Circulating microRNAs in suspected stable coronary artery disease: A coronary computed tomography angiography study

Machine learning for catalysing the integration of noncoding RNA in research and clinical practice

The human transcriptome predominantly consists of noncoding RNAs (ncRNAs), transcripts that do not encode proteins. The noncoding transcriptome governs a multitude of pathophysiological processes, offering a rich source of next-generation biomarkers. Toward achieving a holistic view of disease, the integration of these transcripts with clinical records and additional data from omic technologies ("multiomic" strategies) has motivated the adoption of artificial intelligence (AI) approaches. Given their intricate biological complexity, machine learning (ML) techniques are becoming a key component of ncRNA-based research. This article presents an overview of the potential and challenges associated with employing AI/ML-driven approaches to identify clinically relevant ncRNA biomarkers and to decipher ncRNA-associated pathogenetic mechanisms. Methodological and conceptual constraints are discussed, along with an exploration of ethical considerations inherent to AI applications for healthcare and research. The ultimate goal is to provide a comprehensive examination of the multifaceted landscape of this innovative field and its clinical implications.

Construction and Validation of a Predictive Model for Coronary Artery Disease Using Extreme Gradient Boosting

Purpose

Early recognition of coronary artery disease (CAD) could delay its progress and significantly reduce mortality. Sensitive, specific, cost-efficient and non-invasive indicators for assessing individual CAD risk in community population screening are urgently needed.

Patients and Methods

3112 patients with CAD and 3182 controls were recruited from three clinical centers in China, and differences in baseline and clinical characteristics were compared. For the discovery cohort, the least absolute shrinkage and selection operator (LASSO) regression was used to identify significant features and four machine learning algorithms (logistic regression, support vector machine (SVM), random forest (RF) and extreme gradient boosting (XGBoost)) were applied to construct models for CAD risk assessment, the receiver operating characteristics (ROC) curve and precision-recall (PR) curve were conducted to evaluate their predictive accuracy. The optimal model was interpreted by Shapley additive explanations (SHAP) analysis and assessed by the ROC curve, calibration curve, and decision curve analysis (DCA) and validated by two external cohorts.

Results

Using LASSO filtration, all included variables were considered to be statistically significant. Four machine learning models were constructed based on these features and the results of ROC and PR curve implied that the XGBoost model exhibited the highest predictive performance, which yielded a high area of ROC curve (AUC) of 0.988 (95% CI: 0.986-0.991) to distinguish CAD patients from controls with a sensitivity of 94.6% and a specificity of 94.6%. The calibration curve showed that the predicted results were in good agreement with actual observations, and DCA exhibited a better net benefit across a wide range of threshold probabilities. External validation of the model also exhibited favorable discriminatory performance, with an AUC, sensitivity, and specificity of 0.953 (95% CI: 0.945-0.960), 89.9%, and 87.1% in the validation cohort, and 0.935 (95% CI: 0.915-0.955), 82.0%, and 90.3% in the replication cohort.

Conclusion

Our model is highly informative for clinical practice and will be conducive to primary prevention and tailoring the precise management for CAD patients.

Longitudinal dynamics of circulating miRNAs in a swine model of familial hypercholesterolemia during early atherosclerosis

Atherosclerosis is a complex progressive disease involving intertwined biological mechanisms. We aimed to identify miRNA expression dynamics at the early stages of atherosclerosis using a large swine model (Wisconsin Miniature Swine, WMS). A total of 18 female pigs; 9 familial hypercholesterolemic (WMS-FH) and 9 normal control swine (WMS-N) were studied. miRNA sequencing was performed on plasma cell-free RNA at 3, 6, and 9 months of age. RT-qPCR validated DE miRNAs in a new cohort of animals (n = 30) with both sexes. Gene ontology and mRNA targets for DE miRNAs were identified. In vivo multimodality imaging and histopathology were performed to document the presence of atherosclerosis at termination. 20, 19, and 9 miRNAs were significantly DE between the groups at months 3, 6, and 9, respectively. Most DE miRNAs and their target genes are involved in human atherosclerosis development. Coronary atherosclerosis was documented in 7/9 WMS-FH pigs. Control animals had no lesions. miR-138, miR-152, miR-190a, and miR-196a showed a significant diagnostic power at month 3, whereas miR-486, miR-126-3p, miR-335, and miR-423-5p were of significant diagnostic power at month 9. In conclusion, specific DE miRNAs with significant discriminatory power may be promising biomarkers for the early detection of coronary atherosclerosis.

Circulating miR-133a-3p defines a low-risk subphenotype in patients with heart failure and central sleep apnea: a decision tree machine learning approach

BACKGROUND

Patients with heart failure with reduced ejection fraction (HFrEF) and central sleep apnea (CSA) are at a very high risk of fatal outcomes.

OBJECTIVE

To test whether the circulating miRNome provides additional information for risk stratification on top of clinical predictors in patients with HFrEF and CSA.

METHODS

The study included patients with HFrEF and CSA from the SERVE-HF trial. A three-step protocol was applied: microRNA (miRNA) screening (n = 20), technical validation (n = 60), and biological validation (n = 587). The primary outcome was either death from any cause, lifesaving cardiovascular intervention, or unplanned hospitalization for worsening of heart failure, whatever occurred first. MiRNA quantification was performed in plasma samples using miRNA sequencing and RT-qPCR.

RESULTS

Circulating miR-133a-3p levels were inversely associated with the primary study outcome. Nonetheless, miR-133a-3p did not improve a previously established clinical prognostic model in terms of discrimination or reclassification. A customized regression tree model constructed using the Classification and Regression Tree (CART) algorithm identified eight patient subphenotypes with specific risk patterns based on clinical and molecular characteristics. MiR-133a-3p entered the regression tree defining the group at the lowest risk; patients with log(NT-proBNP) ≤ 6 pg/mL (miR-133a-3p levels above 1.5 arbitrary units). The overall predictive capacity of suffering the event was highly stable over the follow-up (from 0.735 to 0.767).

CONCLUSIONS

The combination of clinical information, circulating miRNAs, and decision tree learning allows the identification of specific risk subphenotypes in patients with HFrEF and CSA.

Study protocol for the epigenetic characterization of angor pectoris according to the affected coronary compartment: Global and comprehensive assessment of the relationship between invasive coronary physiology and microRNAs

BACKGROUND

MicroRNAs (miRNAs) are noncoding RNAs involved in post-transcriptional genetic regulation with a proposed role in intercellular communication. miRNAs are considered promising biomarkers in ischemic heart disease. Invasive physiological evaluation allows a precise assessment of each affected coronary compartment. Although some studies have associated the expression of circulating miRNAs with invasive physiological indexes, their global relationship with coronary compartments has not been assessed. Here, we will evaluate circulating miRNAs profiles according to the coronary pattern of the vascular compartment affectation.

STUDY AND DESIGN

This is an investigator-initiated, multicentre, descriptive study to be conducted at three centres in Spain (NCT05374694). The study will include one hundred consecutive patients older than 18 years with chest pain of presumed coronary cause undergoing invasive physiological evaluation, including fractional flow reserve (FFR) and index of microvascular resistance (IMR). Patients will be initially classified into four groups, according to FFR and IMR: macrovascular and microvascular affectation (FFR≤0.80 / IMR≥25), isolated macrovascular affectation (FFR≤0.80 / IMR<25), isolated microvascular affectation (FFR>0.80 / IMR ≥25) and normal coronary indexes (FFR>0.80 / IMR<25). Patients with isolated microvascular affectation or normal indexes will also undergo the acetylcholine test and may be reclassified as a fifth group in the presence of spasm. A panel of miRNAs previously associated with molecular mechanisms linked to chronic coronary syndrome will be analysed using RT-qPCR.

CONCLUSIONS

The results of this study will identify miRNA profiles associated with patterns of coronary affectation and will contribute to a better understanding of the mechanistic pathways of coronary pathology.

Circulating miR-143 and miR-145 as promising biomarkers for evaluating severity of coronary artery stenosis in patients with acute coronary syndrome

BACKGROUND

Multiple studies have provided evidence that miR-143 and miR-145 play a crucial role in the pathogenesis and progression of atherosclerosis. In the present study, we aim to investigate the expression of plasma miR-143 and miR-145 in patients with acute coronary syndrome (ACS) and their association with the severity of coronary artery stenosis.

METHODS

The study enrolled 279 patients with ACS, including 201 patients with unstable angina (UA) and 78 patients with acute myocardial infarction (AMI), and 65 matched subjects as the control group. The plasma levels of miR-143 and miR-145 were detected by quantitative real-time PCR (qRT-PCR). Gensini score was applied to evaluate the severity of coronary artery stenosis.

RESULTS

Plasma levels of miR-143 and miR-145 in patients with ACS were both decreased compared with the control group (p < 0.001). Plasma levels of miR-143 and miR-145 were negatively correlated with Gensini score (miR-143: r = -0.246, p < 0.001; miR-145: r = -0.222, p < 0.001). Logistic regression analysis showed that miR-143 and miR-145 were protective factors for the onset of ACS, UA, or AMI separately. MiR-143 (AUC: 0.786, p < 0.001) and miR-145 (AUC: 0.793, p < 0.001) were able to predict the degree of coronary artery stenosis greater than 50 %.

CONCLUSION

The plasma levels of miR-143 and miR-145 were significantly decreased in ACS patients and were negatively correlated with coronary stenosis. In conclusion, plasma miR-143 and miR-145 levels can be used as noninvasive biomarkers for evaluating coronary artery stenosis.

The Profile of Circulating Blood microRNAs in Outpatients with Vulnerable and Stable Atherosclerotic Plaques: Associations with Cardiovascular Risks

Non-coding RNAs reflect many biological processes in the human body, including athero-sclerosis. In a cardiology outpatient department cohort (N = 83), we aimed to compare the levels of circulating microRNAs in groups with vulnerable plaques (N = 22), stable plaques (N = 23) and plaque-free (N = 17) depending on coronary computed tomography angiography and to evaluate associations of microRNA levels with calculated cardiovascular risks (CVR), based on the SCORE2 (+OP), ACC/AHA, ATP-III and MESA scales. Coronary computed tomography was performed on a 640-slice computed tomography scanner. Relative plasma levels of microRNA were assessed via a real-time polymerase chain reaction. We found significant differences in miR-143-3p levels (p = 0.0046 in plaque-free vs. vulnerable plaque groups) and miR-181b-5p (p = 0.0179 in stable vs. vulnerable plaques groups). Analysis of microRNA associations with CVR did not show significant differences for SCORE2 (+OP) and ATPIII scales. MiR-126-5p and miR-150-5p levels were significantly higher (p < 0.05) in patients with ACC/AHA risk >10% and miR-145-5p had linear relationships with ACC/AHA score (adjusted p = 0.0164). The relative plasma level of miR-195 was higher (p < 0.05) in patients with MESA risk > 7.5% and higher (p < 0.05) in patients with zero coronary calcium index (p = 0.036). A linear relationship with coronary calcium was observed for miR-126-3p (adjusted p = 0.0484). A positive correlation with high coronary calcium levels (> 100 Agatson units) was found for miR-181-5p (p = 0.036). Analyzing the biological pathways of these microRNAs, we suggest that miR-143-3p and miR-181-5p can be potential markers of the atherosclerosis process. Other miRNAs (miR-126-3p, 126-5p, 145-5p, 150-5p, 195-5p) can be considered as potential cardiovascular risk modifiers, but it is necessary to validate our results in a large prospective trial.

Monocyte-to-albumin ratio as a novel predictor of long-term adverse outcomes in patients after percutaneous coronary intervention

Background: Monocyte count and serum albumin (Alb) have been proven to be involved in the process of systemic inflammation. Therefore, we investigated the prognostic value of monocyte-to-albumin ratio (MAR) in patients who underwent percutaneous coronary intervention (PCI).

Methods: We enrolled a total of 3561 patients in the present study from January 2013 to December 2017. They were divided into two groups according to MAR cut-off value (MAR < 0.014, n=2220; MAR ≥ 0.014, n=1119) as evaluated by receiver operating characteristic (ROC) curve. The average follow-up time was 37.59 ± 22.24 months.

Results: The two groups differed significantly in the incidences of all-cause mortality (ACM; P<0.001), cardiac mortality (CM; P<0.001), major adverse cardiovascular events (MACEs; P=0.038), and major adverse cardiovascular and cerebrovascular events (MACCEs; P=0.037). Multivariate Cox regression analyses revealed MAR as an independent prognostic factor for ACM and CM. The incidence of ACM increased by 56.5% (hazard ratio [HR] = 1.565; 95% confidence interval [CI], 1.086–2.256; P=0.016) and that of CM increased by 76.3% (HR = 1.763; 95% CI, 1.106–2.810; P=0.017) in patients in the higher-MAR group. Kaplan–Meier survival analysis suggested that patients with higher MAR tended to have an increased accumulated risk of ACM (Log-rank P<0.001) and CM (Log-rank P<0.001).

Conclusion: The findings of the present study suggested that MAR was a novel independent predictor of long-term mortality in patients who underwent PCI.

Peripheral blood microRNAs and the COVID-19 patient: methodological considerations, technical challenges and practice points

The COVID-19 emergency pandemic resulting from infection with SARS-CoV-2 represents a major threat to public health worldwide. There is an urgent clinical demand for easily accessible tools to address weaknesses and gaps in the management of COVID-19 patients. In this context, transcriptomic profiling of liquid biopsies, especially microRNAs (miRNAs), has recently emerged as a robust source of potential clinical indicators for medical decision-making. Nevertheless, the analysis of the circulating miRNA signature and its translation to clinical practice requires strict control of a wide array of methodological details. In this review, we indicate the main methodological aspects that should be addressed when evaluating the circulating miRNA profiles in COVID-19 patients, from preanalytical and analytical variables to the experimental design, impact of confounding, analysis of the data and interpretation of the findings, among others. Additionally, we provide practice points to ensure the rigour and reproducibility of miRNA-based biomarker investigations of this condition.Abbreviations: ACE: angiotensin-converting enzyme; ARDS: acute respiratory distress syndrome; COVID-19: coronavirus disease 2019; ERDN: early Detection Research Network; LMWH: low molecular weight heparin; miRNA: microRNA; ncRNA: noncoding RNA; SARS-CoV-2: severe acute respiratory syndrome coronavirus-2; SOP: standard operating procedure.

Development and Validation of a Predictive Model for Coronary Artery Disease Using Machine Learning

Early identification of coronary artery disease (CAD) can prevent the progress of CAD and effectually lower the mortality rate, so we intended to construct and validate a machine learning model to predict the risk of CAD based on conventional risk factors and lab test data. There were 3,112 CAD patients and 3,182 controls enrolled from three centers in China. We compared the baseline and clinical characteristics between two groups. Then, Random Forest algorithm was used to construct a model to predict CAD and the model was assessed by receiver operating characteristic (ROC) curve. In the development cohort, the Random Forest model showed a good AUC 0.948 (95%CI: 0.941–0.954) to identify CAD patients from controls, with a sensitivity of 90%, a specificity of 85.4%, a positive predictive value of 0.863 and a negative predictive value of 0.894. Validation of the model also yielded a favorable discriminatory ability with the AUC, sensitivity, specificity, positive predictive value, and negative predictive value of 0.944 (95%CI: 0.934–0.955), 89.5%, 85.8%, 0.868, and 0.886 in the validation cohort 1, respectively, and 0.940 (95%CI: 0.922–0.960), 79.5%, 94.3%, 0.932, and 0.823 in the validation cohort 2, respectively. An easy-to-use tool that combined 15 indexes to assess the CAD risk was constructed and validated using Random Forest algorithm, which showed favorable predictive capability (http://45.32.120.149:3000/randomforest). Our model is extremely valuable for clinical practice, which will be helpful for the management and primary prevention of CAD patients.

MicroRNAs to guide medical decision-making in obstructive sleep apnea: A review

Obstructive sleep apnea (OSA) is a common and frequently underdiagnosed sleep disorder tightly associated with a wide range of morbidities and an elevated risk of the main causes of mortality. This condition represents a major public health concern due to its increasing worldwide prevalence and its serious pathological consequences. Current clinical guidelines support the importance of effective diagnosis and treatment of OSA and emphasize the unmet need for biomarkers to guide medical decision-making. In recent years, the noncoding transcriptome has emerged as a new opportunity for biomarker discovery. In this review, we provide a brief overview of the current understanding of noncoding RNAs, specifically microRNAs (miRNAs). Then, we carefully address the potential role of miRNAs as novel indicators for the management of both pediatric and adult OSA, highlighting their translational applicability, particularly for diagnosis and therapy allocation. Finally, we identify the gaps in the research state-of-art, discuss current methodological and conceptual limitations and propose future key steps and perspectives for the incorporation of miRNAs into routine clinical practice.

Improved cardiovascular risk prediction in patients with end-stage renal disease on hemodialysis using machine learning modeling and circulating microribonucleic acids

Rationale: To test whether novel biomarkers, such as microribonucleic acids (miRNAs), and nonstandard predictive models, such as decision tree learning, provide useful information for medical decision-making in patients on hemodialysis (HD).

Methods: Samples from patients with end-stage renal disease receiving HD included in the AURORA trial were investigated (n=810). The study included two independent phases: phase I (matched cases and controls, n=410) and phase II (unmatched cases and controls, n=400). The composite endpoint was cardiovascular death, nonfatal myocardial infarction or nonfatal stroke. miRNA quantification was performed using miRNA sequencing and RT-qPCR. The CART algorithm was used to construct regression tree models. A bagging-based procedure was used for validation.

Results: In phase I, miRNA sequencing in a subset of samples (n=20) revealed miR-632 as a candidate (fold change=2.9). miR-632 was associated with the endpoint, even after adjusting for confounding factors (HR from 1.43 to 1.53). These findings were not reproduced in phase II. Regression tree models identified eight patient subgroups with specific risk patterns. miR-186-5p and miR-632 entered the tree by redefining two risk groups: patients older than 64 years and with hsCRP<0.827 mg/L and diabetic patients younger than 64 years. miRNAs improved the discrimination accuracy at the beginning of the follow-up (24 months) compared to the models without miRNAs (integrated AUC [iAUC]=0.71).

Conclusions: The circulating miRNA profile complements conventional risk factors to identify specific cardiovascular risk patterns among patients receiving maintenance HD.

Association of Circulating microRNAs with Coronary Artery Disease and Usefulness for Reclassification of Healthy Individuals: The REGICOR Study

Risk prediction tools cannot identify most individuals at high coronary artery disease (CAD) risk. Oxidized low-density lipoproteins (oxLDLs) and microRNAs are actively involved in atherosclerosis. Our aim was to examine the association of CAD and oxLDLs-induced microRNAs, and to assess the microRNAs predictive capacity of future CAD events. Human endothelial and vascular smooth muscle cells were treated with oxidized/native low-density lipoproteins, and microRNA expression was analyzed. Differentially expressed and CAD-related miRNAs were examined in serum samples from (1) a case-control study with 476 myocardial infarction (MI) patients and 487 controls, and (2) a case-cohort study with 105 incident CAD cases and 455 randomly-selected cohort participants. MicroRNA expression was analyzed with custom OpenArray plates, log rank tests and Cox regression models. Twenty-one microRNAs, two previously undescribed (hsa-miR-193b-5p and hsa-miR-1229-5p), were up- or down-regulated upon cell treatment with oxLDLs. One of the 21, hsa-miR-122-5p, was also upregulated in MI cases (fold change = 4.85). Of the 28 CAD-related microRNAs tested, 11 were upregulated in MI cases-1 previously undescribed (hsa-miR-16-5p)-, and 1/11 was also associated with CAD incidence (adjusted hazard ratio = 0.55 (0.35–0.88)) and improved CAD risk reclassification, hsa-miR-143-3p. We identified 2 novel microRNAs modulated by oxLDLs in endothelial cells, 1 novel microRNA upregulated in AMI cases compared to controls, and one circulating microRNA that improved CAD risk classification.

Emerging role of microRNAs in dilated cardiomyopathy: evidence regarding etiology

Dilated cardiomyopathy (DCM) is a heart muscle disease characterized by ventricular dilation and systolic dysfunction in the absence of abnormal loading conditions or coronary artery disease. This cardiac disorder is a major health problem due to its high prevalence, morbidity, and mortality. DCM is a complex disease with a common phenotype but heterogeneous pathological mechanisms. Early etiological diagnosis and prognosis stratification is crucial for the clinical management of the patient. Advances in imaging technology and genetic tests have provided useful tools for clinical practice. Nevertheless, the assessment of the disease remains challenging. Novel noninvasive indicators are still needed to assist in decision-making. microRNAs (miRNAs), a group of small noncoding RNAs, have been identified as key mediators of cell biology. They are found in a stable form in body fluids and their concentration is altered in response to stress. Previous research has suggested that the miRNA signature constitutes a novel source of noninvasive biomarkers for a wide array of cardiovascular diseases. Specifically, several studies have reported the potential role of miRNAs as clinical indicators among the etiologies of DCM. However, this field has not been reviewed in detail. Here, we summarize the evidence of intracellular and circulating miRNAs in DCM and their usefulness in the development of novel diagnostic, prognostic and therapeutic approaches, with a focus on DCM etiology. Although the findings are still preliminary, due to methodological and technical limitations and the lack of robust population-based studies, miRNAs constitute a promising tool to assist in the clinical management of DCM.

Identification of a blood-based 12-gene signature that predicts the severity of coronary artery stenosis: An integrative approach based on gene network construction, Support Vector Machine algorithm, and multi-cohort validation

BACKGROUND AND AIMS

We aimed to identify a blood-based gene expression score (GES) to predict the severity of coronary artery stenosis in patients with known or suspected coronary artery disease (CAD) by integrative use of gene network construction, Support Vector Machine (SVM) algorithm, and multi-cohort validation.

METHODS

In the discovery phase, a public blood-based microarray dataset of 110 patients with known CAD was analyzed by weighted gene coexpression network analysis and protein-protein interaction network analysis to identify candidate hub genes. In the training set with 151 CAD patients, bioinformatically identified hub genes were experimentally verified by real-time polymerase chain reaction, and statistically filtered with the SVM algorithm to develop a GES. Internal and external validation of GES was performed in patients with suspected CAD from two validation cohorts (n = 209 and 206).

RESULTS

The discovery phase screened 15 network-centric hub genes significantly correlated with the Duke CAD Severity Index. In the training cohort, 12 of 15 hub genes were filtered to construct a blood-based GES12, which showed good discrimination for higher modified Gensini scores (AUC: 0.798 and 0.812), higher Sullivan Extent scores (AUC: 0.776 and 0.778), and the presence of obstructive CAD (AUC: 0.834 and 0.792) in two validation cohorts. A nomogram comprising GES12, smoking status, hypertension status, low density lipoprotein cholesterol level, and body mass index further improved performance, with respect to discrimination, risk classification, and clinical utility, for prediction of coronary stenosis severity.

CONCLUSIONS

GES12 is useful in predicting the severity of coronary artery stenosis in patients with known or suspected CAD.