Deep Learning Analyses to Delineate the Molecular Remodeling Process after Myocardial Infarction.
Ontology highlight
ABSTRACT:
SUBMITTER: Iborra-Egea O
PROVIDER: S-EPMC8699769 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Background: Acute myocardial infarction (AMI) is associated with a poor prognosis. Therefore, accurate diagnosis and early intervention of the culprit lesion are of extreme importance. Therefore, we developed a neural network algorithm in this study to automatically diagnose AMI from 12-lead electrocardiograms (ECGs). Methods: We used the open-source PTB-XL database as the training and validation sets, with a 7:3 sample size ratio. Twenty-One thousand, eight hundred thirty-seven clinical 12-lead ECGs from the PTB-XL dataset were available for training and validation (15,285 were used in the training set and 6,552 in the validation set). Additionally, we randomly selected 205 ECGs from a dataset built by Chapman University, CA, USA and Shaoxing People's Hospital, China, as the testing set. We used a residual network for training and validation. The model performance was experimentally verified in terms of area under the curve (AUC), precision, sensitivity, specificity, and F1 score. Results: The AUC of the training, validation, and testing sets were 0.964 [95% confidence interval (CI): 0.961-0.966], 0.944 (95% CI: 0.939-0.949), and 0.977 (95% CI: 0.961-0.991), respectively. The precision, sensitivity, specificity, and F1 score of the deep learning model for AMI diagnosis from ECGs were 0.827, 0.824, 0.950, and 0.825, respectively, in the training set, 0.789, 0.818, 0.913, and 0.803, respectively, in the validation set, and 0.830, 0.951, 0.951, and 0.886, respectively, in the testing set. The AUC for automatic AMI location diagnosis of LMI, IMI, ASMI, AMI, ALMI were 0.969 (95% CI: 0.959-0.979), 0.973 (95% CI: 0.962-0.978), 0.987 (95% CI: 0.963-0.989), 0.961 (95% CI: 0.956-0.989), and 0.996 (95% CI: 0.957-0.997), respectively. Conclusions: The residual network-based algorithm can effectively automatically diagnose AMI and MI location from 12-lead ECGs.
| S-EPMC8273385 | biostudies-literature
Project description:Myocardial remodeling (MR) following myocardial infarction (MI) contributes to heart failure. Inflammation is a key determinant in cardiac remodeling, with potential prognostic improvements by inhibiting inflammatory factors. Pattern recognition receptors, including interferon gamma-inducible protein-16 (IFI-16), play significant roles in this process, yet its specific involvement remains underexplored. This study investigates IFI-16's role in initiating inflammation via the inflammasome and its direct interaction with galectin-3 protein post-MI. Elevated IFI-16 levels were observed in human and rat myocytes and a mouse MI model under hypoxic, nutrient-deprived conditions, correlating with increased inflammation-associated proteins. Suppression of IFI-16/IFI-204 using short hairpin RNA (shRNA) lentivirus or adeno-associated virus decreased inflammatory factor activation, thereby mitigating remodeling and enhancing cardiac function post-MI. Co-immunoprecipitation (coIP) and double-fluorescence staining confirmed IFI-16's ability to interact directly with galectin-3. These findings underscore IFI-16's critical role as a pro-inflammatory factor in post-MI MR, suggesting its inhibition as a potential therapeutic strategy.
| S-EPMC11345598 | biostudies-literature
Project description:The serine/threonine kinase Pim-1 was recently identified as a cardiomyocyte survival regulator downstream of Akt. The present study aims to examine Pim-1 activity and its association with the post MI remodeling myocardium in a clinically relevant large animal model. Apical myocardial infarction of approximately 25% left ventricular mass was created in an ovine model. Regional post-infarction deformation of the left ventricle was monitored by sonomicrometry and quantified using areal remodeling strain (i.e., areal expansion). Myocardial tissues were harvested at 12weeks from the adjacent and remote regions of the infarct for analysis of Pim-1 mediated survival signaling proteins as well as apoptotic activity. The cDNA coding sequences of two ovine Pim-1 kinase isoforms, 44 and 33kDa, were identified. Both isoforms were detected in heart tissue and the overall Pim-1 expression was found to be tightly controlled at multiple molecular levels. Pim-1 as well as the Pim-1 mediated survival signaling proteins Bcl-2, Bcl-xL, and phospho-Bad (Ser112) were upregulated in the adjacent region at 12weeks post-infarction and their expression correlated positively with the degree of the remodeling, which was accompanied by significant upregulations of the PP2A/BAD mediated apoptotic signaling proteins. However these upregulations were imbalanced, such that p-BAD (Ser112)/BAD decreased in the adjacent region of the infarcted hearts. Apoptotic activity also increased with remodeling strain. Despite an observed intrinsic upregulation of survival proteins, the imbalanced activation of apoptotic pathways resulted in evident apoptosis in the adjacent region.Ultramini-abstractPim-1 mediated survival signaling in myocardial tissues from infarcted ovine hearts was studied. It was shown that the adjacent region of the infarct experienced higher remodeling strain and exhibited increased levels of Pim-1 and related anti-apoptotic proteins. Despite this elevation of survival activity, however, the imbalanced activation of PP2A/BAD mediated apoptotic pathway resulted in evident apoptosis in the adjacent region.
| S-EPMC3791143 | biostudies-literature
Project description:Myocardial infarction is a common cardiovascular disorder caused by prolonged ischemia, and early diagnosis of myocardial infarction (MI) is critical for lifesaving. ECG is a simple and non-invasive approach in MI detection, localization, diagnosis, and prognosis. Population-based screening with ECG can detect MI early and help prevent it but this method is too labor-intensive and time-consuming to carry out in practice unless artificial intelligence (AI) would be able to reduce the workload. Recent advances in using deep learning (DL) for ECG screening might rekindle this hope. This review aims to take stock of 59 major DL studies applied to the ECG for MI detection and localization published in recent 5 years, covering convolutional neural network (CNN), long short-term memory (LSTM), convolutional recurrent neural network (CRNN), gated recurrent unit (GRU), residual neural network (ResNet), and autoencoder (AE). In this period, CNN obtained the best popularity in both MI detection and localization, and the highest performance has been obtained from CNN and ResNet model. The reported maximum accuracies of the six different methods are all beyond 97%. Considering the usage of different datasets and ECG leads, the network that trained on 12 leads ECG data of PTB database has obtained higher accuracy than that on smaller number leads data of other datasets. In addition, some limitations and challenges of the DL techniques are also discussed in this review.
| S-EPMC8990170 | biostudies-literature
Project description:OBJECTIVE:Conventional risk stratification models for mortality of acute myocardial infarction (AMI) have potential limitations. This study aimed to develop and validate deep-learning-based risk stratification for the mortality of patients with AMI (DAMI). METHODS:The data of 22,875 AMI patients from the Korean working group of the myocardial infarction (KorMI) registry were exclusively divided into 12,152 derivation data of 36 hospitals and 10,723 validation data of 23 hospitals. The predictor variables were the initial demographic and laboratory data. The endpoints were in-hospital mortality and 12-months mortality. We compared the DAMI performance with the global registry of acute coronary event (GRACE) score, acute coronary treatment and intervention outcomes network (ACTION) score, and the thrombolysis in myocardial infarction (TIMI) score using the validation data. RESULTS:In-hospital mortality for the study subjects was 4.4% and 6-month mortality after survival upon discharge was 2.2%. The areas under the receiver operating characteristic curves (AUCs) of the DAMI were 0.905 [95% confidence interval 0.902-0.909] and 0.870 [0.865-0.876] for the ST elevation myocardial infarction (STEMI) and non ST elevation myocardial infarction (NSTEMI) patients, respectively; these results significantly outperformed those of the GRACE (0.851 [0.846-0.856], 0.810 [0.803-0.819]), ACTION (0.852 [0.847-0.857], 0.806 [0.799-0.814] and TIMI score (0.781 [0.775-0.787], 0.593[0.585-0.603]). DAMI predicted 30.9% of patients more accurately than the GRACE score. As secondary outcome, during the 6-month follow-up, the high risk group, defined by the DAMI, has a significantly higher mortality rate than the low risk group (17.1% vs. 0.5%, p < 0.001). CONCLUSIONS:The DAMI predicted in-hospital mortality and 12-month mortality of AMI patients more accurately than the existing risk scores and other machine-learning methods.
| S-EPMC6822714 | biostudies-literature
Project description:Lymphatic endothelium serves as a barrier to control fluid balance and immune cell trafficking to maintain tissue homeostasis. Long-term alteration of lymphatic vasculature promotes edema and fibrosis, which is an aggravating factor in the onset of cardiovascular diseases such as myocardial infarction. Apelin is a bioactive peptide that plays a central role in angiogenesis and cardiac contractility. Despite an established role of apelin in lymphangiogenesis, little is known about its function in the cardiac lymphatic endothelium. Here, we show that apelin and its receptor APJ were exclusively expressed on newly formed lymphatic vasculature in a pathological model of myocardial infarction. Using an apelin-knockout mouse model, we identified morphological and functional defects in lymphatic vasculature associated with a proinflammatory status. Surprisingly, apelin deficiency increased the expression of lymphangiogenic growth factors VEGF-C and VEGF-D and exacerbated lymphangiogenesis after myocardial infarction. Conversely, the overexpression of apelin in ischemic heart was sufficient to restore a functional lymphatic vasculature and to reduce matrix remodeling and inflammation. In vitro, the expression of apelin prevented the alteration of cellular junctions in lymphatic endothelial cells induced by hypoxia. In addition, we demonstrated that apelin controls the secretion of the lipid mediator sphingosine-1-phosphate in lymphatic endothelial cells by regulating the level of expression of sphingosine kinase 2 and the transporter SPNS2. Taken together, our results show that apelin plays a key role in lymphatic vessel maturation and stability in pathological settings. Thus, apelin may represent a novel candidate to prevent pathological lymphatic remodeling in diseases.
| S-EPMC5470877 | biostudies-other
Project description:Adverse left ventricular (LV) remodeling after acute ST-elevation myocardial infarction (STEMI) is associated with morbidity and mortality. We studied clinical, biochemical and angiographic determinants of LV end diastolic volume index (LVEDVi), end systolic volume index (LVESVi) and mass index (LVMi) as global LV remodeling parameters 4 months after STEMI, as well as end diastolic wall thickness (EDWT) and end systolic wall thickness (ESWT) of the non-infarcted myocardium, as compensatory remote LV remodeling parameters. Data was collected in 271 patients participating in the GIPS-III trial, presenting with a first STEMI. Laboratory measures were collected at baseline, 2 weeks, and 6-8 weeks. Cardiovascular magnetic resonance imaging (CMR) was performed 4 months after STEMI. Linear regression analyses were performed to determine predictors. At baseline, patients were 21% female, median age was 58 years. At 4 months, mean LV ejection fraction (LVEF) was 54 ± 9%, mean infarct size was 9.0 ± 7.9% of LVM. Strongest univariate predictors (all p < 0.001) were peak Troponin T for LVEDVi (R2 = 0.26), peak CK-MB for LVESVi (R2 = 0.41), NT-proBNP at 2 weeks for LVMi (R2 = 0.24), body surface area for EDWT (R2 = 0.32), and weight for ESWT (R2 = 0.29). After multivariable analysis, cardiac biomarkers remained the strongest predictors of LVMi, LVEDVi and LVESVi. NT-proBNP but none of the acute cardiac injury biomarkers were associated with remote LV wall thickness. Our analyses illustrate the value of cardiac specific biochemical biomarkers in predicting global LV remodeling after STEMI. We found no evidence for a hypertrophic response of the non-infarcted myocardium.
| S-EPMC5539273 | biostudies-other
Project description:Myocardial infarction (MI) is an important clinical problem because of its large contribution to mortality. The main causal and treatable risk factors for MI include hypertension, hypercholesterolemia or dyslipidemia, diabetes mellitus, and smoking. In addition to these risk factors, recent studies have shown the importance of genetic factors and interactions between multiple genes and environmental factors. Disease prevention is an important strategy for reducing the overall burden of MI, with the identification of markers for disease risk being key both for risk prediction and for potential intervention to lower the chance of future events. Although genetic linkage analyses of families and sib-pairs as well as candidate gene and genome-wide association studies have implicated several loci and candidate genes in predisposition to coronary heart disease (CHD) or MI, the genes that contribute to genetic susceptibility to these conditions remain to be identified definitively. In this review, we summarize both candidate loci for CHD or MI identified by linkage analyses and candidate genes examined by association studies. We also review in more detail studies that have revealed the association with MI or CHD of polymorphisms in MTHFR, LPL, and APOE by the candidate gene approach and those in LTA and at chromosomal region 9p21.3 by genome-wide scans. Such studies may provide insight into the function of implicated genes as well as into the role of genetic factors in the development of CHD and MI.
| S-EPMC2518661 | biostudies-literature
Project description:Despite the prevalence of pericytes in the microvasculature of the heart, their role during ischemia-induced remodeling remains unclear. We used multiple lineage-tracing mouse models and found that pericytes migrated to the injury site and expressed profibrotic genes, coinciding with increased vessel leakage after myocardial infarction (MI). Single-cell RNA-Seq of cardiac pericytes at various time points after MI revealed the temporally regulated induction of genes related to vascular permeability, extracellular matrix production, basement membrane degradation, and TGF-β signaling. Deleting TGF-β receptor 1 in chondroitin sulfate proteoglycan 4-expressing (Cspg4-expressing) cells reduced fibrosis following MI, leading to a transient improvement in the cardiac ejection fraction. Furthermore, genetic ablation of Cspg4-expressing cells resulted in excessive vascular permeability, a decline in cardiac function, and increased mortality in the second week after MI. These data reveal an essential role for cardiac pericytes in the control of vascular homeostasis and the fibrotic response after acute ischemic injury, information that will help guide the development of novel strategies to preserve vascular integrity and attenuate pathological cardiac remodeling.
| S-EPMC10178847 | biostudies-literature
Project description:BackgroundLeft ventricular size and shape are important for quantifying cardiac remodeling in response to cardiovascular disease. Geometric remodeling indices have been shown to have prognostic value in predicting adverse events in the clinical literature, but these often describe interrelated shape changes. We developed a novel method for deriving orthogonal remodeling components directly from any (moderately independent) set of clinical remodeling indices.ResultsSix clinical remodeling indices (end-diastolic volume index, sphericity, relative wall thickness, ejection fraction, apical conicity, and longitudinal shortening) were evaluated using cardiac magnetic resonance images of 300 patients with myocardial infarction, and 1991 asymptomatic subjects, obtained from the Cardiac Atlas Project. Partial least squares (PLS) regression of left ventricular shape models resulted in remodeling components that were optimally associated with each remodeling index. A Gram-Schmidt orthogonalization process, by which remodeling components were successively removed from the shape space in the order of shape variance explained, resulted in a set of orthonormal remodeling components. Remodeling scores could then be calculated that quantify the amount of each remodeling component present in each case. A one-factor PLS regression led to more decoupling between scores from the different remodeling components across the entire cohort, and zero correlation between clinical indices and subsequent scores.ConclusionsThe PLS orthogonal remodeling components had similar power to describe differences between myocardial infarction patients and asymptomatic subjects as principal component analysis, but were better associated with well-understood clinical indices of cardiac remodeling. The data and analyses are available from www.cardiacatlas.org.
| S-EPMC5791439 | biostudies-literature