Anti-LGI1 Autoimmune Encephalitis in a Patient with Rheumatoid Arthritis and MGUS.

Background: Anti-leucine-rich glioma inactivated 1 limbic encephalitis (anti-LGI1 LE) is one of the most frequent autoimmune encephalitis, commonly coexisting with other autoimmune diseases. Rheumatoid arthritis (RA) and monoclonal gammopathy of unknown significance (MGUS) are commonly associated with autoimmune phenomena. However, neither RA nor MGUS have been described in the literature to date as coexisting with anti-LGI1 LE. Case description: We present the case of anti-LGI1 LE in a male patient with rheumatoid arthritis, who was also found to have an MGUS. The patient was initially treated with corticosteroids and IV immunoglobulin. After a mild relapse, his treatment was complemented with rituximab, resulting in complete regression of the disease symptoms. Conclusions: Our report provides evidence for the coexistence of anti-LGI1 LE with RA and/or MGUS, thus extending the differential diagnosis of patients suffering with these disease entities that present with neuropsychiatric symptoms suggestive of encephalitis. Moreover, this case raises challenges on the management of the coexistence of these diseases, given the lack of therapeutic guidelines and their potential interaction on a pathophysiological and a clinical level. LEARNING POINTS: In a patient with known autoimmune or malignant background who presents with neuropsychiatric symptoms, after excluding infectious encephalitis or central nervous system involvement in the primary disease condition, autoimmune limbic encephalitis (LE) should also be considered.In a patient diagnosed with anti-LGI1 LE there should be an extensive check for coexisting occult pre-malignant conditions, even for months after disease presentation.Clinical management and treatment options of anti-LGI1 LE when coexisting with other autoimmune or pre-malignant conditions can be challenging; thus, more research is needed towards that direction.

Prevalence, awareness, and control of hypertension in Greece before and after the COVID-19 pandemic: May Measurement Month survey 2019-2022.

OBJECTIVE: The COVID-19 pandemic had an adverse impact on several cardiovascular risk factors. This study investigated the prevalence, awareness and treatment of hypertension in Greece before and after the pandemic. Data were collected in the context of the May Measurement Month (MMM) global survey initiated by the International Society of Hypertension. METHODS: Adult volunteers (age ≥ 18 years) were recruited through opportunistic screening in public areas across cities in Greece in 2019 and 2022. Medical history and triplicate sitting blood pressure (BP) measurements were taken using validated automated upper-arm cuff devices. The data were uploaded to the international MMM cloud platform. Hypertension was defined as systolic BP ≥ 140 mm Hg and/or diastolic ≥90 mm Hg and/or self-reported use of drugs for hypertension. The same threshold was used to define uncontrolled BP in treated individuals. RESULTS: Data from 12,080 adults were collected (5,727/6,353 in MMM 2019/2022; men 46/49%, p < 0.01; mean age 52.7 ± 16.6/54.8 ± 16.2, p < 0.001; smokers, 24.7/30.5, p < 0.001; diabetics 12/11.5%, p = NS; cardiovascular disease 5/5.8%, p = NS). The prevalence of hypertension was 41.6/42.6% (MMM 2019/2022, p = NS), with 21.3/27.5% of individuals with hypertension being unaware of their condition (p < 0.001), 5.6/2.4% aware untreated (p < 0.001), 24.8/22.1% treated uncontrolled (p < 0.05), and 48.3/47.8% treated controlled (p = NS). CONCLUSION: In Greece, the COVID-19 pandemic did not appear to affect the prevalence and control of hypertension; however, the rate of undiagnosed hypertension was higher after the pandemic. National strategies need to be implemented for the early detection and optimal management of hypertension in the general population in Greece.

Progression of subclinical atherosclerosis in ankylosing spondylitis: a 10-year prospective study.

Chronic systemic inflammation contributes to increased CVD burden in Ankylosing Spondylitis (AS). Since long-term follow-up data on subclinical atherosclerosis acceleration are lacking, we examined its progression in contemporary AS patients during 10 years. Fifty-three (89% male, aged 50.4 (36.3-55.9) years,) non-diabetic, CVD-free AS patients and 53 age-sex-matched non-diabetic, control individuals were re-evaluated after 9.2-10.2 years by ultrasonography for carotid/femoral atheromatosis, pulse wave velocity (PWV) and intima-media thickness (IMT), performed by the same operator/protocol. New atheromatic plaque formation, PWV deterioration, and IMT increase were associated only with classical CVD risk factors, as reflected by the heartSCORE (age, gender, smoking status, blood pressure and cholesterol levels) by multivariate analysis, rather than disease presence. However, among AS patients, despite remission/low disease activity at follow-up end in 79%, atheromatosis progression was associated by multivariate analysis with higher BASDAI scores (p = 0.028), independently of biologic therapies administered in 2/3 of them. Moreover, in AS patients, but not in controls, PWV values at baseline were associated with plaque progression during the 10-year follow-up after taking into account baseline heartSCORE and plaque burden status (p = 0.033). Despite comparable prevalence of both hypertension and hypercholesterolemia at baseline between patients and controls, a lower percentage of AS patients had achieved "adequate" CVD risk factor control at follow-up end (11% vs 25% respectively, p = 0.076). Classical CVD risk factors and residual disease activity account for the progression of subclinical atherosclerosis in AS, pointing to the unmet needs in the contemporary management of these patients.

Quality Indicators and Clinical Outcomes of Acute Stroke: Results from a Prospective Multicenter Registry in Greece (SUN4P).

AIM: The Stroke Units Necessity for Patients (SUN4P) project aims to provide essential data on stroke healthcare in Greece. Herein, we present results on established quality indicators and outcomes after first-ever stroke occurrences. METHODS: This prospective multicenter study included consecutive patients admitted to nine hospitals across Greece in 2019-2021. Descriptive statistics were used to present patients' characteristics, key performance measures and stroke outcomes. RESULTS: Among 892 patients, 755 had ischemic stroke (IS) (mean age 75.6 ± 13.6, 48.7% males) and 137 had hemorrhagic stroke (HS) (mean age 75.8 ± 13.2, 57.7% males). Of those, 15.4% of IS and 8% of HS patients were treated in the acute stroke unit (ASU) and 20.7% and 33.8% were admitted to the intensive care unit (ICU) or high-dependency unit (HDU), respectively. A total of 35 (4.6%) out of 125 eligible patients received intravenous alteplase with a door-to needle time of 60 min (21-90). The time to first scan for IS patients was 60 min (31-105) with 53.2% undergoing a CT scan within 60 min post presentation. Furthermore, 94.4% were discharged on antiplatelets, 69.8% on lipid-lowering therapy and 61.6% on antihypertensives. Oral anticoagulants (OAC) were initiated in 73.2% of the 153 IS patients with atrial fibrillation (AF). Among the 687 IS patients who survived, 85.4% were discharged home, 12% were transferred to rehabilitation centers, 1.2% to nursing homes and 1.3% to another hospital. CONCLUSIONS: The SUN4P Registry is the first study to provide data from a prospectively collected cohort of consecutive patients from nine representative national hospitals. It represents an important step in the evaluation and improvement of the quality of acute stroke care in Greece.

The Cost and the Value of Stroke Care in Greece: Results from the SUN4P Study.

The aim of this study was to measure the one-year total cost of strokes and to investigate the value of stroke care, defined as cost per QALY. The study population included 892 patients with first-ever acute strokes, hemorrhagic strokes, and ischemic strokes, (ICD-10 codes: I61, I63, and I64) admitted within 48 h of symptoms onset to nine public hospitals located in six cities. We conducted a bottom-up cost analysis from the societal point of view. All cost components including direct medical costs, productivity losses due to morbidity and mortality, and informal care costs were considered. We used an annual time horizon, including all costs for 2021, irrespective of the time of disease onset. The average cost (direct and indirect) was extrapolated in order to estimate the national annual burden associated with stroke. We estimated the total cost of stroke in Greece at EUR 343.1 mil. a year in 2021, (EUR 10,722/patient or EUR 23,308 per QALY). Out of EUR 343.1 mil., 53.3% (EUR 182.9 mil.) consisted of direct healthcare costs, representing 1.1% of current health expenditure in 2021. Overall, productivity losses were calculated at EUR 160.2 mil. The mean productivity losses were estimated to be 116 work days with 55.1 days lost due to premature retirement and absenteeism from work, 18.5 days lost due to mortality, and 42.4 days lost due to informal caregiving by family members. This study highlights the burden of stroke and underlines the need for stakeholders and policymakers to re-organize stroke care and promote interventions that have been proven cost-effective.

Requirements for design and function of blood pressure measuring devices used for the management of hypertension: Consensus Statement by the European Society of Hypertension Working Group on Blood Pressure Monitoring and Cardiovascular Variability and STRIDE BP.

OBJECTIVE: To develop scientific consensus recommendations for the optimal design and functions of different types of blood pressure (BP) measuring devices used in clinical practice for the detection, management, and long-term follow-up of hypertension. METHODS: A scientific consensus meeting was performed by the European Society of Hypertension (ESH) Working Group on BP Monitoring and Cardiovascular Variability and STRIDE BP (Science and Technology for Regional Innovation and Development in Europe) during the 2022 Scientific Meeting of the ESH in Athens, Greece. Manufacturers were also invited to provide their feedback on BP device design and development. Thirty-one international experts in clinical hypertension and BP monitoring contributed to the development of consensus recommendations on the optimal design of BP devices. STATEMENT: International consensus was reached on the requirements for the design and features of five types of BP monitors, including office (or clinic) BP monitors, ambulatory BP monitors, home BP monitors, home BP telemonitors, and kiosk BP monitors for public spaces. For each device type "essential" requirements (must have), and "optional" ones (may have) are presented, as well as additional comments on the optimal device design and features. CONCLUSIONS: These consensus recommendations aim at providing manufacturers of BP devices with the requirements that are considered mandatory, or optional, by clinical experts involved in the detection and management of hypertension. They are also directed to administrative healthcare personnel involved in the provision and purchase of BP devices so that they can recommend the most appropriate ones.

Alterations in Retinal Vessel Diameters in Patients with Retinal Vein Occlusion before and after Treatment with Intravitreal Ranibizumab.

Purpose: To investigate the alterations of retinal vessel diameters in patients with macular edema secondary to retinal vein occlusion (RVO), before and after treatment with intravitreal ranibizumab. Methods: Digital retinal images were obtained from 16 patients and retinal vessel diameters were measured before and three months after treatment with intravitreal ranibizumab with validated software to determine central retinal arteriolar and venular equivalents, as well as arteriolar to venular ratio. Results: In 17 eyes of 16 patients with macular edema secondary to RVO (10 with branch RVO and 6 with central RVO) aged 67 ± 10.2 years, we found that diameters of both retinal arterioles and venules were significantly decreased after intravitreal ranibizumab treatment. Specifically, the central retinal arteriolar equivalent was 215.2 ± 11.2 µm at baseline and 201.2 ± 11.1 µm at month 3 after treatment (p < 0.001), while the central retinal venular equivalent was 233.8 ± 29.6 µm before treatment versus 207.6 ± 21.7 µm at month 3 after treatment (p < 0.001). Conclusions: A significant vasoconstriction in both retinal arterioles and venules in patients with RVO was found at month 3 after intravitreal ranibizumab treatment compared to baseline. This could be of clinical importance, since the degree of vasoconstriction might be an early marker of treatment efficacy, compatible with the idea that hypoxia is the major trigger of VEGF in RVO. Further studies should be conducted to confirm our findings.

Blood pressure variability: methodological aspects, clinical relevance and practical indications for management - a European Society of Hypertension position paper ∗.

Blood pressure is not a static parameter, but rather undergoes continuous fluctuations over time, as a result of the interaction between environmental and behavioural factors on one side and intrinsic cardiovascular regulatory mechanisms on the other side. Increased blood pressure variability (BPV) may indicate an impaired cardiovascular regulation and may represent a cardiovascular risk factor itself, having been associated with increased all-cause and cardiovascular mortality, stroke, coronary artery disease, heart failure, end-stage renal disease, and dementia incidence. Nonetheless, BPV was considered only a research issue in previous hypertension management guidelines, because the available evidence on its clinical relevance presents several gaps and is based on heterogeneous studies with limited standardization of methods for BPV assessment. The aim of this position paper, with contributions from members of the European Society of Hypertension Working Group on Blood Pressure Monitoring and Cardiovascular Variability and from a number of international experts, is to summarize the available evidence in the field of BPV assessment methodology and clinical applications and to provide practical indications on how to measure and interpret BPV in research and clinical settings based on currently available data. Pending issues and clinical and methodological recommendations supported by available evidence are also reported. The information provided by this paper should contribute to a better standardization of future studies on BPV, but should also provide clinicians with some indications on how BPV can be managed based on currently available data.

Time of blood pressure in target range in acute ischemic stroke.

OBJECTIVE: The purpose of this study was to investigate the association of blood pressure (BP) time-in-target range (TTR) derived from 24-h ambulatory BP monitoring (ABPM) during the acute phase of ischemic stroke (AIS), with the severity of stroke and its predictive value for the 3 months outcome. METHODS: A total of 228 AIS patients (prospective multicenter follow-up study) underwent ABPM every 20 min within 48 h from stroke onset using an automated oscillometric device. Clinical and laboratory findings were recorded. Mean BP parameters, BP variability and TTR for SBP (90-140 mmHg), DBP (60-90 mmHg), and mean arterial pressure (MAP) were calculated. Endpoints were death and disability/death at 3 months. RESULTS: A total of 14 942 BP measurements were recorded (∼66 per AIS patient) within 72 h of stroke onset. Patient's 24-h TTR was 34.7 ±â€Š29.9, 64.3 ±â€Š24.2, and 55.3 ±â€Š29.4% for SBP, DBP and MAP, respectively. In patients without prior hypertension, TTR was lower as stroke severity increased for both DBP (P = 0.031) and MAP (P = 0.016). In 175 patients without prior disability, increase in TTR of DBP and MAP associated significantly with a decreased risk of disability/death (hazard ratio 0.96, 95% CI 0.95-0.99, P = 0.007 and hazard ratio 0.97, 95% CI 0.96-0.99, P = 0.007). TTR of SBP in 130-180 mmHg and 110-160 mmHg ranges seems to be related with mortality and disability outcomes, respectively. CONCLUSION: TTR can be included for a more detailed description of BP course, according to stroke severity, and for the evaluation of BP predictive role, in addition to mean BP values, derived from ABPM during the acute phase of AIS. CLINICAL TRIAL REGISTRATIONURL: http://www.clinicaltrials.gov. Unique identifier: NCT01915862.

Economics of Artificial Intelligence in Healthcare: Diagnosis vs. Treatment.

Motivation: The price of medical treatment continues to rise due to (i) an increasing population; (ii) an aging human growth; (iii) disease prevalence; (iv) a rise in the frequency of patients that utilize health care services; and (v) increase in the price. Objective: Artificial Intelligence (AI) is already well-known for its superiority in various healthcare applications, including the segmentation of lesions in images, speech recognition, smartphone personal assistants, navigation, ride-sharing apps, and many more. Our study is based on two hypotheses: (i) AI offers more economic solutions compared to conventional methods; (ii) AI treatment offers stronger economics compared to AI diagnosis. This novel study aims to evaluate AI technology in the context of healthcare costs, namely in the areas of diagnosis and treatment, and then compare it to the traditional or non-AI-based approaches. Methodology: PRISMA was used to select the best 200 studies for AI in healthcare with a primary focus on cost reduction, especially towards diagnosis and treatment. We defined the diagnosis and treatment architectures, investigated their characteristics, and categorized the roles that AI plays in the diagnostic and therapeutic paradigms. We experimented with various combinations of different assumptions by integrating AI and then comparing it against conventional costs. Lastly, we dwell on three powerful future concepts of AI, namely, pruning, bias, explainability, and regulatory approvals of AI systems. Conclusions: The model shows tremendous cost savings using AI tools in diagnosis and treatment. The economics of AI can be improved by incorporating pruning, reduction in AI bias, explainability, and regulatory approvals.

Cardiovascular/Stroke Risk Stratification in Diabetic Foot Infection Patients Using Deep Learning-Based Artificial Intelligence: An Investigative Study.

A diabetic foot infection (DFI) is among the most serious, incurable, and costly to treat conditions. The presence of a DFI renders machine learning (ML) systems extremely nonlinear, posing difficulties in CVD/stroke risk stratification. In addition, there is a limited number of well-explained ML paradigms due to comorbidity, sample size limits, and weak scientific and clinical validation methodologies. Deep neural networks (DNN) are potent machines for learning that generalize nonlinear situations. The objective of this article is to propose a novel investigation of deep learning (DL) solutions for predicting CVD/stroke risk in DFI patients. The Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) search strategy was used for the selection of 207 studies. We hypothesize that a DFI is responsible for increased morbidity and mortality due to the worsening of atherosclerotic disease and affecting coronary artery disease (CAD). Since surrogate biomarkers for CAD, such as carotid artery disease, can be used for monitoring CVD, we can thus use a DL-based model, namely, Long Short-Term Memory (LSTM) and Recurrent Neural Networks (RNN) for CVD/stroke risk prediction in DFI patients, which combines covariates such as office and laboratory-based biomarkers, carotid ultrasound image phenotype (CUSIP) lesions, along with the DFI severity. We confirmed the viability of CVD/stroke risk stratification in the DFI patients. Strong designs were found in the research of the DL architectures for CVD/stroke risk stratification. Finally, we analyzed the AI bias and proposed strategies for the early diagnosis of CVD/stroke in DFI patients. Since DFI patients have an aggressive atherosclerotic disease, leading to prominent CVD/stroke risk, we, therefore, conclude that the DL paradigm is very effective for predicting the risk of CVD/stroke in DFI patients.

Vascular Implications of COVID-19: Role of Radiological Imaging, Artificial Intelligence, and Tissue Characterization: A Special Report.

The SARS-CoV-2 virus has caused a pandemic, infecting nearly 80 million people worldwide, with mortality exceeding six million. The average survival span is just 14 days from the time the symptoms become aggressive. The present study delineates the deep-driven vascular damage in the pulmonary, renal, coronary, and carotid vessels due to SARS-CoV-2. This special report addresses an important gap in the literature in understanding (i) the pathophysiology of vascular damage and the role of medical imaging in the visualization of the damage caused by SARS-CoV-2, and (ii) further understanding the severity of COVID-19 using artificial intelligence (AI)-based tissue characterization (TC). PRISMA was used to select 296 studies for AI-based TC. Radiological imaging techniques such as magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound were selected for imaging of the vasculature infected by COVID-19. Four kinds of hypotheses are presented for showing the vascular damage in radiological images due to COVID-19. Three kinds of AI models, namely, machine learning, deep learning, and transfer learning, are used for TC. Further, the study presents recommendations for improving AI-based architectures for vascular studies. We conclude that the process of vascular damage due to COVID-19 has similarities across vessel types, even though it results in multi-organ dysfunction. Although the mortality rate is ~2% of those infected, the long-term effect of COVID-19 needs monitoring to avoid deaths. AI seems to be penetrating the health care industry at warp speed, and we expect to see an emerging role in patient care, reduce the mortality and morbidity rate.

COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans.

Background: The previous COVID-19 lung diagnosis system lacks both scientific validation and the role of explainable artificial intelligence (AI) for understanding lesion localization. This study presents a cloud-based explainable AI, the "COVLIAS 2.0-cXAI" system using four kinds of class activation maps (CAM) models. Methodology: Our cohort consisted of ~6000 CT slices from two sources (Croatia, 80 COVID-19 patients and Italy, 15 control patients). COVLIAS 2.0-cXAI design consisted of three stages: (i) automated lung segmentation using hybrid deep learning ResNet-UNet model by automatic adjustment of Hounsfield units, hyperparameter optimization, and parallel and distributed training, (ii) classification using three kinds of DenseNet (DN) models (DN-121, DN-169, DN-201), and (iii) validation using four kinds of CAM visualization techniques: gradient-weighted class activation mapping (Grad-CAM), Grad-CAM++, score-weighted CAM (Score-CAM), and FasterScore-CAM. The COVLIAS 2.0-cXAI was validated by three trained senior radiologists for its stability and reliability. The Friedman test was also performed on the scores of the three radiologists. Results: The ResNet-UNet segmentation model resulted in dice similarity of 0.96, Jaccard index of 0.93, a correlation coefficient of 0.99, with a figure-of-merit of 95.99%, while the classifier accuracies for the three DN nets (DN-121, DN-169, and DN-201) were 98%, 98%, and 99% with a loss of ~0.003, ~0.0025, and ~0.002 using 50 epochs, respectively. The mean AUC for all three DN models was 0.99 (p < 0.0001). The COVLIAS 2.0-cXAI showed 80% scans for mean alignment index (MAI) between heatmaps and gold standard, a score of four out of five, establishing the system for clinical settings. Conclusions: The COVLIAS 2.0-cXAI successfully showed a cloud-based explainable AI system for lesion localization in lung CT scans.

Cardiovascular Risk Stratification in Diabetic Retinopathy via Atherosclerotic Pathway in COVID-19/Non-COVID-19 Frameworks Using Artificial Intelligence Paradigm: A Narrative Review.

Diabetes is one of the main causes of the rising cases of blindness in adults. This microvascular complication of diabetes is termed diabetic retinopathy (DR) and is associated with an expanding risk of cardiovascular events in diabetes patients. DR, in its various forms, is seen to be a powerful indicator of atherosclerosis. Further, the macrovascular complication of diabetes leads to coronary artery disease (CAD). Thus, the timely identification of cardiovascular disease (CVD) complications in DR patients is of utmost importance. Since CAD risk assessment is expensive for low-income countries, it is important to look for surrogate biomarkers for risk stratification of CVD in DR patients. Due to the common genetic makeup between the coronary and carotid arteries, low-cost, high-resolution imaging such as carotid B-mode ultrasound (US) can be used for arterial tissue characterization and risk stratification in DR patients. The advent of artificial intelligence (AI) techniques has facilitated the handling of large cohorts in a big data framework to identify atherosclerotic plaque features in arterial ultrasound. This enables timely CVD risk assessment and risk stratification of patients with DR. Thus, this review focuses on understanding the pathophysiology of DR, retinal and CAD imaging, the role of surrogate markers for CVD, and finally, the CVD risk stratification of DR patients. The review shows a step-by-step cyclic activity of how diabetes and atherosclerotic disease cause DR, leading to the worsening of CVD. We propose a solution to how AI can help in the identification of CVD risk. Lastly, we analyze the role of DR/CVD in the COVID-19 framework.

COVLIAS 1.0Lesion vs. MedSeg: An Artificial Intelligence Framework for Automated Lesion Segmentation in COVID-19 Lung Computed Tomography Scans.

Background: COVID-19 is a disease with multiple variants, and is quickly spreading throughout the world. It is crucial to identify patients who are suspected of having COVID-19 early, because the vaccine is not readily available in certain parts of the world. Methodology: Lung computed tomography (CT) imaging can be used to diagnose COVID-19 as an alternative to the RT-PCR test in some cases. The occurrence of ground-glass opacities in the lung region is a characteristic of COVID-19 in chest CT scans, and these are daunting to locate and segment manually. The proposed study consists of a combination of solo deep learning (DL) and hybrid DL (HDL) models to tackle the lesion location and segmentation more quickly. One DL and four HDL models­namely, PSPNet, VGG-SegNet, ResNet-SegNet, VGG-UNet, and ResNet-UNet­were trained by an expert radiologist. The training scheme adopted a fivefold cross-validation strategy on a cohort of 3000 images selected from a set of 40 COVID-19-positive individuals. Results: The proposed variability study uses tracings from two trained radiologists as part of the validation. Five artificial intelligence (AI) models were benchmarked against MedSeg. The best AI model, ResNet-UNet, was superior to MedSeg by 9% and 15% for Dice and Jaccard, respectively, when compared against MD 1, and by 4% and 8%, respectively, when compared against MD 2. Statistical tests­namely, the Mann−Whitney test, paired t-test, and Wilcoxon test­demonstrated its stability and reliability, with p < 0.0001. The online system for each slice was <1 s. Conclusions: The AI models reliably located and segmented COVID-19 lesions in CT scans. The COVLIAS 1.0Lesion lesion locator passed the intervariability test.

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.

Stroke Units Necessity for Patients, Web-Based "SUN4P" Registry: Descriptive Characteristics of the Population.

The aim of this study was to present the descriptive characteristics of the Stroke Units Necessity for Patients (SUN4P) registry. METHODS: The study population derived from the web-based SUN4P registry included 823 patients with first-ever acute stroke. Descriptive statistics were used to present patients' characteristics. RESULTS: The vast majority of patients (80.4%) had an ischemic stroke, whereas 15.4% had a hemorrhagic stroke. Hypertension was the leading risk factor in both patients. The patients with ischemic stroke had higher prevalence of traditional cardiovascular risk factors such as diabetes mellitus, dyslipidemia and smoking and most commonly cryptogenic stroke (39%). National Institutes of Health Stroke Scale (NIHSS) was higher among patients with hemorrhagic in comparison to those with ischemic stroke (10.5 vs 6 respectively). Moreover, all patients had similar rate of disability prior to stroke, as shown by Modified Rankin Scale (mRS=0). CONCLUSIONS: These data are in accordance with current evidence and should be thoroughly assessed in order to ensure optimal therapeutic management of stroke patients.

Assessing Staff's and Stroke Patients' Experiences in 8 Hospitals in Greece: Results from a Prospective Multi-Center Study ("SUN4Patients").

To assess stroke patient-reported experiences and hospital staff experiences, during hospital stay. METHODS: Stroke patient-reported experiences (n=387) were recorded using the translated and culturally adapted NHS-Stroke Questionnaire into Greek and staff experiences (n=236) were investigated using the Compassion Satisfaction and Burnout subscales of the ProQOL questionnaire. RESULTS: Staff's mean compassion satisfaction score was 39.2 (SD=6.3) and mean burnout score was 24.3 (SD=5.6). Only 38.5% of the staff stated that there is smooth cooperation with healthcare professionals of other specialties/disciplines. Personnel working in an NHS Hospital was more satisfied and less burned-out when compared to personnel working at a University Hospital (p=0.02 and p<0.001, respectively). Mean total patient-reported experiences score was 81.9 (SD=9.5). Bivariate analysis revealed statistically significant differences for total patient-reported experiences among the eight study hospitals (p>0.001). CONCLUSIONS: Health policy planners and decision-makers must take into consideration the results of such self-reported measures to establish innovative techniques to accomplish goals such as staff-specialization, continuous training and applying formal frameworks for efficient cooperation amongst different disciplines.

Inpatient Cost of Stroke Care in Greece: Preliminary Results of the Web-Based "SUN4P" Registry.

The aim of this study was to calculate the average operational cost per sub-type of stroke patient and to investigate cost drivers (e.g. ALoS, NIHSS score, age) correlated to cost. METHODS: Direct medical costs (diagnostic imaging and clinical laboratory exams, overheads/bed cost, pharmaceuticals, ringers and other non-durables and inpatient rehabilitation) per patient were calculated from the providers' (hospitals') perspective. Resource use data derived from the "SUN4P" web-based registry and unit costs were retrieved from publically available sources and were assigned to resource use. RESULTS: The sample comprised 6,282 inpatient days of 750 patients (mean age: 75.5±13.3 years) admitted from July 2019 to July 2021, in nine public hospitals. Mean length of stay was 8.4±7.6 days and mean total operational cost was calculated to €1,239.4 (from which 45% and 35% related to diagnostic exams and overheads/bed cost respectively). Mean cost related to hemorrhagic stroke patients that were discharged alive was calculated significantly higher compared to mean cost related to ischemic stroke patients who didn't undertake thrombolysis and were also discharged alive from the hospital (€2,155.2 vs. €945.2, p<0.001). Linear regression analysis revealed that length of stay was significantly correlated with cost (coefficient beta=232, 95% CI confidence interval = 220-243, p<0.001). CONCLUSIONS: These findings are in accordance with current evidence and should be thoroughly assessed to rationalize inpatient reimbursement rates in order to achieve improved value of care.

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.