Citations

Importance In patients with severe aortic valve stenosis at intermediate surgical risk, transcatheter aortic valve replacement (TAVR) with a self-expanding supra-annular valve was noninferior to surgery for all-cause mortality or disabling stroke at 2 years. Comparisons of longer-term clinical and hemodynamic outcomes in these patients are limited. Objective To report prespecified secondary 5-year outcomes from the Symptomatic Aortic Stenosis in Intermediate Risk Subjects Who Need Aortic Valve Replacement (SURTAVI) randomized clinical trial. Design, Setting, and Participants SURTAVI is a prospective randomized, unblinded clinical trial. Randomization was stratified by investigational site and need for revascularization determined by the local heart teams. Patients with severe aortic valve stenosis deemed to be at intermediate risk of 30-day surgical mortality were enrolled at 87 centers from June 19, 2012, to June 30, 2016, in Europe and North America. Analysis took place between August and October 2021. Intervention Patients were randomized to TAVR with a self-expanding, supra-annular transcatheter or a surgical bioprosthesis. Main Outcomes and Measures The prespecified secondary end points of death or disabling stroke and other adverse events and hemodynamic findings at 5 years. An independent clinical event committee adjudicated all serious adverse events and an independent echocardiographic core laboratory evaluated all echocardiograms at 5 years. Results A total of 1660 individuals underwent an attempted TAVR (n = 864) or surgical (n = 796) procedure. The mean (SD) age was 79.8 (6.2) years, 724 (43.6%) were female, and the mean (SD) Society of Thoracic Surgery Predicted Risk of Mortality score was 4.5% (1.6%). At 5 years, the rates of death or disabling stroke were similar (TAVR, 31.3% vs surgery, 30.8%; hazard ratio, 1.02 [95% CI, 0.85-1.22]; P = .85). Transprosthetic gradients remained lower (mean [SD], 8.6 [5.5] mm Hg vs 11.2 [6.0] mm Hg; P < .001) and aortic valve areas were higher (mean [SD], 2.2 [0.7] cm 2 vs 1.8 [0.6] cm 2 ; P < .001) with TAVR vs surgery. More patients had moderate/severe paravalvular leak with TAVR than surgery (11 [3.0%] vs 2 [0.7%]; risk difference, 2.37% [95% CI, 0.17%- 4.85%]; P = .05). New pacemaker implantation rates were higher for TAVR than surgery at 5 years (289 [39.1%] vs 94 [15.1%]; hazard ratio, 3.30 [95% CI, 2.61-4.17]; log-rank P < .001), as were valve reintervention rates (27 [3.5%] vs 11 [1.9%]; hazard ratio, 2.21 [95% CI, 1.10-4.45]; log-rank P = .02), although between 2 and 5 years only 6 patients who underwent TAVR and 7 who underwent surgery required a reintervention. Conclusions and Relevance Among intermediate-risk patients with symptomatic severe aortic stenosis, major clinical outcomes at 5 years were similar for TAVR and surgery. TAVR was associated with superior hemodynamic valve performance but also with more paravalvular leak and valve reinterventions.

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.

Abstract Aims Post-operative atrial fibrillation (POAF) is associated with stroke and mortality. It is unknown if POAF is associated with subsequent heart failure (HF) hospitalization. This study aims to examine the association between POAF and incident HF hospitalization among patients undergoing cardiac and non-cardiac surgeries. Methods and results A retrospective cohort study was conducted using all-payer administrative claims data that included all non-federal emergency department visits and acute care hospitalizations across 11 states in the USA. The study population included adults aged at least 18 years hospitalized for surgery without a prior diagnosis of HF. Cox proportional hazards regression models were used to examine the association between POAF and incident HF hospitalization after making adjustment for socio-demographics and comorbid conditions. Among 76 536 patients who underwent cardiac surgery, 14 365 (18.8%) developed incident POAF. In an adjusted Cox model, POAF was associated with incident HF hospitalization [hazard ratio (HR) 1.33; 95% confidence interval (CI) 1.25–1.41]. In a sensitivity analysis excluding HF within 1 year of surgery, POAF remained associated with incident HF hospitalization (HR 1.15; 95% CI 1.01–1.31). Among 2 929 854 patients who underwent non-cardiac surgery, 23 763 (0.8%) developed incident POAF. In an adjusted Cox model, POAF was again associated with incident HF hospitalization (HR 2.02; 95% CI 1.94–2.10), including in a sensitivity analysis excluding HF within 1 year of surgery (HR 1.49; 95% CI 1.38–1.61). Conclusions Post-operative atrial fibrillation is associated with incident HF hospitalization among patients without prior history of HF undergoing both cardiac and non-cardiac surgeries. These findings reinforce the adverse prognostic impact of POAF and suggest that POAF may be a marker for identifying patients with subclinical HF and those at elevated risk for HF.

Parkinson’s disease (PD) is generally considered a sporadic disorder, but a strong genetic background is often found. The aim of this study was to identify the underlying genetic cause of PD in two affected siblings and to subsequently assess the role of mutations in Cathepsin B (CTSB) in susceptibility to PD. A typical PD family was identified and whole-exome sequencing was performed in two affected siblings. Variants of interest were validated using Sanger sequencing. CTSB p.Gly284Val was genotyped in 2077 PD patients and 615 unrelated healthy controls from the Czech Republic, Ireland, Poland, Ukraine, and the USA. The gene burden analysis was conducted for the CTSB gene in an additional 769 PD probands from Mayo Clinic Florida familial PD cohort. CTSB expression and activity in patient-derived fibroblasts and controls were evaluated by qRT-PCR, western blot, immunocytochemistry, and enzymatic assay. The CTSB p.Gly284Val candidate variant was only identified in affected family members. Functional analysis of CTSB patient-derived fibroblasts under basal conditions did not reveal overt changes in endogenous expression, subcellular localization, or enzymatic activity in the heterozygous carrier of the CTSB variant. The identification of the CTSB p.Gly284Val may support the hypothesis that the CTSB locus harbors variants with differing penetrance that can determine the disease risk.

Background and Motivation: Parkinson’s disease (PD) is one of the most serious, non-curable, and expensive to treat. Recently, machine learning (ML) has shown to be able to predict cardiovascular/stroke risk in PD patients. The presence of COVID-19 causes the ML systems to become severely non-linear and poses challenges in cardiovascular/stroke risk stratification. Further, due to comorbidity, sample size constraints, and poor scientific and clinical validation techniques, there have been no well-explained ML paradigms. Deep neural networks are powerful learning machines that generalize non-linear conditions. This study presents a novel investigation of deep learning (DL) solutions for CVD/stroke risk prediction in PD patients affected by the COVID-19 framework. Method: The PRISMA search strategy was used for the selection of 292 studies closely associated with the effect of PD on CVD risk in the COVID-19 framework. We study the hypothesis that PD in the presence of COVID-19 can cause more harm to the heart and brain than in non-COVID-19 conditions. COVID-19 lung damage severity can be used as a covariate during DL training model designs. We, therefore, propose a DL model for the estimation of, (i) COVID-19 lesions in computed tomography (CT) scans and (ii) combining the covariates of PD, COVID-19 lesions, office and laboratory arterial atherosclerotic image-based biomarkers, and medicine usage for the PD patients for the design of DL point-based models for CVD/stroke risk stratification. Results: We validated the feasibility of CVD/stroke risk stratification in PD patients in the presence of a COVID-19 environment and this was also verified. DL architectures like long short-term memory (LSTM), and recurrent neural network (RNN) were studied for CVD/stroke risk stratification showing powerful designs. Lastly, we examined the artificial intelligence bias and provided recommendations for early detection of CVD/stroke in PD patients in the presence of COVID-19. Conclusion: The DL is a very powerful tool for predicting CVD/stroke risk in PD patients affected by COVID-19.

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.

3084 Background: Homologous recombination (HR) is an essential, high-fidelity mechanism to repair DNA double strand breaks (DSBs) in cancer cells. CYT-0851 inhibits HR leading to an accumulation of unrepaired DSBs and tumor cell death. We are reporting the completed Phase 1 dose-escalation results and RP2D selection to support ongoing development of CYT-0851. Methods: Patients (pts) with advanced hematologic and solid tumors were treated with continuous 28-day cycles of increasing doses of CYT-0851 following a 3+3 design. The primary objective was determining the maximum tolerated dose. Secondary objectives included safety, pharmacokinetics, and anti-tumor activity. Results: As of a 15 Nov 2021 data cutoff (DCO), 73 pts with advanced cancers (NHL n = 18; Sarcoma n = 16; Pancreas n = 11; Breast n = 8; HNSCC n = 6; Ovarian n = 4; SCLC n = 4; Other n = 4; Myeloma n = 2) were treated in 12 cohorts (total daily doses: 30 mg to 1200 mg). One pt experienced a dose-limiting toxicity (DLT) of reversible metabolic acidosis at 1200 mg. Two of 3 pts at 800 mg experienced reversible DLT-like events in Cycle 2 of Gr3 dry skin and Gr3 myalgia and polyarthritis, respectively. Three of 10 pts treated at 600 mg experienced DLT-like events in Cycle 1: 1 pt experienced an SAE of Gr3 anorexia with Gr3 stomatitis, vomiting, and dehydration and 2 pts had Gr3 fatigue. No DLTs occurred at 400 mg daily which was selected as the RP2D. 42 pts (57.5%) experienced a CYT-0851-related adverse event (AE), including 12 (16.4%) with a Gr3/4 AE. There were no treatment-related deaths. AE leading to CYT-0851 withdrawal were reported in 2 pts (2.7%) treated with 600 and 800 mg. The most common CYT-0851-related AEs were primarily Gr1/2 and included fatigue (20.5%), hyperuricemia (11%), nausea (11%), alopecia (9.6%), constipation (8.2%) and headache (8.2%). CYT-0851 exposure was approximately dose-proportional across the evaluated doses with an effective half-life of ̃3 days. Exposure at 400 mg daily was consistent with efficacy in preclinical models. 46 pts were evaluable for response at the DCO. 12 pts with NHL were evaluable by Lugano and included 1 CR in FL and 1 PR in DLBCL treated for 393+ and 244 days respectively. 34 pts with solid tumors were evaluable by RECIST v1.1 with 1 PR in a pt with myxofibrosarcoma treated for 313 days and 16 pts with stable disease. Fifteen pts were treated for 100+ days and 5 for 180+ days. Conclusions: CYT-0851 has demonstrated promising and broad clinical activity in a Ph 1 population of pts with advanced cancers. The safety profile is favorable as characterized by events that were infrequent, primarily Gr1/2, and reversible. Six expansion cohorts (DLBCL, Follicular Lymphoma, Myeloma, Pancreatic, Ovarian and Sarcoma) are enrolling to characterize activity at the RP2D. Ph 1 evaluation of CYT-0851 in combination with 3 chemotherapy backbones is also ongoing. Clinical trial information: NCT03997968.

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 models—namely, PSPNet, VGG-SegNet, ResNet-SegNet, VGG-UNet, and ResNet-UNet—were 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 tests—namely, the Mann–Whitney test, paired t-test, and Wilcoxon test—demonstrated 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.

Purpose: The role of erectile dysfunction (ED) has recently shown an association with the risk of stroke and coronary heart disease (CHD) via the atherosclerotic pathway. Cardiovascular disease (CVD)/stroke risk has been widely understood with the help of carotid artery disease (CTAD), a surrogate biomarker for CHD. The proposed study emphasizes artificial intelligence-based frameworks such as machine learning (ML) and deep learning (DL) that can accurately predict the severity of CVD/stroke risk using carotid wall arterial imaging in ED patients. Methods: Using the PRISMA model, 231 of the best studies were selected. The proposed study mainly consists of two components: (i) the pathophysiology of ED and its link with coronary artery disease (COAD) and CHD in the ED framework and (ii) the ultrasonic-image morphological changes in the carotid arterial walls by quantifying the wall parameters and the characterization of the wall tissue by adapting the ML/DL-based methods, both for the prediction of the severity of CVD risk. The proposed study analyzes the hypothesis that ML/DL can lead to an accurate and early diagnosis of the CVD/stroke risk in ED patients. Our finding suggests that the routine ED patient practice can be amended for ML/DL-based CVD/stroke risk assessment using carotid wall arterial imaging leading to fast, reliable, and accurate CVD/stroke risk stratification. Summary: We conclude that ML and DL methods are very powerful tools for the characterization of CVD/stroke in patients with varying ED conditions. We anticipate a rapid growth of these tools for early and better CVD/stroke risk management in ED patients.