Deep learning approach for cardiovascular disease risk stratification and survival analysis on a Canadian cohort.

The quantification of carotid plaque has been routinely used to predict cardiovascular risk in cardiovascular disease (CVD) and coronary artery disease (CAD). To determine how well carotid plaque features predict the likelihood of CAD and cardiovascular (CV) events using deep learning (DL) and compare against the machine learning (ML) paradigm. The participants in this study consisted of 459 individuals who had undergone coronary angiography, contrast-enhanced ultrasonography, and focused carotid B-mode ultrasound. Each patient was tracked for thirty days. The measurements on these patients consisted of maximum plaque height (MPH), total plaque area (TPA), carotid intima-media thickness (cIMT), and intraplaque neovascularization (IPN). CAD risk and CV event stratification were performed by applying eight types of DL-based models. Univariate and multivariate analysis was also conducted to predict the most significant risk predictors. The DL's model effectiveness was evaluated by the area-under-the-curve measurement while the CV event prediction was evaluated using the Cox proportional hazard model (CPHM) and compared against the DL-based concordance index (c-index). IPN showed a substantial ability to predict CV events (p < 0.0001). The best DL system improved by 21% (0.929 vs. 0.762) over the best ML system. DL-based CV event prediction showed a ~ 17% increase in DL-based c-index compared to the CPHM (0.86 vs. 0.73). CAD and CV incidents were linked to IPN and carotid imaging characteristics. For survival analysis and CAD prediction, the DL-based system performs superior to ML-based models.

ACR Appropriateness Criteria® Sudden Onset of Cold, Painful Leg: 2023 Update.

Acute onset of a cold, painful leg, also known as acute limb ischemia, describes the sudden loss of perfusion to the lower extremity and carries significant risk of morbidity and mortality. Acute limb ischemia requires rapid identification and the management of suspected vascular compromise and is inherently driven by clinical considerations. The objectives of initial imaging include confirmation of diagnosis, identifying the location and extent of vascular occlusion, and preprocedural/presurgical planning. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

Vasculitis: When to Consider this Diagnosis?

Vasculitis is a diverse group of disorders involving inflammation of the blood vessels. Approaching the diagnosis of vasculitis can be challenging, given the differing clinical presentation and organ manifestations. Often vasculitis is a diagnosis that is considered too late, given the heterogeneous presentation and various mimics. This article aims to provide physicians with a diagnostic approach to vasculitis.

Cardiovascular disease/stroke risk stratification in deep learning framework: a review.

The global mortality rate is known to be the highest due to cardiovascular disease (CVD). Thus, preventive, and early CVD risk identification in a non-invasive manner is vital as healthcare cost is increasing day by day. Conventional methods for risk prediction of CVD lack robustness due to the non-linear relationship between risk factors and cardiovascular events in multi-ethnic cohorts. Few recently proposed machine learning-based risk stratification reviews without deep learning (DL) integration. The proposed study focuses on CVD risk stratification by the use of techniques mainly solo deep learning (SDL) and hybrid deep learning (HDL). Using a PRISMA model, 286 DL-based CVD studies were selected and analyzed. The databases included were Science Direct, IEEE Xplore, PubMed, and Google Scholar. This review is focused on different SDL and HDL architectures, their characteristics, applications, scientific and clinical validation, along with plaque tissue characterization for CVD/stroke risk stratification. Since signal processing methods are also crucial, the study further briefly presented Electrocardiogram (ECG)-based solutions. Finally, the study presented the risk due to bias in AI systems. The risk of bias tools used were (I) ranking method (RBS), (II) region-based map (RBM), (III) radial bias area (RBA), (IV) prediction model risk of bias assessment tool (PROBAST), and (V) risk of bias in non-randomized studies-of interventions (ROBINS-I). The surrogate carotid ultrasound image was mostly used in the UNet-based DL framework for arterial wall segmentation. Ground truth (GT) selection is vital for reducing the risk of bias (RoB) for CVD risk stratification. It was observed that the convolutional neural network (CNN) algorithms were widely used since the feature extraction process was automated. The ensemble-based DL techniques for risk stratification in CVD are likely to supersede the SDL and HDL paradigms. Due to the reliability, high accuracy, and faster execution on dedicated hardware, these DL methods for CVD risk assessment are powerful and promising. The risk of bias in DL methods can be best reduced by considering multicentre data collection and clinical evaluation.

A Brief Review of Thrombolytics for Venous Interventions.

Anticoagulation continues to be the mainstay of therapy for the management of venous thromboembolism. However, anticoagulation does not lead to the breakdown or dissolving of the thrombus. In an acute pulmonary embolism, extensive thrombus burden can be associated with a high risk for early decompensation, and in acute deep venous thrombosis, it can be associated with an increased risk for phlegmasia. In addition, residual thrombosis can be associated with chronic thromboembolic pulmonary hypertension and postthrombotic syndrome in a chronic setting. Thrombolytic therapy is a crucial therapeutic choice in treating venous thromboembolism for thrombus resolution. Historically, it was administered systemically and was associated with high bleeding rates, particularly major bleeding, including intracranial bleeding. In the last two decades, there has been a significant increase in catheter-based therapies with and without ultrasound, where lower doses of thrombolytic agents are utilized, potentially reducing the risk for major bleeding events and improving the odds of reducing the thrombus burden. In this article, we provide an overview of several thrombolytic therapies, including delivery methods, doses, and outcomes.

Mechanical aspiration thrombectomy for the treatment of pulmonary embolism: A systematic review and meta-analysis.

INTRODUCTION: There are no randomized trials studying the outcomes of mechanical aspiration thrombectomy (MAT) for management of pulmonary embolism (PE). METHODS: We performed a systematic review and meta-analysis of existing literature to evaluate the safety and efficacy of MAT in the setting of PE. Inclusion criteria were as follows: studies reporting more than five patients, study involved MAT, and reported clinical outcomes and pulmonary artery pressures. Studies were excluded if they failed to separate thrombectomy data from catheter-directed thrombolysis data. Databases searched include PubMed, EMBASE, Web of Science until April, 2021. RESULTS: Fourteen case series were identified, consisting of 516 total patients (mean age 58.4 ± 13.6 years). Three studies had only high-risk PE, two studies had only intermediate-risk PE, and the remaining nine studies had a combination of both high-risk and intermediate-risk PE. Six studies used the Inari FlowTriever device, five studies used the Indigo Aspiration system, and the remaining three studies used the Rotarex or Aspirex suction thrombectomy system. Four total studies employed thrombolytics in a patient-specific manner, with seven receiving local lysis and 17 receiving systemic lysis, and 40 receiving both. A random-effects meta-analyses of proportions of in-hospital mortality, major bleeding, technical success, and clinical success were calculated, which yielded estimate pooled percentages [95% CI] of 3.6% [0.7%, 7.9%], 0.5% [0.0%, 1.8%], 97.1% [94.8%, 98.4%], and 90.7% [85.5%, 94.3%]. CONCLUSION: There is significant heterogeneity in clinical, physiologic, and angiographic data in the currently available data on MAT. RCTs with consistent parameters and outcomes measures are still needed.

A Powerful Paradigm for Cardiovascular Risk Stratification Using Multiclass, Multi-Label, and Ensemble-Based Machine Learning Paradigms: A Narrative Review.

Background and Motivation: Cardiovascular disease (CVD) causes the highest mortality globally. With escalating healthcare costs, early non-invasive CVD risk assessment is vital. Conventional methods have shown poor performance compared to more recent and fast-evolving Artificial Intelligence (AI) methods. The proposed study reviews the three most recent paradigms for CVD risk assessment, namely multiclass, multi-label, and ensemble-based methods in (i) office-based and (ii) stress-test laboratories. Methods: A total of 265 CVD-based studies were selected using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) model. Due to its popularity and recent development, the study analyzed the above three paradigms using machine learning (ML) frameworks. We review comprehensively these three methods using attributes, such as architecture, applications, pro-and-cons, scientific validation, clinical evaluation, and AI risk-of-bias (RoB) in the CVD framework. These ML techniques were then extended under mobile and cloud-based infrastructure. Findings: Most popular biomarkers used were office-based, laboratory-based, image-based phenotypes, and medication usage. Surrogate carotid scanning for coronary artery risk prediction had shown promising results. Ground truth (GT) selection for AI-based training along with scientific and clinical validation is very important for CVD stratification to avoid RoB. It was observed that the most popular classification paradigm is multiclass followed by the ensemble, and multi-label. The use of deep learning techniques in CVD risk stratification is in a very early stage of development. Mobile and cloud-based AI technologies are more likely to be the future. Conclusions: AI-based methods for CVD risk assessment are most promising and successful. Choice of GT is most vital in AI-based models to prevent the RoB. The amalgamation of image-based strategies with conventional risk factors provides the highest stability when using the three CVD paradigms in non-cloud and cloud-based frameworks.

Antithrombotic Therapy After Venous Interventions: AJR Expert Panel Narrative Review.

Interventions for thrombotic and nonthrombotic venous disorders have increased with technical advances and more trained venous specialists. Antithrombotic therapy is essential to clinical and procedural success; however, postprocedural therapeutic regimens exhibit significant heterogeneity due to limited prospective randomized data and incomplete mechanistic understanding of the critical factors driving long-term patency. Postinterventional antithrombotic therapy for thrombotic venous disorders should adhere to existing venous thromboembolism management guidelines, which include 3-6 months of therapeutic anticoagulation at minimum and consideration of extended therapy in patients with higher risk of thrombosis because of procedural or patient factors. The added benefit of antiplatelet agents in the acute and intermediate period is unknown, having shown improved long-term stent patency in some retrospective studies. Dual- and/or triple-agent therapy should be limited based on individual risks of thrombosis and bleeding. The treatment of nonthrombotic disorders is more heterogeneous, though patients with limited flow, extensive stent material, or underlying prothrombotic states such as malignancy or chronic inflammation may benefit from single-agent or multiagent antithrombotic therapy. However, the agent, dose, and duration of therapy remain indeterminate. Future prospective studies are warranted to improve patient risk stratification and standardize postprocedural anti-thrombotic therapy in patients receiving venous interventions.

Cardiovascular disease detection using machine learning and carotid/femoral arterial imaging frameworks in rheumatoid arthritis patients.

The study proposes a novel machine learning (ML) paradigm for cardiovascular disease (CVD) detection in individuals at medium to high cardiovascular risk using data from a Greek cohort of 542 individuals with rheumatoid arthritis, or diabetes mellitus, and/or arterial hypertension, using conventional or office-based, laboratory-based blood biomarkers and carotid/femoral ultrasound image-based phenotypes. Two kinds of data (CVD risk factors and presence of CVD-defined as stroke, or myocardial infarction, or coronary artery syndrome, or peripheral artery disease, or coronary heart disease) as ground truth, were collected at two-time points: (i) at visit 1 and (ii) at visit 2 after 3 years. The CVD risk factors were divided into three clusters (conventional or office-based, laboratory-based blood biomarkers, carotid ultrasound image-based phenotypes) to study their effect on the ML classifiers. Three kinds of ML classifiers (Random Forest, Support Vector Machine, and Linear Discriminant Analysis) were applied in a two-fold cross-validation framework using the data augmented by synthetic minority over-sampling technique (SMOTE) strategy. The performance of the ML classifiers was recorded. In this cohort with overall 46 CVD risk factors (covariates) implemented in an online cardiovascular framework, that requires calculation time less than 1 s per patient, a mean accuracy and area-under-the-curve (AUC) of 98.40% and 0.98 (p < 0.0001) for CVD presence detection at visit 1, and 98.39% and 0.98 (p < 0.0001) at visit 2, respectively. The performance of the cardiovascular framework was significantly better than the classical CVD risk score. The ML paradigm proved to be powerful for CVD prediction in individuals at medium to high cardiovascular risk.

Understanding the bias in machine learning systems for cardiovascular disease risk assessment: The first of its kind review.

BACKGROUND: Artificial Intelligence (AI), in particular, machine learning (ML) has shown promising results in coronary artery disease (CAD) or cardiovascular disease (CVD) risk prediction. Bias in ML systems is of great interest due to its over-performance and poor clinical delivery. The main objective is to understand the nature of risk-of-bias (RoB) in ML and non-ML studies for CVD risk prediction. METHODS: PRISMA model was used to shortlisting 117 studies, which were analyzed to understand the RoB in ML and non-ML using 46 and 32 attributes, respectively. The mean score for each study was computed and then ranked into three ML and non-ML bias categories, namely low-bias (LB), moderate-bias (MB), and high-bias (HB), derived using two cutoffs. Further, bias computation was validated using the analytical slope method. RESULTS: Five types of the gold standard were identified in the ML design for CAD/CVD risk prediction. The low-moderate and moderate-high bias cutoffs for 24 ML studies (5, 10, and 9 studies for each LB, MB, and HB) and 14 non-ML (3, 4, and 7 studies for each LB, MB, and HB) were in the range of 1.5 to 1.95. BiasML< Biasnon-ML by ∼43%. A set of recommendations were proposed for lowering RoB. CONCLUSION: ML showed a lower bias compared to non-ML. For a robust ML-based CAD/CVD prediction design, it is vital to have (i) stronger outcomes like death or CAC score or coronary artery stenosis; (ii) ensuring scientific/clinical validation; (iii) adaptation of multiethnic groups while practicing unseen AI; (iv) amalgamation of conventional, laboratory, image-based and medication-based biomarkers.

Optimal Medical Therapy Following Deep Venous Interventions: Proceedings from the Society of Interventional Radiology Foundation Research Consensus Panel.

The optimal medical management of patients following endovascular deep venous interventions remains ill-defined. As such, the Society of Interventional Radiology Foundation (SIRF) convened a multidisciplinary group of experts in a virtual Research Consensus Panel (RCP) to develop a prioritized research agenda regarding antithrombotic therapy following deep venous interventions. The panelists presented the gaps in knowledge followed by discussion and ranking of research priorities based on clinical relevance, overall impact, and technical feasibility. The following research topics were identified as high priority: 1) characterization of biological processes leading to in-stent stenosis/rethrombosis; 2) identification and validation of methods to assess venous flow dynamics and their effect on stent failure; 3) elucidation of the role of inflammation and anti-inflammatory therapies; and 4) clinical studies to compare antithrombotic strategies and improve venous outcome assessment. Collaborative, multicenter research is necessary to answer these questions and thereby enhance the care of patients with venous disease.

Venoarterial Extracorporeal Membrane Oxygenation for Acute Massive Pulmonary Embolism: a Meta-Analysis and Call to Action.

Venoarterial extracorporeal membrane oxygenation (ECMO) has been used to treat acute massive pulmonary embolism (PE) patients. However, the incremental benefit of ECMO to standard therapy remains unclear. Our meta-analysis objective is to compare in-hospital mortality in patients treated for acute massive PE with and without ECMO. The National Library of Medicine MEDLINE (USA), Web of Science, and PubMed databases from inception through October 2020 were searched. Screening identified 1002 published articles. Eleven eligible studies were identified, and 791 patients with acute massive PE were included, of whom 270 received ECMO and 521 did not. In-hospital mortality was not significantly different between patients treated with vs. without ECMO (OR = 1.24 [95% CI, 0.63-2.44], p = 0.54). However, these findings were limited by significant study heterogeneity. Additional research will be needed to clarify the role of ECMO in massive PE treatment. In-hospital mortality for patients with acute massive pulmonary embolism was not significantly different (OR of 1.24, p = 0.54) between those treated with and without venoarterial ECMO.

Venous thromboembolism in patients with COVID-19 infection: risk factors, prevention, and management.

Venous thromboembolic complications have emerged as serious sequelae in COVID-19 infections. This article summarizes the most current information regarding pathophysiology, risk factors and hematologic markers, incidence and timing of events, atypical venous thromboembolic complications, prophylaxis recommendations, and therapeutic recommendations. Data will likely to continue to rapidly evolve as more knowledge is gained regarding venous events in COVID-19 patients.

Association of Fibromuscular Dysplasia and Pulsatile Tinnitus: A Report of the US Registry for Fibromuscular Dysplasia.

Background Fibromuscular dysplasia (FMD) is a nonatherosclerotic arterial disease that has a variable presentation including pulsatile tinnitus (PT). The frequency and characteristics of PT in FMD are not well understood. The objective of this study was to evaluate the frequency of PT in FMD and compare characteristics between patients with and without PT. Methods and Results Data were queried from the US Registry for FMD from 2009 to 2020. The primary outcomes were frequency of PT among the FMD population and prevalence of baseline characteristics, signs/symptoms, and vascular bed involvement in patients with and without PT. Of 2613 patients with FMD who were included in the analysis, 972 (37.2%) reported PT. Univariable analysis and multivariable logistic regression were performed to explore factors associated with PT. Compared with those without PT, patients with PT were more likely to have involvement of the extracranial carotid artery (90.0% versus 78.6%; odds ratio, 1.49; P=0.005) and to have higher prevalence of other neurovascular signs/symptoms including headache (82.5% versus 62.7%; odds ratio, 1.82; P<0.001), dizziness (44.9% versus 22.9%; odds ratio, 2.01; P<0.001), and cervical bruit (37.5% versus 15.8%; odds ratio, 2.73; P<0.001) compared with those without PT. Conclusions PT is common among patients with FMD. Patients with FMD who present with PT have higher rates of neurovascular signs/symptoms, cervical bruit, and involvement of the extracranial carotid arteries. The coexistence of the 2 conditions should be recognized, and providers who evaluate patients with PT should be aware of FMD as a potential cause.

Multimodality carotid plaque tissue characterization and classification in the artificial intelligence paradigm: a narrative review for stroke application.

Cardiovascular disease (CVD) is one of the leading causes of morbidity and mortality in the United States of America and globally. Carotid arterial plaque, a cause and also a marker of such CVD, can be detected by various non-invasive imaging modalities such as magnetic resonance imaging (MRI), computer tomography (CT), and ultrasound (US). Characterization and classification of carotid plaque-type in these imaging modalities, especially into symptomatic and asymptomatic plaque, helps in the planning of carotid endarterectomy or stenting. It can be challenging to characterize plaque components due to (I) partial volume effect in magnetic resonance imaging (MRI) or (II) varying Hausdorff values in plaque regions in CT, and (III) attenuation of echoes reflected by the plaque during US causing acoustic shadowing. Artificial intelligence (AI) methods have become an indispensable part of healthcare and their applications to the non-invasive imaging technologies such as MRI, CT, and the US. In this narrative review, three main types of AI models (machine learning, deep learning, and transfer learning) are analyzed when applied to MRI, CT, and the US. A link between carotid plaque characteristics and the risk of coronary artery disease is presented. With regard to characterization, we review tools and techniques that use AI models to distinguish carotid plaque types based on signal processing and feature strengths. We conclude that AI-based solutions offer an accurate and robust path for tissue characterization and classification for carotid artery plaque imaging in all three imaging modalities. Due to cost, user-friendliness, and clinical effectiveness, AI in the US has dominated the most.

Fibromuscular dysplasia: A comprehensive review on evaluation and management and role for multidisciplinary comprehensive care and patient input model.

Fibromuscular dysplasia is a nonatherosclerotic, under-recognized disorder primarily seen in middle-aged women. It can lead to several complications, such as hypertension, headaches, dissections, aneurysms, myocardial infarctions, and cerebrovascular accidents, to name a few. This article provides a comprehensive review of current literature on epidemiology, etiology, diagnosis, treatment, and long-term surveillance and fibromuscular dysplasia management. In addition, it renders the role of education and prevention for patients living with this condition and family screening. Lastly, it emphasizes the importance of a comprehensive multidisciplinary care model and patient input, given the complexity of this disease and its systemic presence and protean manifestations.

Bidirectional link between diabetes mellitus and coronavirus disease 2019 leading to cardiovascular disease: A narrative review.

Coronavirus disease 2019 (COVID-19) is a global pandemic where several comorbidities have been shown to have a significant effect on mortality. Patients with diabetes mellitus (DM) have a higher mortality rate than non-DM patients if they get COVID-19. Recent studies have indicated that patients with a history of diabetes can increase the risk of severe acute respiratory syndrome coronavirus 2 infection. Additionally, patients without any history of diabetes can acquire new-onset DM when infected with COVID-19. Thus, there is a need to explore the bidirectional link between these two conditions, confirming the vicious loop between "DM/COVID-19". This narrative review presents (1) the bidirectional association between the DM and COVID-19, (2) the manifestations of the DM/COVID-19 loop leading to cardiovascular disease, (3) an understanding of primary and secondary factors that influence mortality due to the DM/COVID-19 loop, (4) the role of vitamin-D in DM patients during COVID-19, and finally, (5) the monitoring tools for tracking atherosclerosis burden in DM patients during COVID-19 and "COVID-triggered DM" patients. We conclude that the bidirectional nature of DM/COVID-19 causes acceleration towards cardiovascular events. Due to this alarming condition, early monitoring of atherosclerotic burden is required in "Diabetes patients during COVID-19" or "new-onset Diabetes triggered by COVID-19 in Non-Diabetes patients".

Wilson disease tissue classification and characterization using seven artificial intelligence models embedded with 3D optimization paradigm on a weak training brain magnetic resonance imaging datasets: a supercomputer application.

Wilson's disease (WD) is caused by copper accumulation in the brain and liver, and if not treated early, can lead to severe disability and death. WD has shown white matter hyperintensity (WMH) in the brain magnetic resonance scans (MRI) scans, but the diagnosis is challenging due to (i) subtle intensity changes and (ii) weak training MRI when using artificial intelligence (AI). Design and validate seven types of high-performing AI-based computer-aided design (CADx) systems consisting of 3D optimized classification, and characterization of WD against controls. We propose a "conventional deep convolution neural network" (cDCNN) and an "improved DCNN" (iDCNN) where rectified linear unit (ReLU) activation function was modified ensuring "differentiable at zero." Three-dimensional optimization was achieved by recording accuracy while changing the CNN layers and augmentation by several folds. WD was characterized using (i) CNN-based feature map strength and (ii) Bispectrum strengths of pixels having higher probabilities of WD. We further computed the (a) area under the curve (AUC), (b) diagnostic odds ratio (DOR), (c) reliability, and (d) stability and (e) benchmarking. Optimal results were achieved using 9 layers of CNN, with 4-fold augmentation. iDCNN yields superior performance compared to cDCNN with accuracy and AUC of 98.28 ± 1.55, 0.99 (p < 0.0001), and 97.19 ± 2.53%, 0.984 (p < 0.0001), respectively. DOR of iDCNN outperformed cDCNN fourfold. iDCNN also outperformed (a) transfer learning-based "Inception V3" paradigm by 11.92% and (b) four types of "conventional machine learning-based systems": k-NN, decision tree, support vector machine, and random forest by 55.13%, 28.36%, 15.35%, and 14.11%, respectively. The AI-based systems can potentially be useful in the early WD diagnosis. Graphical Abstract.