Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 236
Filtrar
1.
Artículo en Inglés | MEDLINE | ID: mdl-35561974

RESUMEN

OBJECTIVE: Extended anticoagulation should always be considered after standard treatment for an unprovoked episode of venous thromboembolism (VTE). It may also be considered in selected patients with provoked VTE. However, evidence-based protocols suggested by some clinical guidelines and risk assessment tools to guide this practice are limited and ambiguous. The goal of this survey research was to analyze current practices in applying extended anticoagulation therapy in patients with VTE among members of the American Venous Forum (AVF) and the European Venous Forum (EVF). METHODS: An online survey was created by the AVF Research Committee. The survey consisted of sixteen questions to identify the country of practice, specialty, experience of participating physicians, and their clinical practice patterns in applying extended anticoagulation in VTE patients. The survey was distributed over email to the members of the AVF and EVF. RESULTS: A total of 144 practitioners, 48 (33%) AVF members and 96 (66%) EVF members, participated in the survey. The majority of respondents identified themselves as vascular specialists with primary certification in vascular surgery (70%), vascular medicine/angiology (9%), and venous disease/phlebology (3%). Seventy-two percent of participants believe that the risk of VTE recurrence generally overweighs the risk of bleeding in patients with unprovoked VTE. Extended anticoagulation may be utilized by 97% of providers. Different patterns in real world clinical practice were identified. More than half of practitioners estimated VTE recurrence and bleeding risk subjectively. The antithrombotic drugs most commonly used for secondary prophylaxis were rivaroxaban, apixaban, warfarin, dabigatran, and aspirin, in decreasing order of frequency. Among the reasons selected for not considering extended anticoagulation on a regular basis were the lack of specific clinical practice guidelines (24%), the lack of published evidence (9%), and the absence of valid VTE/bleeding risk prediction calculators (8%). Twelve participants (8%) stated that extended anticoagulation was not beneficial for the majority of patients with VTE. Ten participants (7%) indicated that prescribing extended anticoagulation was outside the scope of their specialty. CONCLUSIONS: There are different practice patterns in extending anticoagulation beyond the standard treatment in patients with VTE. Major gaps in knowledge remain a serious challenge at least partially explaining inaccuracy and inconsistency in long-term VTE management. Appropriately designed studies are needed to evaluate risk stratification tools when contemporary best medical therapy is used, accurately predict VTE recurrence and its long-term outcomes, and to tailor safe and effective secondary prophylaxis.

2.
Artículo en Inglés | MEDLINE | ID: mdl-35482484

RESUMEN

OBJECTIVE: Patients with systemic lupus erythematosus (SLE) have increased prevalence of clinical cardiovascular disease (CVD) and subclinical atherosclerosis. Although 30-40% of patients with SLE have vascular plaque on ultrasound scanning, this study is the first to consider the relationship between total burden of plaque and subsequent CVD risk. METHODS: One hundred patients with SLE and without any previous clinical CVD underwent vascular ultrasound scans of both carotid and both common femoral bifurcations between 2011 and 2013. Clinical, serological, demographic and treatment data were collected at baseline. Patients were followed till 2020 to identify those who developed new onset coronary disease or stroke. Statistical analysis to identify factors associated with increased risk of developing CVD events was carried out. RESULTS: Thirty-six patients had plaque at baseline. During follow-up five patients (all had baseline plaque) developed coronary disease and two, without baseline plaque, developed lacunar strokes. Mean (SD) age of these patients was 46.5 (4.5) years. Patients with three or more baseline bifurcations with plaque were 10 times more likely to develop CVD than those with 0-2 bifurcations with plaques (OR 9.9, p= 0.009). TPA > 16mm2 was associated with six-fold increased risk of CVD (OR = 6.44, p= 0.028). Patients with disease duration > 14 years were more likely than those with disease duration < 14 years to develop CVD (OR 8.3 p= 0.043). CONCLUSIONS: The number of bifurcations with plaque and TPA in patients with SLE may be valuable in assessing risk of CVD and deciding on clinical measures to reduce this risk.

3.
Atherosclerosis ; 348: 25-35, 2022 May.
Artículo en Inglés | MEDLINE | ID: mdl-35398698

RESUMEN

Atherosclerosis has a long preclinical phase, and the risk of cardiovascular (CV) events may be high in asymptomatic subjects. Conventional risk factors provide information for the statistical probability of developing CV events, but they lack precision in asymptomatic subjects. This review aims to summarize the role of some widely publicized indicators of early atherosclerosis in predicting CV events. The earliest measurable indicator of the atherosclerotic process is endothelial dysfunction, measured by flow-mediated dilation (FMD) of the brachial artery. However, reduced FMD is a stronger predictor of future CV events in patients with existing CV disease than in apparently healthy persons. Alternatively, measurement of carotid artery intima-media thickness does not improve the predictive value of risk factor scores, while detection of asymptomatic atherosclerotic plaques in carotid or common femoral arteries by ultrasound indicates high CV risk. Coronary calcium is a robust and validated help in the estimation of vascular changes and risk, which may improve risk stratification beyond traditional risk factors with relatively low radiation exposure. Arterial stiffness of the aorta, measured as the carotid-femoral pulse wave velocity is an independent marker of CV risk at the population level, but it is not recommended as a routine procedure because of measurement difficulties. Low ankle-brachial index (ABI) indicates flow-limiting atherosclerosis in the lower limbs and indicates high CV risk, while normal ABI does not rule out advanced asymptomatic atherosclerosis. Novel circulating biomarkers are associated with the atherosclerotic process. However, because of limited specificity, their ability to improve risk classification at present remains low.


Asunto(s)
Aterosclerosis , Enfermedades Cardiovasculares , Aterosclerosis/diagnóstico , Enfermedades Cardiovasculares/diagnóstico , Arterias Carótidas/diagnóstico por imagen , Grosor Intima-Media Carotídeo , Consenso , Humanos , Análisis de la Onda del Pulso , Factores de Riesgo
4.
Int Angiol ; 2022 Apr 04.
Artículo en Inglés | MEDLINE | ID: mdl-35373942

RESUMEN

INTRODUCTION: Chronic venous disease is a persistent venous drainage alteration caused by valvular incompetence and/or outflow obstruction. Disease management includes a variety of treatments, whose evidence and clinical performance in the mid-long term are variable. The objective of this umbrella review was to summarise efficacy data for pharmacological treatments including venoactive drugs from previously published reviews that included a meta-analytic component. EVIDENCE ACQUISITION: Systematic database searches were conducted via Ovid SP on 13 August 2019, covering MEDLINE, Embase, and the Cochrane Database of Systematic Reviews. Reviews that included a meta-analytic component of four or more clinical trials or observational studies reporting on the efficacy of systemic or topical pharmacological treatments for adults with chronic venous disease published since 2010 were eligible for inclusion. EVIDENCE SYNTHESIS: Eleven publications were included in this umbrella review. Change in ankle circumference was the most commonly reported outcome. Overall, several systemic treatments had significant effects compared with placebo on multiple efficacy outcomes, including measures of oedema and pain. Out of them, Micronized Purified Flavonoid Fraction had the most comprehensive evidence of effectiveness on main symptoms and signs and on improving quality of life throughout chronic venous disease stages. CONCLUSIONS: Systemic pharmacotherapies represent a valuable therapeutic option in CVD management. As a result of this umbrella review, several gaps were identified with respect to research topics that warrant further investigation, particularly in the category of topical medications.

5.
Angiology ; : 33197221081914, 2022 Apr 12.
Artículo en Inglés | MEDLINE | ID: mdl-35412377

RESUMEN

Despite the publication of several national/international guidelines, the optimal management of patients with asymptomatic carotid stenosis (AsxCS) remains controversial. This article compares 3 recently released guidelines (the 2020 German-Austrian, the 2021 European Stroke Organization [ESO], and the 2021 Society for Vascular Surgery [SVS] guidelines) vs the 2017 European Society for Vascular Surgery (ESVS) guidelines regarding the optimal management of AsxCS patients.The 2017 ESVS guidelines defined specific imaging/clinical parameters that may identify patient subgroups at high future stroke risk and recommended that carotid endarterectomy (CEA) should or carotid artery stenting (CAS) may be considered for these individuals. The 2020 German-Austrian guidelines provided similar recommendations with the 2017 ESVS Guidelines. The 2021 ESO Guidelines also recommended CEA for AsxCS patients at high risk for stroke on best medical treatment (BMT), but recommended against routine use of CAS in these patients. Finally, the SVS guidelines provided a strong recommendation for CEA+BMT vs BMT alone for low-surgical risk patients with >70% AsxCS. Thus, the ESVS, German-Austrian, and ESO guidelines concurred that all AsxCS patients should receive risk factor modification and BMT, but CEA should or CAS may also be considered for certain AsxCS patient subgroups at high risk for future ipsilateral ischemic stroke.

6.
Comput Biol Med ; 144: 105333, 2022 05.
Artículo en Inglés | MEDLINE | ID: mdl-35279425

RESUMEN

After publishing an in-depth study that analyzed the ability of computerized methods to assist or replace human experts in obtaining carotid intima-media thickness (CIMT) measurements leading to correct therapeutic decisions, here the same consortium joined to present technical outlooks on computerized CIMT measurement systems and provide considerations for the community regarding the development and comparison of these methods, including considerations to encourage the standardization of computerized CIMT measurements and results presentation. A multi-center database of 500 images was collected, upon which three manual segmentations and seven computerized methods were employed to measure the CIMT, including traditional methods based on dynamic programming, deformable models, the first order absolute moment, anisotropic Gaussian derivative filters and deep learning-based image processing approaches based on U-Net convolutional neural networks. An inter- and intra-analyst variability analysis was conducted and segmentation results were analyzed by dividing the database based on carotid morphology, image signal-to-noise ratio, and research center. The computerized methods obtained CIMT absolute bias results that were comparable with studies in literature and they generally were similar and often better than the observed inter- and intra-analyst variability. Several computerized methods showed promising segmentation results, including one deep learning method (CIMT absolute bias = 106 ± 89 µm vs. 160 ± 140 µm intra-analyst variability) and three other traditional image processing methods (CIMT absolute bias = 139 ± 119 µm, 143 ± 118 µm and 139 ± 136 µm). The entire database used has been made publicly available for the community to facilitate future studies and to encourage an open comparison and technical analysis (https://doi.org/10.17632/m7ndn58sv6.1).


Asunto(s)
Arterias Carótidas , Grosor Intima-Media Carotídeo , Arterias Carótidas/diagnóstico por imagen , Arteria Carótida Común/diagnóstico por imagen , Humanos , Ultrasonografía/métodos , Ultrasonografía Doppler
9.
Cochrane Database Syst Rev ; 1: CD005258, 2022 01 28.
Artículo en Inglés | MEDLINE | ID: mdl-35089599

RESUMEN

BACKGROUND: It is generally assumed by practitioners and guideline authors that combined modalities (methods of treatment) are more effective than single modalities in preventing venous thromboembolism (VTE), defined as deep vein thrombosis (DVT) or pulmonary embolism (PE), or both. This is the second update of the review first published in 2008. OBJECTIVES: The aim of this review was to assess the efficacy of combined intermittent pneumatic leg compression (IPC) and pharmacological prophylaxis compared to single modalities in preventing VTE. SEARCH METHODS: The Cochrane Vascular Information Specialist searched the Cochrane Vascular Specialised Register, CENTRAL, MEDLINE, Embase, CINAHL, and AMED databases, and World Health Organization International Clinical Trials Registry Platform and ClinicalTrials.gov trials registers to 18 January 2021. We searched the reference lists of relevant articles for additional studies.  SELECTION CRITERIA: We included randomised controlled trials (RCTs) or controlled clinical trials (CCTs) of combined IPC and pharmacological interventions used to prevent VTE compared to either intervention individually. DATA COLLECTION AND ANALYSIS: We independently selected studies, applied Cochrane's risk of bias tool, and extracted data. We resolved disagreements by discussion. We performed fixed-effect model meta-analyses with odds ratios (ORs) and 95% confidence intervals (CIs). We used a random-effects model when there was heterogeneity. We assessed the certainty of the evidence using GRADE. The outcomes of interest were PE, DVT, bleeding and major bleeding. MAIN RESULTS: We included a total of 34 studies involving 14,931 participants, mainly undergoing surgery or admitted with trauma. Twenty-five studies were RCTs (12,672 participants) and nine were CCTs (2259 participants). Overall, the risk of bias was mostly unclear or high. We used GRADE to assess the certainty of the evidence and this was downgraded due to the risk of bias, imprecision or indirectness. The addition of pharmacological prophylaxis to IPC compared with IPC alone reduced the incidence of symptomatic PE from 1.34% (34/2530) in the IPC group to 0.65% (19/2932) in the combined group (OR 0.51, 95% CI 0.29 to 0.91; 19 studies, 5462 participants, low-certainty evidence). The incidence of DVT was 3.81% in the IPC group and 2.03% in the combined group showing a reduced incidence of DVT in favour of the combined group (OR 0.51, 95% CI 0.36 to 0.72; 18 studies, 5394 participants, low-certainty evidence). The addition of pharmacological prophylaxis to IPC, however, increased the risk of any bleeding compared to IPC alone: 0.95% (22/2304) in the IPC group and 5.88% (137/2330) in the combined group (OR 6.02, 95% CI 3.88 to 9.35; 13 studies, 4634 participants, very low-certainty evidence). Major bleeding followed a similar pattern: 0.34% (7/2054) in the IPC group compared to 2.21% (46/2079) in the combined group (OR 5.77, 95% CI 2.81 to 11.83; 12 studies, 4133 participants, very low-certainty evidence). Tests for subgroup differences between orthopaedic and non-orthopaedic surgery participants were not possible for PE incidence as no PE events were reported in the orthopaedic subgroup. No difference was detected between orthopaedic and non-orthopaedic surgery participants for DVT incidence (test for subgroup difference P = 0.19).  The use of combined IPC and pharmacological prophylaxis modalities compared with pharmacological prophylaxis alone reduced the incidence of PE from 1.84% (61/3318) in the pharmacological prophylaxis group to 0.91% (31/3419) in the combined group (OR 0.46, 95% CI 0.30 to 0.71; 15 studies, 6737 participants, low-certainty evidence). The incidence of DVT was 9.28% (288/3105) in the pharmacological prophylaxis group and 5.48% (167/3046) in the combined group (OR 0.38, 95% CI 0.21 to 0.70; 17 studies; 6151 participants, high-certainty evidence). Increased bleeding side effects were not observed for IPC when it was added to anticoagulation (any bleeding: OR 0.87, 95% CI 0.56 to 1.35, 6 studies, 1314 participants, very low-certainty evidence; major bleeding: OR 1.21, 95% CI 0.35 to 4.18, 5 studies, 908 participants, very low-certainty evidence). No difference was detected between the orthopaedic and non-orthopaedic surgery participants for PE incidence (test for subgroup difference P = 0.82) or for DVT incidence (test for subgroup difference P = 0.69). AUTHORS' CONCLUSIONS: Evidence suggests that combining IPC with pharmacological prophylaxis, compared to IPC alone reduces the incidence of both PE and DVT (low-certainty evidence). Combining IPC with pharmacological prophylaxis, compared to pharmacological prophylaxis alone, reduces the incidence of both PE (low-certainty evidence) and DVT (high-certainty evidence). We downgraded due to risk of bias in study methodology and imprecision. Very low-certainty evidence suggests that the addition of pharmacological prophylaxis to IPC increased the risk of bleeding compared to IPC alone, a side effect not observed when IPC is added to pharmacological prophylaxis (very low-certainty evidence), as expected for a physical method of thromboprophylaxis. The certainty of the evidence for bleeding was downgraded to very low due to risk of bias in study methodology, imprecision and indirectness. The results of this update agree with current guideline recommendations, which support the use of combined modalities in hospitalised people (limited to those with trauma or undergoing surgery) at risk of developing VTE. More studies on the role of combined modalities in VTE prevention are needed to provide evidence for specific patient groups and to increase our certainty in the evidence.


Asunto(s)
Embolia Pulmonar , Tromboembolia Venosa , Anticoagulantes/uso terapéutico , Hemorragia , Humanos , Pierna , Embolia Pulmonar/prevención & control , Tromboembolia Venosa/prevención & control
10.
J Stroke Cerebrovasc Dis ; 31(1): 106182, 2022 Jan.
Artículo en Inglés | MEDLINE | ID: mdl-34735900

RESUMEN

OBJECTIVES: The recommendations of international guidelines for the management of asymptomatic carotid stenosis (ACS) often vary considerably and extend from a conservative approach with risk factor modification and best medical treatment (BMT) alone, to a more aggressive approach with a carotid intervention plus BMT. The aim of the current multispecialty position statement is to reconcile the conflicting views on the topic. MATERIALS AND METHODS: A literature review was performed with a focus on data from recent studies. RESULTS: Several clinical and imaging high-risk features have been identified that are associated with an increased long-term ipsilateral ischemic stroke risk in patients with ACS. Such high-risk clinical/imaging features include intraplaque hemorrhage, impaired cerebrovascular reserve, carotid plaque echolucency/ulceration/ neovascularization, a lipid-rich necrotic core, a thin or ruptured fibrous cap, silent brain infarction, a contralateral transient ischemic attack/stroke episode, male patients < 75 years and microembolic signals on transcranial Doppler. There is growing evidence that 80-99% ACS indicate a higher stroke risk than 50-79% stenoses. CONCLUSIONS: Although aggressive risk factor control and BMT should be implemented in all ACS patients, several high-risk features that may increase the risk of a future cerebrovascular event are now documented. Consequently, some guidelines recommend a prophylactic carotid intervention in high-risk patients to prevent future cerebrovascular events. Until the results of the much-anticipated randomized controlled trials emerge, the jury is still out regarding the optimal management of ACS patients.


Asunto(s)
Estenosis Carotídea , Estenosis Carotídea/terapia , Humanos , Guías de Práctica Clínica como Asunto
11.
Int Angiol ; 41(1): 9-23, 2022 Feb.
Artículo en Inglés | MEDLINE | ID: mdl-34825801

RESUMEN

BACKGROUND: The death due to stroke is caused by embolism of the arteries which is due to the rupture of the atherosclerotic lesions in carotid arteries. The lesion formation is over time, and thus, early screening is recommended for asymptomatic and moderate-risk patients. The previous techniques adopted conventional methods or semi-automated and, more recently, machine learning solutions. A handful of studies have emerged based on solo deep learning (SDL) models such as UNet architecture. METHODS: The proposed research is the first to adopt hybrid deep learning (HDL) artificial intelligence models such as SegNet-UNet. This model is benchmarked against UNet and advanced conventional models using scale-space such as AtheroEdge 2.0 (AtheroPoint, CA, USA). All our resultant statistics of the three systems were in the order of UNet, SegNet-UNet, and AtheroEdge 2.0. RESULTS: Using the database of 379 ultrasound scans from a Japanese cohort of 190 patients having moderate risk and implementing the cross-validation deep learning framework, our system performance using area-under-the-curve (AUC) for UNet, SegNet-UNet, and AtheroEdge 2.0 were 0.93, 0.94, and 0.95 (P<0.001), respectively. The coefficient of correlation between the three systems and ground truth (GT) were: 0.82, 0.89, and 0.85 (P<0.001 for all three), respectively. The mean absolute area error for the three systems against manual GT was 4.07±4.70 mm2, 3.11±3.92 mm2, 3.72±4.76 mm2, respectively, proving the superior performance SegNet-UNet against UNet and AtheroEdge 2.0, respectively. Statistical tests were also conducted for their reliability and stability. CONCLUSIONS: The proposed study demonstrates a fast, accurate, and reliable solution for early detection and quantification of plaque lesions in common carotid artery ultrasound scans. The system runs on a test US image in <1 second, proving overall performance to be clinically reliable.


Asunto(s)
Aprendizaje Profundo , Placa Aterosclerótica , Inteligencia Artificial , Arterias Carótidas/diagnóstico por imagen , Estudios de Cohortes , Humanos , Japón , Reproducibilidad de los Resultados
13.
J Vasc Surg Venous Lymphat Disord ; 10(2): 423-429.e2, 2022 03.
Artículo en Inglés | MEDLINE | ID: mdl-34450356

RESUMEN

OBJECTIVE: Traditional air plethysmography (APG) provides a quantitative measure of the residual volume fraction (RVF) after 10 tiptoe movements. The recent development of a wireless Bluetooth (Bluetooth SIG, Inc, Kirkland, Wash) APG device, the PicoFlow (Microlab Elettronica, Padua, Italy), enabled us to measure RVF during normal walking. The aim of our study was to compare the RVF obtained during tiptoeing with RVF obtained during normal walking in patients with deep venous pathology (ie, reflux and/or obstruction). METHODS: A total of 61 consecutive symptomatic patients (27 women and 34 men; median age, 46 years; range, 18-79 years) with chronic venous disease due to deep venous pathology (venous reflux or obstruction, or both) before treatment or persisting after intervention were included in the present study. Of the 122 total limbs examined, 79 were affected by deep chronic venous disease and 43 contralateral limbs were normal with normal deep veins and acted as controls. The APG examination was performed using the PicoFlow device using the standard examination technique. The RVF was calculated from the residual volume at the end of 10 tiptoe movements and also during normal walking. RESULTS: At the end of the 10 tiptoe movements, the mean ± standard deviation RVF was 27.0% ± 13.2% in the limbs with normal deep veins and 38.8% ± 16.9% in the limbs with deep chronic venous disease (P < .001). During walking, when a steady state in volume was reached, the RVF was 26.3% ± 17.8% in the limbs with normal deep veins and 43.1% ± 18.6% in limbs with deep venous disease (P < 0.001). A significant difference was found between limbs with normal deep veins and limbs with deep venous reflux, irrespective of which exercise was performed. However, the mean RVF between the limbs with normal deep veins and those with outflow obstruction in the absence of reflux was significant during walking (P = .012) but not during tiptoeing (P = .212). The mean RVF was higher in the C3 to C6 limbs than in the C0 to C2 limbs with tiptoeing (29.9% ± 14.5% vs 38.3% ± 17.0%; P < .006). Similar results were obtained with walking (29.2% ± 18.0% vs 42.4% ± 18.8%; P < .004). CONCLUSIONS: In limbs with normal deep veins and deep veins with reflux, the RVF measured during walking with wireless APG was similar to the RVF obtained during tiptoeing. However, in the limbs with outflow obstruction in the absence of reflux, the RVF during walking was higher than the RVF after tiptoeing. Our results have shown that the evaluation of RVF during walking is feasible and practical.


Asunto(s)
Determinación del Volumen Sanguíneo , Volumen Sanguíneo , Extremidad Inferior/irrigación sanguínea , Pletismografía , Venas/fisiopatología , Insuficiencia Venosa/diagnóstico , Caminata , Tecnología Inalámbrica , Adolescente , Adulto , Anciano , Determinación del Volumen Sanguíneo/instrumentación , Enfermedad Crónica , Femenino , Humanos , Masculino , Persona de Mediana Edad , Pletismografía/instrumentación , Valor Predictivo de las Pruebas , Insuficiencia Venosa/fisiopatología , Tecnología Inalámbrica/instrumentación , Adulto Joven
14.
Comput Biol Med ; 141: 105131, 2022 02.
Artículo en Inglés | MEDLINE | ID: mdl-34922173

RESUMEN

BACKGROUND: Early and automated detection of carotid plaques prevents strokes, which are the second leading cause of death worldwide according to the World Health Organization. Artificial intelligence (AI) offers automated solutions for plaque tissue characterization. Recently, solo deep learning (SDL) models have been used, but they do not take advantage of the tandem connectivity offered by AI's hybrid nature. Therefore, this study explores the use of hybrid deep learning (HDL) models in a multicenter framework, making this study the first of its kind. METHODS: We hypothesize that HDL techniques perform better than SDL and transfer learning (TL) techniques. We propose two kinds of HDL frameworks: (i) the fusion of two SDLs (Inception with ResNet) or (ii) 10 other kinds of tandem models that fuse SDL with ML. The system Atheromatic™ 2.0HDL (AtheroPoint, CA, USA) was designed on an augmentation framework and three kinds of loss functions (cross-entropy, hinge, and mean-square-error) during training to determine the best optimization paradigm. These 11 combined HDL models were then benchmarked against one SDL model and five types of TL models; thus, this study considers a total of 17 AI models. RESULTS: Among the 17 AI models, the best performing HDL system was that comprising CNN and decision tree (DT), as its accuracy and area-under-the-curve were 99.78 ± 1.05% and 0.99 (p<0.0001), respectively. These values are 6.4% and 3.2% better than those recorded for the SDL and TL models, respectively. We validated the performance of the HDL models with diagnostics odds ratio (DOR) and Cohen and Kappa statistics; here, HDL outperformed DL and TL by 23% and 7%, respectively. The online system ran in <2 s. CONCLUSION: HDL is a fast, reliable, and effective tool for characterizing the carotid plaque for early stroke risk stratification.


Asunto(s)
Aprendizaje Profundo , Placa Aterosclerótica , Accidente Cerebrovascular , Inteligencia Artificial , Arterias Carótidas , Humanos , Placa Aterosclerótica/diagnóstico por imagen
15.
Int Angiol ; 41(2): 158-169, 2022 Apr.
Artículo en Inglés | MEDLINE | ID: mdl-34913633

RESUMEN

The recommendations of international guidelines for the management of asymptomatic carotid stenosis (ACS) often vary considerably and extend from a conservative approach with risk factor modification and best medical treatment (BMT) alone, to a more aggressive approach with a carotid intervention plus BMT. The aim of the current multispecialty position statement was to reconcile the conflicting views on the topic. A literature review was performed with a focus on data from recent studies. Several clinical and imaging high-risk features have been identified that are associated with an increased long-term ipsilateral ischemic stroke risk in patients with ACS. Such high-risk clinical/imaging features include intraplaque hemorrhage, impaired cerebrovascular reserve, carotid plaque echolucency/ulceration/ neovascularization, a lipid-rich necrotic core, a thin or ruptured fibrous cap, silent brain infarction, a contralateral transient ischemic attack/stroke episode, male patients <75 years and microembolic signals on transcranial Doppler. There is growing evidence that 80-99% ACS indicate a higher stroke risk than 50-79% stenoses. Although aggressive risk factor control and BMT should be implemented in all ACS patients, several high-risk features that may increase the risk of a future cerebrovascular event are now documented. Consequently, some guidelines recommend a prophylactic carotid intervention in high-risk patients to prevent future cerebrovascular events. Until the results of the much-anticipated randomized controlled trials emerge, the jury is still out regarding the optimal management of ACS patients.


Asunto(s)
Estenosis Carotídea , Placa Aterosclerótica , Accidente Cerebrovascular , Arterias Carótidas , Estenosis Carotídea/complicaciones , Estenosis Carotídea/diagnóstico por imagen , Estenosis Carotídea/terapia , Humanos , Masculino , Factores de Riesgo , Accidente Cerebrovascular/etiología , Accidente Cerebrovascular/prevención & control
16.
Front Biosci (Landmark Ed) ; 26(11): 1312-1339, 2021 11 30.
Artículo en Inglés | MEDLINE | ID: mdl-34856770

RESUMEN

Background: Atherosclerosis is the primary cause of the cardiovascular disease (CVD). Several risk factors lead to atherosclerosis, and altered nutrition is one among those. Nutrition has been ignored quite often in the process of CVD risk assessment. Altered nutrition along with carotid ultrasound imaging-driven atherosclerotic plaque features can help in understanding and banishing the problems associated with the late diagnosis of CVD. Artificial intelligence (AI) is another promisingly adopted technology for CVD risk assessment and management. Therefore, we hypothesize that the risk of atherosclerotic CVD can be accurately monitored using carotid ultrasound imaging, predicted using AI-based algorithms, and reduced with the help of proper nutrition. Layout: The review presents a pathophysiological link between nutrition and atherosclerosis by gaining a deep insight into the processes involved at each stage of plaque development. After targeting the causes and finding out results by low-cost, user-friendly, ultrasound-based arterial imaging, it is important to (i) stratify the risks and (ii) monitor them by measuring plaque burden and computing risk score as part of the preventive framework. Artificial intelligence (AI)-based strategies are used to provide efficient CVD risk assessments. Finally, the review presents the role of AI for CVD risk assessment during COVID-19. Conclusions: By studying the mechanism of low-density lipoprotein formation, saturated and trans fat, and other dietary components that lead to plaque formation, we demonstrate the use of CVD risk assessment due to nutrition and atherosclerosis disease formation during normal and COVID times. Further, nutrition if included, as a part of the associated risk factors can benefit from atherosclerotic disease progression and its management using AI-based CVD risk assessment.


Asunto(s)
Arterias/diagnóstico por imagen , Aterosclerosis/diagnóstico por imagen , COVID-19/fisiopatología , Enfermedades Cardiovasculares/diagnóstico por imagen , Estado Nutricional , Algoritmos , COVID-19/diagnóstico por imagen , COVID-19/virología , Humanos , Factores de Riesgo , SARS-CoV-2/aislamiento & purificación
17.
Diagnostics (Basel) ; 11(12)2021 Dec 15.
Artículo en Inglés | MEDLINE | ID: mdl-34943603

RESUMEN

(1) Background: COVID-19 computed tomography (CT) lung segmentation is critical for COVID lung severity diagnosis. Earlier proposed approaches during 2020-2021 were semiautomated or automated but not accurate, user-friendly, and industry-standard benchmarked. The proposed study compared the COVID Lung Image Analysis System, COVLIAS 1.0 (GBTI, Inc., and AtheroPointTM, Roseville, CA, USA, referred to as COVLIAS), against MedSeg, a web-based Artificial Intelligence (AI) segmentation tool, where COVLIAS uses hybrid deep learning (HDL) models for CT lung segmentation. (2) Materials and Methods: The proposed study used 5000 ITALIAN COVID-19 positive CT lung images collected from 72 patients (experimental data) that confirmed the reverse transcription-polymerase chain reaction (RT-PCR) test. Two hybrid AI models from the COVLIAS system, namely, VGG-SegNet (HDL 1) and ResNet-SegNet (HDL 2), were used to segment the CT lungs. As part of the results, we compared both COVLIAS and MedSeg against two manual delineations (MD 1 and MD 2) using (i) Bland-Altman plots, (ii) Correlation coefficient (CC) plots, (iii) Receiver operating characteristic curve, and (iv) Figure of Merit and (v) visual overlays. A cohort of 500 CROATIA COVID-19 positive CT lung images (validation data) was used. A previously trained COVLIAS model was directly applied to the validation data (as part of Unseen-AI) to segment the CT lungs and compare them against MedSeg. (3) Result: For the experimental data, the four CCs between COVLIAS (HDL 1) vs. MD 1, COVLIAS (HDL 1) vs. MD 2, COVLIAS (HDL 2) vs. MD 1, and COVLIAS (HDL 2) vs. MD 2 were 0.96, 0.96, 0.96, and 0.96, respectively. The mean value of the COVLIAS system for the above four readings was 0.96. CC between MedSeg vs. MD 1 and MedSeg vs. MD 2 was 0.98 and 0.98, respectively. Both had a mean value of 0.98. On the validation data, the CC between COVLIAS (HDL 1) vs. MedSeg and COVLIAS (HDL 2) vs. MedSeg was 0.98 and 0.99, respectively. For the experimental data, the difference between the mean values for COVLIAS and MedSeg showed a difference of <2.5%, meeting the standard of equivalence. The average running times for COVLIAS and MedSeg on a single lung CT slice were ~4 s and ~10 s, respectively. (4) Conclusions: The performances of COVLIAS and MedSeg were similar. However, COVLIAS showed improved computing time over MedSeg.

18.
Diagnostics (Basel) ; 11(12)2021 Dec 02.
Artículo en Inglés | MEDLINE | ID: mdl-34943494

RESUMEN

BACKGROUND: The early detection of carotid wall plaque is recommended in the prevention of cardiovascular disease (CVD) in moderate-risk patients. Previous techniques for B-mode carotid atherosclerotic wall plaque segmentation used artificial intelligence (AI) methods on monoethnic databases, where training and testing are from the "same" ethnic group ("Seen AI"). Therefore, the versatility of the system is questionable. This is the first study of its kind that uses the "Unseen AI" paradigm where training and testing are from "different" ethnic groups. We hypothesized that deep learning (DL) models should perform in 10% proximity between "Unseen AI" and "Seen AI". METHODOLOGY: Two cohorts from multi-ethnic groups (330 Japanese and 300 Hong Kong (HK)) were used for the validation of our hypothesis. We used a four-layered UNet architecture for the segmentation of the atherosclerotic wall with low plaque. "Unseen AI" (training: Japanese, testing: HK or vice versa) and "Seen AI" experiments (single ethnicity or mixed ethnicity) were performed. Evaluation was conducted by measuring the wall plaque area. Statistical tests were conducted for its stability and reliability. RESULTS: When using the UNet DL architecture, the "Unseen AI" pair one (Training: 330 Japanese and Testing: 300 HK), the mean accuracy, dice-similarity, and correlation-coefficient were 98.55, 78.38, and 0.80 (p < 0.0001), respectively, while for "Unseen AI" pair two (Training: 300 HK and Testing: 330 Japanese), these were 98.67, 82.49, and 0.87 (p < 0.0001), respectively. Using "Seen AI", the same parameters were 99.01, 86.89 and 0.92 (p < 0.0001), respectively. CONCLUSION: We demonstrated that "Unseen AI" was in close proximity (<10%) to "Seen AI", validating our DL model for low atherosclerotic wall plaque segmentation. The online system runs < 1 s.

19.
Diagnostics (Basel) ; 11(11)2021 Nov 01.
Artículo en Inglés | MEDLINE | ID: mdl-34829372

RESUMEN

Background: For COVID-19 lung severity, segmentation of lungs on computed tomography (CT) is the first crucial step. Current deep learning (DL)-based Artificial Intelligence (AI) models have a bias in the training stage of segmentation because only one set of ground truth (GT) annotations are evaluated. We propose a robust and stable inter-variability analysis of CT lung segmentation in COVID-19 to avoid the effect of bias. Methodology: The proposed inter-variability study consists of two GT tracers for lung segmentation on chest CT. Three AI models, PSP Net, VGG-SegNet, and ResNet-SegNet, were trained using GT annotations. We hypothesized that if AI models are trained on the GT tracings from multiple experience levels, and if the AI performance on the test data between these AI models is within the 5% range, one can consider such an AI model robust and unbiased. The K5 protocol (training to testing: 80%:20%) was adapted. Ten kinds of metrics were used for performance evaluation. Results: The database consisted of 5000 CT chest images from 72 COVID-19-infected patients. By computing the coefficient of correlations (CC) between the output of the two AI models trained corresponding to the two GT tracers, computing their differences in their CC, and repeating the process for all three AI-models, we show the differences as 0%, 0.51%, and 2.04% (all < 5%), thereby validating the hypothesis. The performance was comparable; however, it had the following order: ResNet-SegNet > PSP Net > VGG-SegNet. Conclusions: The AI models were clinically robust and stable during the inter-variability analysis on the CT lung segmentation on COVID-19 patients.

20.
Diagnostics (Basel) ; 11(11)2021 Nov 15.
Artículo en Inglés | MEDLINE | ID: mdl-34829456

RESUMEN

Background and Purpose: Only 1-2% of the internal carotid artery asymptomatic plaques are unstable as a result of >80% stenosis. Thus, unnecessary efforts can be saved if these plaques can be characterized and classified into symptomatic and asymptomatic using non-invasive B-mode ultrasound. Earlier plaque tissue characterization (PTC) methods were machine learning (ML)-based, which used hand-crafted features that yielded lower accuracy and unreliability. The proposed study shows the role of transfer learning (TL)-based deep learning models for PTC. Methods: As pertained weights were used in the supercomputer framework, we hypothesize that transfer learning (TL) provides improved performance compared with deep learning. We applied 11 kinds of artificial intelligence (AI) models, 10 of them were augmented and optimized using TL approaches-a class of Atheromatic™ 2.0 TL (AtheroPoint™, Roseville, CA, USA) that consisted of (i-ii) Visual Geometric Group-16, 19 (VGG16, 19); (iii) Inception V3 (IV3); (iv-v) DenseNet121, 169; (vi) XceptionNet; (vii) ResNet50; (viii) MobileNet; (ix) AlexNet; (x) SqueezeNet; and one DL-based (xi) SuriNet-derived from UNet. We benchmark 11 AI models against our earlier deep convolutional neural network (DCNN) model. Results: The best performing TL was MobileNet, with accuracy and area-under-the-curve (AUC) pairs of 96.10 ± 3% and 0.961 (p < 0.0001), respectively. In DL, DCNN was comparable to SuriNet, with an accuracy of 95.66% and 92.7 ± 5.66%, and an AUC of 0.956 (p < 0.0001) and 0.927 (p < 0.0001), respectively. We validated the performance of the AI architectures with established biomarkers such as greyscale median (GSM), fractal dimension (FD), higher-order spectra (HOS), and visual heatmaps. We benchmarked against previously developed Atheromatic™ 1.0 ML and showed an improvement of 12.9%. Conclusions: TL is a powerful AI tool for PTC into symptomatic and asymptomatic plaques.

SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA
...