microRNA neural networks improve diagnosis of acute coronary syndrome (ACS)

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.

Clinical Application of Serum microRNAs in Atherosclerotic Coronary Artery Disease

MicroRNAs (miRs) are promising diagnostic, prognostic and therapeutic biomolecules for atherosclerotic cardiovascular disease. Atherosclerotic occlusive disease concerns a large population of patients, carrying the highest incidence of fatal and non-fatal adverse events, such as myocardial infarction, ischemic stroke, and limb ischemia, worldwide. Consistently, miRs are involved in regulation and pathogenesis of atherosclerotic coronary artery disease (CAD), acute coronary syndromes (ACS), both with ST-segment (STEMI) and non-ST segment elevation myocardial infarctions (NSTEMI), as well as cardiac remodeling and fibrosis following ACS. However, the genetic and molecular mechanisms underlying adverse outcomes in CAD are multifactorial, and sometimes difficult to interpret for clinicians. Therefore, in the present review paper we have focused on the clinical meaning and the interpretation of various miRs findings, and their potential application in routine clinical practice.

Marathon-Induced Cardiac Strain as Model for the Evaluation of Diagnostic microRNAs for Acute Myocardial Infarction

Background: The current gold standard biomarker for myocardial infarction (MI), cardiac troponin (cTn), is recognized for its high sensitivity and organ specificity; however, it lacks diagnostic specificity. Numerous studies have introduced circulating microRNAs as potential biomarkers for MI. This study investigates the MI-specificity of these serum microRNAs by investigating myocardial stress/injury due to strenuous exercise. Methods: MicroRNA biomarkers were retrieved by comprehensive review of 109 publications on diagnostic serum microRNAs for MI. MicroRNA levels were first measured by next-generation sequencing in pooled sera from runners (n = 46) before and after conducting a full competitive marathon. Hereafter, reverse transcription quantitative real-time PCR (qPCR) of 10 selected serum microRNAs in 210 marathon runners was performed (>10,000 qPCR measurements). Results: 27 potential diagnostic microRNA for MI were retrieved by the literature review. Eight microRNAs (miR-1-3p, miR-21-5p, miR-26a-5p, miR-122-5p, miR-133a-3p, miR-142-5p, miR-191-5p, miR-486-3p) showed positive correlations with cTnT in marathon runners, whereas two miRNAs (miR-134-5p and miR-499a-5p) showed no correlations. Upregulation of miR-133a-3p (p = 0.03) and miR-142-5p (p = 0.01) went along with elevated cTnT after marathon. Conclusion: Some MI-associated microRNAs (e.g., miR-133a-3p and miR-142-5p) have similar kinetics under strenuous exercise and MI as compared to cTnT, which suggests that their diagnostic specificity could be limited. In contrast, several MI-associated microRNAs (miR-26a-5p, miR-134-5p, miR-191-5p) showed different release behavior; hence, combining cTnT with these microRNAs within a multi-marker strategy may add diagnostic accuracy in MI.

Regulation of Long Non-coding RNAs and MicroRNAs in Heart Disease: Insight Into Mechanisms and Therapeutic Approaches

Cardiovascular disease is the leading cause of mortality worldwide and there is an increasing need to identify new therapeutic targets that could be used to prevent or treat these diseases. Due to recent scientific advances, non-coding RNAs are widely accepted as important regulators of cellular processes, and the identification of an axis of interaction between long non-coding RNAs (lncRNAs) and micro RNAs (miRNAs) has provided another platform through which cardiovascular disease could be targeted therapeutically. Increasing evidence has detailed the importance of these non-coding RNAs, both individually and in an axis of regulation, in the processes and diseases involving the heart. However, further investigation into the consequences of targeting this mechanism, as well as refinement of how the system is targeted, are required before a treatment can be provided in clinic. This level of genomic regulation provides an exciting potential novel therapeutic strategy for the treatment of cardiovascular disease.