon-counting CT enable precise estimation of myocardial extracellular volume, facilitating the detection of infiltrative disorders and myocardial fibrosis. Additionally, CT-based myocardial strain analysis allows for the classification of impaired myocardial contractility, while quantifying cardiac volumes and function remains crucial in cardiomyopathy evaluation. This review explores the emerging role of cardiac CT in cardiomyopathy phenotyping, emphasizing recent technological advancements. Full article

Brugada syndrome (BrS) is an inherited electrical cardiac disorder that is associated with a higher risk of ventricular fibrillation (VF) and sudden cardiac death (SCD) in patients without structural heart disease. The diagnosis is based on the documentation of the typical pattern in the electrocardiogram (ECG) characterized by a J-point elevation of ≥2 mm, coved-type ST-segment elevation, and negative T wave in one or more right precordial leads, called type 1 Brugada ECG. Risk stratification is particularly difficult in asymptomatic cases. Patients who have experienced documented VF are generally recommended to receive an implantable cardioverter defibrillator to lower the likelihood of sudden death due to recurrent episodes. However, for asymptomatic individuals, the most appropriate course of action remains uncertain. Accurate risk prediction is critical to avoiding premature deaths and unnecessary treatments. Due to the challenges associated with experimental research on human cardiac tissue, alternative techniques such as computational modeling and deep learning-based artificial intelligence (AI) are becoming increasingly important. This study introduces a vision transformer (ViT) model that leverages 12-lead ECG images to predict potentially fatal arrhythmic events in BrS patients. This dataset includes a total of 278 ECGs, belonging to 210 patients which have been diagnosed with Brugada syndrome, and it is split into two classes: event and no event. The event class contains 94 ECGs of patients with documented ventricular tachycardia, ventricular fibrillation, or sudden cardiac death, while the no event class is composed of 184 ECGs used as the control group. At first, the ViT is trained on a balanced dataset, achieving satisfactory results (89% accuracy, 94% specificity, 84% sensitivity, and 89% F1-score). Then, the discarded no event ECGs are attached to additional 30 event ECGs, extracted by a 24 h recording of a singular individual, composing a new test set. Finally, the use of an optimized classification threshold improves the predictions on an unbalanced set of data (74% accuracy, 95% negative predictive value, and 90% sensitivity), suggesting that the ECG signal can reveal key information for the risk stratification of patients with Brugada syndrome. Full article

22q11.2 is a region prone to chromosomal rearrangements due to the presence of eight large blocks of low-copy repeats (LCR22s). The 3 Mb 22q11.2 “typical deletion”, between LCR22-A and D, causes a fairly well-known clinical picture, while the effects of smaller CNVs harbored in this interval are still to be fully elucidated. Nested deletions, flanked by LCR22B-D, LCR22B-C, or LCR22C-D, are very rare and are collectively described as “central deletions”. The LCR22C-D deletion (CDdel) has never been separately analyzed. In this paper, we focused only on CDdel, evaluating its gene content and reviewing the literature and public databases in order to obtain new insights for the classification of this CNV. At first glance, CDdels are associated with a broad phenotypic spectrum, ranging from clinically normal to quite severe phenotypes. However, the frequency of specific clinical traits highlights that renal/urinary tract abnormalities, cardiac defects, and neurological/behavioral disorders are much more common in CDdel than in the general population. This frequency is too high to be fortuitous, indicating that CDdel is a predisposing factor for these phenotypic traits. Among the genes present in this interval, CRKL is an excellent candidate for cardiac and renal defects. Even if further data are necessary to confirm the role of CDdels, according to our review, this CNV fits into the class of ‘likely pathogenic’ CNVs. Full article

Background: Electrocardiography (ECG) signals are commonly used to detect cardiac disorders, with 12-lead ECGs being the standard method for acquiring these signals. The primary objective of this research is to propose a new feature engineering model that achieves both high classification accuracy and explainable results using ECG signals. To this end, a symbolic language, named Cardioish, has been introduced. Methods: In this research, two publicly available datasets were used: (i) a mental disorder classification dataset and (ii) a myocardial infarction (MI) dataset. These datasets contain ECG beats and include 4 and 11 classes, respectively. To obtain explainable results from these ECG signal datasets, a new explainable feature engineering (XFE) model has been proposed. The Cardioish-based XFE model consists of four main phases: (i) lead transformation and transition table feature extraction, (ii) iterative neighborhood component analysis (INCA) for feature selection, (iii) classification, and (iv) explainable results generation using the recommended Cardioish. In the feature extraction phase, the lead transformer converts ECG signals into lead indexes. To extract features from the transformed signals, a transition table-based feature extractor is applied, resulting in 144 features (12 × 12) from each ECG signal. In the feature selection phase, INCA is used to select the most informative features from the 144 generated, which are then classified using the k-nearest neighbors (kNN) classifier. The final phase is the explainable artificial intelligence (XAI) phase. In this phase, Cardioish symbols are created, forming a Cardioish sentence. By analyzing the extracted sentence, XAI results are obtained. Additionally, these results can be integrated into connectome theory for applications in cardiology. Results: The presented Cardioish-based XFE model achieved over 99% classification accuracy on both datasets. Moreover, the XAI results related to these disorders have been presented in this research. Conclusions: The recommended Cardioish-based XFE model achieved high classification performance for both datasets and provided explainable results. In this regard, our proposal paves a new way for ECG classification and interpretation. Full article

Overnight sleep staging is an important part of the diagnosis of various sleep disorders. Polysomnography is the gold standard for sleep staging, but less-obtrusive sensing modalities are of emerging interest. Here, we developed and validated an algorithm to perform “proxy” sleep staging using cardiac and respiratory signals derived from a chest-worn accelerometer. We collected data in two sleep centers, using a chest-worn accelerometer in combination with full PSG. A total of 323 participants were analyzed, aged 13–83 years, with BMI 18–47 kg/m². We derived cardiac and respiratory features from the accelerometer and then applied a previously developed method for automatic cardio-respiratory sleep staging. We compared the estimated sleep stages against those derived from PSG and determined performance. Epoch-by-epoch agreement with four-class scoring (Wake, REM, N1+N2, N3) reached a Cohen’s kappa coefficient of agreement of 0.68 and an accuracy of 80.8%. For Wake vs. Sleep classification, an accuracy of 93.3% was obtained, with a sensitivity of 78.7% and a specificity of 96.6%. We showed that cardiorespiratory signals obtained from a chest-worn accelerometer can be used to estimate sleep stages among a population that is diverse in age, BMI, and prevalence of sleep disorders. This opens up the path towards various clinical applications in sleep medicine. Full article

The identification of the genetic causes of inherited disorders from next-generation sequencing (NGS) data remains a complicated process, in particular due to challenges in interpretation of the vast amount of generated data and hundreds of candidate variants identified. Inconsistencies in variant classification, where genetic centers classify the same variant differently, can hinder accurate diagnoses for rare diseases. Publicly available databases that collect data on human genetic variations and their association with diseases provide ample opportunities to discover conflicts in variant interpretation worldwide. In this study, we explored patterns of variant classification discrepancies using data from ClinVar, a public archive of variant interpretations. We found that 5.7% of variants have conflicting interpretations (COIs) reported, and the vast majority of interpretation conflicts arise for variants of uncertain significance (VUS). As many as 78% of clinically relevant genes harbor variants with COIs, and genes with high COI rates tended to have more exons and longer transcripts, with a greater proportion of genes linked to several distinct conditions. The enrichment analysis of COI-enriched genes revealed that the products of these genes are involved in cardiac disorders, muscle development, and function. To improve diagnoses, we believe that specific variant interpretation rules could be developed for such genes. Additionally, our findings underscore the need for the publication of variant pathogenicity evidence and the importance of considering every variant as VUS unless proven otherwise. Full article

Antiphospholipid syndrome (APS) is a complex systemic autoimmune disorder characterized by a hypercoagulable state, leading to severe vascular thrombosis and obstetric complications. The 2023 ACR/EULAR guidelines have revolutionized the classification and understanding of APS, introducing broader diagnostic criteria that encompass previously overlooked cardiac, renal, and hematologic manifestations. Despite these advancements, diagnosing APS remains particularly challenging in seronegative patients, where traditional tests fail, yet clinical symptoms persist. Emerging non-criteria antiphospholipid antibodies offer promising new diagnostic and management avenues for these patients. Managing APS involves a strategic balance of cardiovascular risk mitigation and long-term anticoagulation therapy, though the use of direct oral anticoagulants remains contentious due to varying efficacy and safety profiles. This article delves into the intricate pathogenesis of APS, explores the latest classification criteria, and evaluates cutting-edge diagnostic tools and therapeutic strategies. Full article

Sleep disorders can have harmful consequences in both the short and long term. They can lead to attention deficits, as well as cardiac, neurological and behavioral repercussions. One of the most widely used methods for assessing sleep disorders is polysomnography (PSG). A major challenge associated with this method is all the cables needed to connect the recording devices, making the examination more intrusive and usually requiring a clinical environment. This can have potential consequences on the test results and their accuracy. One simple way to assess the state of the central nervous system (CNS), a well-known indicator of sleep disorder, could be the use of a portable medical device. With this in mind, we implemented a simple model using both the RR interval (RRI) and its second derivative to accurately predict the awake and napping states of a subject using a feature classification model. For training and validation, we used a database providing measurements from nine healthy young adults (six men and three women), in which heart rate variability (HRV) associated with light-on, light-off, sleep onset and sleep offset events. Results show that using a 30 min RRI time series window suffices for this lightweight model to accurately predict whether the patient was awake or napping. Full article

Background: Though out-of-hospital CA (OHCA) is widely reported, data on in-hospital CA (IHCA) and especially cardiac arrest (CA) in the emergency department (CAED) are scarce. This study aimed to determine the frequency, prevalence, and clinical features of unexpected CAED and compare the data with those of expected CAED. Methods: We defined unexpected CAED as CA occurring in patients in non-critical ED-care areas; classified as not requiring strict monitoring. This classification was the modified Japanese Triage and Acuity Scale and physician assessment. A retrospective analysis of cases from 2016 to 2018 was performed, in comparison to other patients experiencing CAED. Results: The 38 cases of unexpected CA in this study constituted 34.5% of CA diagnosed in the ED and 8.4% of all CA treated in the ED. This population did not differ significantly from other CAED regarding demographics, comorbidities, and survival rates. The commonest symptoms were dyspnoea, disorders of consciousness, generalised weakness, and chest pain. The commonest causes of death were acute myocardial infarction, malignant neoplasms with metastases, septic shock, pulmonary embolism, and heart failure. Conclusions: Unexpected CAED represents a group of potentially avoidable CA and deaths. These patients should be analysed, and ED management should include measures aimed at reducing their incidence. Full article

Light-chain amyloidosis (AL) is a rare multisystem disorder characterized by the deposition of misfolded amyloid fibrils derived from monoclonal immunoglobulin light chains in various organs. One of the most common organs involved in AL is the heart, with 50–70% of patients clinically symptomatic at diagnosis. We conducted a multi-center, retrospective analysis of 67 patients diagnosed between July 2012 and August 2022 with the European 2012 modification of Mayo 2004 stage III cardiac AL. The most important factors identified in the univariate Cox analysis contributing to a longer OS included Eastern Cooperative Oncology Group performance status (ECOG PS) ≤ 1, New York Heart Association functional classification (NYHA FC) ≤ 2, the use of autologous stem cell transplantation (ASCT) after induction treatment, achieving a hematological response (≥very good partial response) and cardiac (≥partial response) response after first-line treatment. The most important prognostic factors with the most significant impact on OS improvement in patients with modified Mayo stage III cardiac AL identified by multivariate Cox analysis are ECOG PS ≤ 1, NYHA FC ≤ 2, and achieving hematological response ≥ VGPR and cardiac response ≥ PR after first-line treatment. Full article

Introduction: Hip fractures pose a significant challenge for older individuals given their high incidence and one-year mortality rate. The objective of this study was to identify the primary predictors of one-year mortality in older adults hospitalized for hip fractures. Methods: We conducted a retrospective cohort study involving adults aged 70 years or older who were admitted to the hospital for fragility hip fractures between 1 January 2014 and 31 December 2021. A total of 3229 patients were recruited, with 846 (26.2%) experiencing one-year mortality. Results: Respiratory complications (HR 2.42, 95%CI 1.42–4.14; p = 0.001) were the most significant predictors of one-year mortality, followed by hospital readmission (HR 1.96, 95%CI 1.66–2.32; p < 0.001), the male sex (HR 1.88, 95%CI 1.46–2.32; p < 0.001), cardiac complications (HR 1.88, 95%CI 1.46–2.32; p < 0.001), and a diagnosis of dementia at admission (HR 1.37, 95%CI 1.13–1.66; p = 0.001). The Charlson Index and the American Society of Anesthesiologists physical status classification system also significantly increased the mortality risk. Conversely, higher hemoglobin levels at admission and elevated albumin at discharge significantly reduced the mortality risk. Conclusions: The one-year mortality rate is substantial in older adults with hip fractures who are admitted to an orthogeriatric unit. The appropriate management of anemia, nutritional disorders, and comorbidity at admission and during the follow-up could potentially mitigate long-term mortality after hip fractures. Full article

Cardiac arrhythmia (CA) is a severe cardiac disorder that results in a significant number of fatalities worldwide each year. Conventional electrocardiography (ECG) devices are often unable to detect arrhythmia symptoms during patients’ hospital visits due to their intermittent nature. This paper presents a wearable ECG processor for cardiac arrhythmia (CA) detection. The processor utilizes a Hilbert transform-based R-peak detection engine for R-peak detection, a Haar discrete wavelet transform (HDWT) unit for feature extraction, and a Hybrid ECG classifier that combines linear methods and Non-Linear Support Vector Machines (NLSVM) classifiers to distinguish between normal and abnormal heartbeats. The processor is fabricated by the CMOS 110 nm process with an area of 1.34 mm² and validated with the MIT_BIH Database. The whole design consumes 4.08 μW with an average classification accuracy of 97.34%. Full article