Machine-learning facilitates selection of a novel diagnostic panel of metabolites for the detection of heart failure

Machine learning and multi-omics integration: advancing cardiovascular translational research and clinical practice

The global burden of cardiovascular diseases continues to rise, making their prevention, diagnosis and treatment increasingly critical. With advancements and breakthroughs in omics technologies such as high-throughput sequencing, multi-omics approaches can offer a closer reflection of the complex physiological and pathological changes in the body from a molecular perspective, providing new microscopic insights into cardiovascular diseases research. However, due to the vast volume and complexity of data, accurately describing, utilising, and translating these biomedical data demands substantial effort. Researchers and clinicians are actively developing artificial intelligence (AI) methods for data-driven knowledge discovery and causal inference using various omics data. These AI approaches, integrated with multi-omics research, have shown promising outcomes in cardiovascular studies. In this review, we outline the methods for integrating machine learning, one of the most successful applications of AI, with omics data and summarise representative AI models developed that leverage various omics data to facilitate the exploration of cardiovascular diseases from underlying mechanisms to clinical practice. Particular emphasis is placed on the effectiveness of using AI to extract potential molecular information to address current knowledge gaps. We discuss the challenges and opportunities of integrating omics with AI into routine diagnostic and therapeutic practices and anticipate the future development of novel AI models for wider application in the field of cardiovascular diseases.

Insights into heart failure metabolite markers through explainable machine learning

Understanding molecular traits through metabolomics offers an avenue to tailor cardiovascular prevention, diagnosis and treatment strategies more effectively. This study focuses on the application of machine learning (ML) and explainable artificial intelligence (XAI) algorithms to detect discriminant molecular signatures in heart failure (HF). We aim to uncover metabolites with significant predictive value by analyzing targeted metabolomics data through ML and XAI algorithms. After quality control, we analyzed 55 metabolites from 124 plasma samples, including 53 HF patients and 71 controls, comparing Ridge Logistic Regression, Support Vector Machine and eXtreme Gradient Boosting models. All achieved high accuracy in predicting group labels: 84.0% [95% CI: 75.3 - 92.7], 85.73 [95% CI: 78.6 - 92.9], and 84.8% [95% CI: 76.1 - 93.5], respectively. Permutation-based variable importance and Local Interpretable Model-agnostic Explanations (LIME) were used for group-level and individual-level explainability, respectively, complemented by H-Friedman statistics for variable interactions, yielding reliable, explainable insights of the ML models. Metabolites well-known for their association with HF, such as glucose and cholesterol, and more recently described, the C18:1 carnitine, were reaffirmed in our analysis. The novel discovery of lignoceric acid (C24:0 fatty acid) as a critical discriminator, was confirmed in a replication cohort, underscoring its potential as a metabolite marker. Furthermore, our study highlights the utility of 2-way variable interaction analysis in unveiling a network of metabolite interactions essential for accurate disease prediction. The results demonstrate our approach's efficacy in identifying key metabolites and their interactions, illustrating the power of ML and XAI in advancing personalized healthcare solutions.

Metabolomic Panel for the Diagnosis of Heart Failure with Preserved Ejection Fraction

The diagnosis of heart failure with preserved ejection fraction (HFpEF) remains challenging. The use of metabolomics approaches seems promising in speeding up and simplifying the diagnostic process in HFpEF patients, which can lead to earlier treatment initiation and better improvement of patient condition. The aim of this study was to develop a diagnostic panel of metabolites (metabolomic biomarkers) for the detection and diagnosis of HF with preserved ejection fraction. The study included 76 participants with hypertension, 36 of whom were diagnosed with HFpEF. The blood plasma metabolomic profile, including 72 metabolites, was detected using high-performance liquid chromatography combined with mass spectrometry. There were 18 statistically significant differences in concentrations of metabolites and 3 differences in their ratios between HFpEF and hypertension groups. The prognostic model for detecting the possibility of HFpEF included seven metabolites and two ratios: hexadecenoylcarnitine, arginine, trimethylamine-N-oxide, asymmetric dimethylarginine (ADMA), arginine/ADMA ratio, kynurenine, kynurenine/tryptophan, neopterin, and anthranilic acid. The area under the ROC curve was 0.981 ± 0.017. The resulting model was statistically significant (p < 0.001). The metabolomic panel could be considered as an addition to the present HFpEF laboratory diagnostic criteria for blood plasma analysis in clinical practice.

Integrating Metabolomics Domain Knowledge with Explainable Machine Learning in Atherosclerotic Cardiovascular Disease Classification

Metabolomic data often present challenges due to high dimensionality, collinearity, and variability in metabolite concentrations. Machine learning (ML) application in metabolomic analyses is enabling the extraction of meaningful information from complex data. Bringing together domain-specific knowledge from metabolomics with explainable ML methods can refine the predictive performance and interpretability of models used in atherosclerosis research. In this work, we aimed to identify the most impactful metabolites associated with the presence of atherosclerotic cardiovascular disease (ASCVD) in cross-sectional case-control studies using explainable ML methods integrated with metabolomics domain knowledge. For this, a subset from the FLEMENGHO cohort with metabolomic data available was used as the training cohort, including 63 patients with a history of ASCVD and 52 non-smoking controls matched by age, sex, and body mass index from the same population. First, Partial Least Squares Discriminant Analysis (PLS-DA) was applied for dimensionality reduction. The selected metabolites' correlations were analyzed by considering their chemical categorization. Then, eXtreme Gradient Boosting (XGBoost) was used to identify metabolites that characterize ASCVD. Next, the selected metabolites were evaluated in an external cohort to determine their effectiveness in distinguishing between cases and controls. A total of 56 metabolites were selected for ASCVD discrimination using PLS-DA. The primary identified metabolites' superclasses included lipids, organic acids, and organic oxygen compounds. Upon integrating these metabolites with the XGBoost model, the classification yielded a test area under the curve (AUC) of 0.75. SHAP analyses ranked cholesterol, 3-methylhistidine, and glucuronic acid among the most impactful features and showed the diversity of metabolites considered for building the ASCVD discriminator. Also using XGBoost, the selected metabolites achieved an AUC of 0.93 in an independent external validation cohort. In conclusion, the combination of different metabolites has the potential to build classifiers for ASCVD. Integrating metabolite categorization within the SHAP analysis further enhanced the interpretability of the model, offering insights into metabolite-specific contributions to ASCVD risk.

Cardiometabolic Modulation by Semaglutide Contributes to Cardioprotection in Rats with Myocardial Infarction

Background

Acute myocardial infarction (AMI) is a significant clinical challenge. Semaglutide has therapeutic potential in cardiovascular disease management, but its specific impact and mechanisms in AMI are not fully understood.

Methods

Twenty-four male Sprague-Dawley rats were divided into three groups: control (Control), infarction-only (MI), and semaglutide-treated (SEMA). Weight, blood glucose, and lipid profiles were analyzed. Cardiac function was evaluated via echocardiography. Histopathological assessment and immunohistochemical analysis were performed. Untargeted metabolomic analysis using LC-MS/MS was utilized.

Results

Semaglutide treatment was associated with a reduction in body weight, blood glucose, total cholesterol (TC), and low-density lipoprotein cholesterol (LDL-C), as well as an enhancement in the left ventricular ejection fraction (Control vs MI vs SEMA, 69.13±4.30 vs 30.16±3.17 vs 39.81±6.13, P < 0.05). It also had a lower collagen volume fraction (3.05 vs 34.05 vs 17.73, P < 0.05) and ameliorated the accumulation of glycogen in the myocardium. Metabolomic profiling revealed differentially expressed metabolites between the control/MI and MI/SEMA groups, predominantly within benzenoid, lipid, and organic acid categories. Pathway enrichment analysis highlighted amino sugar and nucleotide sugar metabolism, chlorocyclohexane and chlorobenzene degradation, and phenylalanine, tyrosine, and tryptophan biosynthesis. Random forest analysis identified key metabolites, including downregulated Docusate sodium, 1-(2-Thienyl)-1-heptanone, and Adenylyl-molybdopterin, alongside upregulated Methylenediphosphonic acid, Choline sulfate, and Lactosamine.

Conclusion

Semaglutide significantly ameliorated myocardial fibrosis and metabolic dysregulation in rats post-myocardial infarction. Its mechanism involves modulating glucose metabolism, lipid metabolism, and organic acid metabolism. Targeted metabolites, including Docusate sodium, 1-(2-Thienyl)-1-heptanone, Adenylyl-molybdopterin, Methylenediphosphonic acid, Choline sulfate, and Lactosamine, are implicated in the metabolic reprogramming induced by semaglutide.

Understanding ayahuasca effects in major depressive disorder treatment through in vitro metabolomics and bioinformatics

Emerging insights from metabolomic-based studies of major depression disorder (MDD) are mainly related to biochemical processes such as energy or oxidative stress, in addition to neurotransmission linked to specific metabolite intermediates. Hub metabolites represent nodes in the biochemical network playing a critical role in integrating the information flow in cells between metabolism and signaling pathways. Limited technical-scientific studies have been conducted to understand the effects of ayahuasca (Aya) administration in the metabolism considering MDD molecular context. Therefore, this work aims to investigate an in vitro primary astrocyte model by untargeted metabolomics of two cellular subfractions: secretome and intracellular content after pre-defined Aya treatments, based on DMT concentration. Mass spectrometry (MS)-based metabolomics data revealed significant hub metabolites, which were used to predict biochemical pathway alterations. Branched-chain amino acid (BCAA) metabolism, and vitamin B6 and B3 metabolism were associated to Aya treatment, as "housekeeping" pathways. Dopamine synthesis was overrepresented in the network results when considering the lowest tested DMT concentration (1 µmol L^-1). Building reaction networks containing significant and differential metabolites, such as nicotinamide, L-DOPA, and L-leucine, is a useful approach to guide on dose decision and pathway selection in further analytical and molecular studies.

Artificial Intelligence and Cardiovascular Risk Prediction: All That Glitters is not Gold

Artificial intelligence (AI) is a broad term referring to any automated systems that need 'intelligence' to carry out specific tasks. During the last decade, AI-based techniques have been gaining popularity in a vast range of biomedical fields, including the cardiovascular setting. Indeed, the dissemination of cardiovascular risk factors and the better prognosis of patients experiencing cardiovascular events resulted in an increase in the prevalence of cardiovascular disease (CVD), eliciting the need for precise identification of patients at increased risk for development and progression of CVD. AI-based predictive models may overcome some of the limitations that hinder the performance of classic regression models. Nonetheless, the successful application of AI in this field requires knowledge of the potential pitfalls of the AI techniques, to guarantee their safe and effective use in daily clinical practice. The aim of the present review is to summarise the pros and cons of different AI methods and their potential application in the cardiovascular field, with a focus on the development of predictive models and risk assessment tools.

Probiotic-mediated p38 MAPK immune signaling prolongs the survival of Caenorhabditis elegans exposed to pathogenic bacteria

The host-microbiota cross-talk represents an important factor contributing to innate immune response and host resistance during infection. It has been shown that probiotic lactobacilli exhibit the ability to modulate innate immunity and enhance pathogen elimination. Here we showed that heat-inactivated probiotic strain Lactobacillus curvatus BGMK2-41 stimulates immune response and resistance of the Caenorhabditis elegans against Staphylococcus aureus and Pseudomonas aeruginosa. By employing qRT-PCR and western blot analysis we showed that heat-inactivated BGMK2-41 activated PMK-1/p38 MAPK immunity pathway which prolongs the survival of C. elegans exposed to pathogenic bacteria in nematode killing assays. The C. elegans pmk-1 mutant was used to demonstrate a mechanistic basis for the antimicrobial potential of BGMK2-41, showing that BGMK2-41 upregulated PMK-1/p38 MAPK dependent transcription of C-type lectins, lysozymes and tight junction protein CLC-1. Overall, this study suggests that PMK-1/p38 MAPK-dependent immune regulation by BGMK2-41 is essential for probiotic-mediated C. elegans protection against gram-positive and gram-negative bacteria and could be further explored for development of probiotics with the potential to increase resistance of the host towards pathogens.

Metabolomic Profiling of Adults with Congenital Heart Disease

Metabolomic analysis may provide an integrated assessment in genetically and pathologically heterogeneous populations. We used metabolomic analysis to gain mechanistic insight into the small and diverse population of adults with congenital heart disease (ACHD). Consecutive ACHD patients seen at a single institution were enrolled. Clinical variables and whole blood were collected at regular clinical visits. Stored plasma samples were analyzed for the concentrations of 674 metabolites and metabolic markers using mass spectrometry with internal standards. These samples were compared to 28 simultaneously assessed healthy non-ACHD controls. Principal component analysis and multivariable regression modeling were used to identify metabolites associated with clinical outcomes in ACHD. Plasma from ACHD and healthy control patients differed in the concentrations of multiple metabolites. Differences between control and ACHD were greater in number and in degree than those between ACHD anatomic groups. A metabolite cluster containing amino acids and metabolites of amino acids correlated with negative clinical outcomes across all anatomic groups. Metabolites in the arginine metabolic pathway, betaine, dehydroepiandrosterone, cystine, 1-methylhistidine, serotonin and bile acids were associated with specific clinical outcomes. Metabolic markers of disease may both be useful as biomarkers for disease activity and suggest etiologically related pathways as possible targets for disease-modifying intervention.

Application of machine learning in understanding atherosclerosis: Emerging insights

Biological processes are incredibly complex—integrating molecular signaling networks involved in multicellular communication and function, thus maintaining homeostasis. Dysfunction of these processes can result in the disruption of homeostasis, leading to the development of several disease processes including atherosclerosis. We have significantly advanced our understanding of bioprocesses in atherosclerosis, and in doing so, we are beginning to appreciate the complexities, intricacies, and heterogeneity atherosclerosi. We are also now better equipped to acquire, store, and process the vast amount of biological data needed to shed light on the biological circuitry involved. Such data can be analyzed within machine learning frameworks to better tease out such complex relationships. Indeed, there has been an increasing number of studies applying machine learning methods for patient risk stratification based on comorbidities, multi-modality image processing, and biomarker discovery pertaining to atherosclerotic plaque formation. Here, we focus on current applications of machine learning to provide insight into atherosclerotic plaque formation and better understand atherosclerotic plaque progression in patients with cardiovascular disease.

Clinical applications of machine learning in the diagnosis, classification, and prediction of heart failure

Machine learning and artificial intelligence are generating significant attention in the scientific community and media. Such algorithms have great potential in medicine for personalizing and improving patient care, including in the diagnosis and management of heart failure. Many physicians are familiar with these terms and the excitement surrounding them, but many are unfamiliar with the basics of these algorithms and how they are applied to medicine. Within heart failure research, current applications of machine learning include creating new approaches to diagnosis, classifying patients into novel phenotypic groups, and improving prediction capabilities. In this paper, we provide an overview of machine learning targeted for the practicing clinician and evaluate current applications of machine learning in the diagnosis, classification, and prediction of heart failure.

Collaborative AI and Laboratory Medicine integration in precision cardiovascular medicine

Artificial Intelligence (AI) is a broad term that combines computation with sophisticated mathematical models and in turn allows the development of complex algorithms which are capable to simulate human intelligence such as problem solving and learning. It is devised to promote a significant paradigm shift in the most diverse areas of medical knowledge. On the other hand, Cardiology is a vast field dealing with diseases relating to the heart, the circulatory system, and includes coronary heart disease, cerebrovascular disease, rheumatic heart disease and other conditions. AI has emerged as a promising tool in cardiovascular medicine which is aimed in augmenting the effectiveness of the cardiologist and to extend better quality to patients. It has the ability to support decision‑making and improve diagnostic and prognostic performance. Attempt has also been made to explore novel genotypes and phenotypes in existing cardiovascular diseases, improve the quality of patient care, to enablecost-effectiveness with reducereadmissionand mortality rates. Our review addresses the integration of AI and laboratory medicine as an accelerator of personalization care associated with the precision and the need of value creation services in cardiovascular medicine.