Lerman, Amir

Background: We previously developed deep-learning algorithms that identify coronary artery disease (CAD) risk based on (i) coronary artery calcium (CAC), (ii) obstructive CAD by angiography, and (iii) left ventricular akinesis in ≥1 segment by echocardiogram, using a 12-lead electrocardiogram (CAD ECG-AI). We tested the hypothesis that those with increased probability of CAD by CAD ECG-AI algorithms will have an increased risk of atherosclerotic cardiovascular disease (ASCVD) events and would refine the AHA Predicting Risk of Cardiovascular Disease Events (PREVENT TM ) equations’ predictive capabilities. Methods: We assessed a group of consecutive patients who sought primary care in Olmsted County, MN, between 1997 and 2003. Passive follow-up was conducted using the Rochester Epidemiology Project's record linkage system. Patients included met the same criteria of the original PREVENT TM equations. The probability output of each CAD ECG-AI algorithm was used to predict ASCVD (fatal and non-fatal myocardial infarction and ischemic stroke) and ASCVD-Plus [further including percutaneous coronary intervention (PCI), coronary artery bypass grafting (CABG), and all-cause mortality]. Events were validated in duplicate. Cox proportional hazard models adjusted for age, sex, and risk factors while modeling each CAD ECG-AI algorithm as an individual and additive predictor (see footnote). PREVENT TM risk categories stratified analysis to evaluate the effect of the CAD ECG-AI models on predicted ASCVD risk. Results: We included 21,193 patients, with mean ± SD age 51.6 ± 12.0, 54% women and 95% white. After 14.2±12.4 years follow-up, 1,351 (6.4%) developed ASCVD, and 2,808 (13.2%) had ASCVD-Plus. The risk of ASCVD and ASCVD-Plus increased with positivity for the CAD ECG-AI algorithms after adjustments for age, sex, and PREVENT TM equations factors, all p for trend <0.001 (data not shown). In additive analyses, the risk of ASCVD and ASCVD-Plus increased with increased CAD ECG-AI factors, all p for trend <0.001 ( Fig. A-B ). Furthermore, the CAD ECG-AI algorithm enhanced the predictive capabilities of PREVENT TM equations across most risk subgroups ( Fig. C-E ). Conclusions: The deep-learning CAD ECG-AI algorithms displayed an independent and additive association with long-term ASCVD and ASCVD-Plus events in the community and improved the PREVENT TM predicted ASCVD risk. The CAD ECG-AI algorithms could help identify individuals at risk in primary prevention of cardiovascular events.

Background: Recent studies have reported associations between alterations in gut microbiome composition (GMC) and cardiovascular disease risk factors (CVR). However, data regarding the use of GMC as a biomarker of CVR is scarce. Aims: The current study was designed to assess the distinct patterns in GMC among patients with varying degrees of CVR and/or atherosclerotic cardiovascular disease (ASCVD). Methods: Patients with a range of CVR including hypertension (HTN), hyperlipidemia (HLD), diabetes (DM), and/or ASCVD referring to Mayo Clinic from 2013 to 2018 were prospectively enrolled. DNA extracted from stool samples was analyzed using the V3-V5 region of the 16s data. Microbial α-diversity was assessed by the observed taxonomic units, Shannon, and Chao1 indices. β-diversity was assessed using Bray-Curtis dissimilarity and plotted using principal coordinates analysis. Hierarchical clustering was used to identify patterns in the GMC samples. Random Forest analysis was used to identify the most important clinical factors differentiating the clusters. Results: A total of 211 patients with a median age of 60 [IQR: 50,70] years and with 90 (42.7%) males were included. Two clusters of GMC were identified (Figure 1A) . Cluster 1 and 2 had 104 (49.3%) and 107 (50.7%) patients, respectively. Among CVRs, age and body mass index were the most prominent factors contributing to the difference in GMC among clusters ( Figure 1B ). Cluster 2 had a better α diversity profile than Cluster 1 (Figure 1C-E) . There was no significant difference in TMAO between clusters (P=0.6). Cluster 2 patients were younger (P<0.001), leaner (P=0.007), more physically active (P<0.001), less male (P=0.009), and had a lower prevalence of ASCVD (P=0.003), HTN (P=0.010), and HLD (P=0.005). There was no significant difference in the prevalence of DM (P=0.063), smoking (P=0.446), and alcohol intake (P=0.134) between the clusters. Conclusion: This study suggests the potential of GMC profiling as a valuable biomarker for assessing CVRs, with age and BMI as the most prominent factors associated with GMC clustering.

Introduction: Identifying patients at risk for ischemic events after percutaneous coronary intervention (PCI) relies on traditional analysis of limited clinical and imaging variables. Machine learning (ML) has shown promise in effectively predicting cardiovascular risk in population studies. While existing ML models mainly predict mortality and incorporate clinical variables, there is a lack of tools that have utilized genetic data and that predict ischemic events. Aims: This study aims to develop and validate a ML model incorporating genotyping and clinical data to enhance prediction of ischemic outcomes for PCI patients utilizing large prospectively derived diverse datasets. Methods: Patients from the TAILOR-PCI trial (n=5302) were utilized for model development. 50% of the sample was utilized for Boruta feature selection and 50% for training and testing using cross validation. Features included demographics, medical history, medications, PCI characteristics, and genetic data (specifically, CYP2C19 *2, *3, *17 alleles). The primary endpoint was a composite of cardiovascular death, myocardial infarction, stroke, stent thrombosis, and severe recurrent ischemia at 12 months. Multiple ML classification algorithms, including Support Vector Machine (SVM) polynomial, Random Forest, Light gradient boost, XG Boost, among others, were benchmarked for their prediction performance on rare events. The top performing classifiers were externally validated on an independent dataset from the PRECISION PCI study (n=3,745). Results: Mean participant age of the training set was 64.2 ± 11.0 years, with 75.4% being male. During follow-up of 12 months, among 4,572 patients in the entire cohort 343 (7.5%) met the primary outcome. The SVM polynomial model demonstrated the highest area under the curve (AUC) of 0.67 for predicting the primary outcome with test dataset. The sensitivity, specificity, precision, and recall were 0.87, 0.28, 0.07, and 0.87 respectively (Figure). Peripheral arterial disease, body mass index, and age were among the top variables by feature importance. Conclusion: ML models incorporating both clinical and genetic data are feasible and highly promising in predicting major adverse cardiac events that may help guide use of anti-platelet drug therapy. The AUC values are reasonable given imbalances and misclassifications in datasets, and further model optimization with prospective utilization of the model will be paramount.

Background: Cardiac allograft vasculopathy (CAV) is one of the leading causes of graft failure and death after heart transplantation (HTx). Conventionally, CAV is characterized by concentric intimal thickening, however the long-term progression patterns of plaque morphology are not yet well understood. Research Question: This study aimed to assess the plaque morphology, including histology and eccentricity, in a temporal manner post-HTx using virtual histology intravascular ultrasonography (VH-IVUS). Methods: We included 50 patients who underwent serial VH-IVUS assessment at three assessment points (A1:0-1 year, A2:3-5 years, A3:7-10 years) after HTx. Differences in VH-IVUS findings between timepoints A1 to A2 (early period) and A2 to A3 (late period) were investigated. Plaque volume index was defined as (plaque volume/vessel volume) × 100%. Eccentricity index (EI) was defined as (maximum intimal thickness – minimum intimal thickness)/maximum intimal thickness and was evaluated in 39 patients with significant plaque (maximal intimal thickness >0.50 mm at the A3) at each timepoint. The serial changes of EI and relationship between EI and other VH-IVUS findings were investigated. Results: Of 50 patients, mean age was 51±13 years, 36 (72%) were males. In both early and late periods, the plaque volume (PV) index showed a significant increase, however, the rate of progression was significantly slower in late period. (5.8% [0.9, 13.2] vs 2.4% [-0.2, 7.4], p=0.015). The EI showed a trend of decrease in the early period, compared to increases in the late period (-0.040 [-0.103, 0.004] vs 0.003 [-0.030, 0.052], p=0.036). Patients with EI change in late period higher than median value had significantly lower proportion of fibrous plaque (70.8% [67.2, 75.1] vs 62.7 [55.5, 66.9], p=0.002) and higher dense calcium (1.1% [0.9, 1.9], 4.5% [1.8, 6.9], p=0.022) at A3. Conclusion: In heart transplant patients, coronary artery plaque progression in the late period showed more eccentric progression with lower fibrous plaque composition, a pattern commonly observed in typical and conventional coronary atherosclerosis. These findings may provide a novel mechanism and therapeutic insight into the temporal patterns in CAV progression during long term follow up.

Background: Coronary microvascular disease (CMD) may be endothelium-independent (coronary flow reserve, CFR<2.5) or endothelium-dependent (<50% increase in coronary blood flow in response to acetylcholine). Endothelium-independent CMD has been subclassified into structural and functional groups based on hyperemic microvascular resistance (hMR, mmHg/cm/s). We hypothesized that endothelium-dependent CMD also has these subtypes. Methods: Patients with non-obstructive coronary artery disease who underwent coronary catheterization of the left anterior descending artery were included (n=112). Pressure and flow were recorded at rest, with adenosine, and with acetylcholine. Patients were classified by endothelial type and functional CMD (hMR<2.5) or structural CMD (hMR>2.5). Wave intensity analysis was performed and cumulative separated wave intensity (Joules/m 2 ) was calculated by standard formulae. Three dominant waves were analyzed (forward compression wave, FCW; backward compression wave, BCW; backward expansion wave, BEW). Results: Seventy-four of 109 patients had CMD, of which 59 had endothelium-independent and 38 had endothelium-dependent CMD (23 had both). Functional and structural subgroups were identified (Figure 1). All CMD subtypes had significantly different wave intensities at rest, adenosine, and acetylcholine (p<0.05). Comparing subtypes, there was no difference in wave intensities at rest. However, wave intensities significantly differed between all CMD subtypes with adenosine and acetylcholine, with higher energy waves in the endothelium-independent and functional groups (p<0.05, Figure 2). Conclusions: CMD is a heterogenous condition with distinct subtypes. Functional and structural groups exist in both endothelium-dependent and endothelium-independent CMD. These subgroups have distinct hemodynamic profiles as measured by wave intensity. A patient-specific approach to first line medical therapy may be improved by subgroup classification.

Introduction: Atrial fibrillation (AF) is prevalent in patients with atherosclerotic coronary and carotid artery disease and is associated with elevated plasma inflammatory markers, such as Interleukin (IL)-6. In carotid artery atherosclerosis, macrophages are considered a local marker of inflammation. Hypothesis: We hypothesize that AF is independently associated with carotid plaque inflammation. Aims: In patients undergoing carotid endarterectomy (CEA), we aimed to determine whether carotid plaques inflammation is associated with AF. Approach: In this prospective cohort study, consecutive patients with carotid artery disease undergoing CEA were enrolled. From the plaques removed during surgery, fixed in formalin and embedded in paraffin blocks, sections were stained with antibodies against CD68 to detect macrophages (Fig.1A) . Digital copies of the slides were created by Motic Easy Scan and histologically annotated with QuPath. The percentage of CD68+ cells was defined as (CD68+ positive cells/total nuclei) x 100. Flash-frozen plaque segments were analyzed by ELISA for IL-6 concentration. Baseline demographics and clinical data, including AF diagnosis, were extracted from the electronic health records. Results: A total of 106 patients undergoing CEA, with a median age of 73 [67-78] years and comprising 83 (78.3%) males, were included in the study. AF was diagnosed prior to CEA in 13 (12.3%) patients. Univariate logistic regression showed that plaque CD68+ cell content was associated with AF (OR 1.048 [95% CI 1.010 – 1.088]; p = 0.013). Additionally, in Mann-Whitney test IL-6 levels were significantly over twofold higher in plaques of patients with AF compared to those without AF (82.4 [64.9-111.7] pg/mg vs 37.0 [18.4-93.3] pg/mg; p=0.020) (Fig. 1B) . Conclusions: The current study demonstrates an association between carotid atherosclerotic plaque macrophage content, IL6 levels and AF, supporting the role of inflammation in the pathogenesis of AF in these patients. Further studies are needed to determine the potential of plaque inflammation as a therapeutic target in AF.

Background A subset of individuals with major depressive disorder (MDD) have a high burden of cardiovascular risk factors and cerebral small‐vessel disease, implicating vascular disease in the development of depression. Cross‐sectional studies demonstrate a link between endothelial dysfunction and MDD, but the prospective association between peripheral endothelial dysfunction (PED) and an incident diagnosis of MDD is unknown. Methods and Results Patients undergoing a baseline assessment of cardiovascular risk were evaluated for PED using reactive hyperemia–peripheral arterial tonometry (≤1.8 consistent with PED). Patient medical records were reviewed to identify those who underwent a formal clinical evaluation of MDD after the index PED evaluation. The frequency of PED was compared in those with and without MDD. Logistic regression analyses were performed to assess the association between baseline PED and incident MDD. Between January 2006 and December 2020, 1614 patients underwent testing for PED. Four hundred eighty‐four (30.1%) patients underwent a formal evaluation for MDD after (0–15 years) the index procedure (mean±SD age, 52.8±13.8 years; 65.2% women). Of these, 157 (32.4%) had PED and 108 (31.0%) were diagnosed with MDD. Individuals with MDD had a higher frequency of PED (40.2% versus 30.2%; P =0.034) compared with those without MDD. In multivariable analyses, PED was significantly associated with MDD (odds ratio, 2.3 [95% CI, 1.4–3.8]; P <0.001). Conclusions PED is significantly associated with incident MDD. Thus, PED may be a useful marker to identify individuals at increased risk of depression who may benefit from more frequent and earlier management strategies.

Positive remodeling (PR) is an atherosclerotic plaque feature defined as an increase in arterial caliber at the level of an atheroma, in response to increasing plaque burden. The mechanisms that lead to its formation are incompletely understood, but its role in coronary atherosclerosis has major clinical implications. Indeed, plaques with PR have elevated risk of provoking acute cardiac events. Hence, PR figures among the high-risk plaque features that cardiac imaging studies should report. This review aims to provide an overview of the current literature on coronary PR. It outlines the pathophysiology of PR, the different techniques used to assess its presence, and the imaging findings associated to PR, on both noninvasive and invasive studies. This review also summarizes clinical observations, trials, and studies, focused on the impact of PR on clinical outcome.

Abstract Background Cardiovascular disease remains the leading cause of death and burden globally, warranting the need to explore novel predictors of major adverse cardiovascular events (MACE) using new technologies. Artificial Intelligence (AI)-enhanced ECG (AI-ECG) algorithms can provide information on cardiovascular health of individuals, independent of conventional risk factors. Purpose The current study aimed to understand whether a previously described AI-ECG sex estimation algorithm could be applied for risk stratification of major adverse cardiovascular events (MACE), with a focus on a population without previous history of MACE. Methods Patients having 12-lead ECGs between 2018-2019 were included and followed up until August 2023. Exclusion criterion was a prior history of MACE. AI-ECG sex estimation was determined using a previously described algorithm predicting sex based on 12-lead ECGs. The algorithm generates outputs ranging from 0 to 1, representing the estimated probability of being male. Outputs above 0.5 were considered as AI-ECG-estimated male, and below as AI-ECG-estimated female. This was compared with biological sex to determine whether the two matched. Inconsistency between AI-ECG estimated sex and biological sex was defined as discordance. MACE was defined as myocardial infarction, coronary revascularization, non-fatal stroke, and all-cause death. Results Among 80,578 subjects (mean age 59.1 ± 16.1 years, 52.4% female), 9.7% exhibited sex discordance in AI-ECG estimation. Discordance was associated with a 56% higher risk of MACE (HR, 1.56, 95% CI 1.46-1.65, p &lt;0.001), and remained significant in multivariable analysis with traditional risk factors (HR 1.35, 95% CI 1.27-1.43, p &lt;0.001) (Figure 1). Sex-specific analysis showed increased MACE risk in both discordant males and females (Figure 2). Conclusion In patients with no history of MACE, discordance in AI-ECG sex estimation is associated with increased risk of MACE. These findings suggest the potential of AI-ECG sex estimation algorithm for risk assessment, especially in patients with no history of MACE.Figure 1.Cox proportional hazard modelFigure 2.Kaplan-Meier of MACE by sex

Abstract Background Patients with carotid artery disease undergoing carotid endarterectomy (CEA) appear to be at high risk of all-cause mortality during their follow-up. However, the possible predictors of this adverse outcome are not elucidated yet. Purpose We aimed to test cardiovascular (CV) risk factors as possible predictors of all-cause mortality in patients undergoing CEA and to determine whether there is a difference between the mortality rate of our study cohort and the general population. We hypothesize that CEA-treated patients have a higher mortality rate during follow-up after surgery than the general population, which is not related to the presence of CV risk factors. Methods We prospectively enrolled and followed up patients undergoing CEA. Univariate and multivariable Cox regression were performed to test whether common CV risk factors (demographics, laboratory values, comorbidities, and events before CEA) were predictive of all-cause mortality. We then compared the standardized mortality ratio (SMR) of our population and the age-sex-matched Minnesota (MN) general population at 5,10, and 21 years of follow-up after CEA. Results A total of 710 patients were followed for a median of 7.1 [2.9-11.9] years after CEA. Mortality occurred in 198 (27.0%) patients during the follow-up. The median time to event was 11.0 [10.0-12.0] years. Age was the only predictor of all-cause mortality in CEA-treated patients in multivariable models adjusted for known CV risk factors (Model 1: HR 1.03 [95%CI 1.01-1.06]; p=0.004; Model 2: HR 1.02 [95%CI 1.00-1.04]; p=0.023) (Table 1). However, the CEA-treated group had a higher mortality rate than would have been expected in the MN population (log-rank p&lt;0.001) (Fig.1A). Compared to the MN population, at 5 years of follow-up only patients &lt;60 years old had a higher SMR (4.53 [1.95-8.92]; p=0.001), whereas, at 10 years and 21 years of follow-up, our study population had a higher mortality rate at any age (Fig.1B). Conclusions The elevated mortality risk post-CEA in our cohort cannot be solely attributed to chronological aging. The underlying process of atherosclerosis likely contributes to all-cause mortality, and plaque characteristics may offer additional insight into the risk stratification of this patient group.All cause mortality predictors after CEAStudy population vs. MN population SMR