Combining the Strengths of the Explainable Boosting Machine and Metabolomics Approaches for Biomarker Discovery in Acute Myocardial Infarction
Ontology highlight
ABSTRACT:
SUBMITTER: Arslan A
PROVIDER: S-EPMC11240568 | biostudies-literature | 2024 Jun
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:ObjectiveThe occurrence of cardiovascular adverse events in the first year after ST-acute myocardial infarction (STEMI) remains high; therefore, identification of patients with poor prognosis is essential for early intervention. This study aimed to evaluate the prognostic value of metabolomics-based biomarkers in STEMI patients and explore their functional mechanisms.MethodsMetabolite profiling was performed using nuclear magnetic resonance. The plasma concentration of Kynurenine (Kyn) was measured using ultraperformance liquid chromatography/electrospray ionization quadruple time-of-flight mass spectrometry. Major adverse cardiac and cerebral events were assessed for 1 year. A functional metabolomics strategy was proposed for investigating the role of Kyn in both vitro and vivo models.ResultsThe adjusted hazard ratios in STEMI patients for Kyn in the 4th quartile 7.12(5.71-10.82) was significantly higher than that in the 3rd quartile 3.03(2.62-3.74), 2nd quartile 1.86(1.70-2.03), and 1st quartile 1.20(0.93-1.39).The incidence of MACCE was significantly different among Kyn quartiles and the highest incidence of MACCE was observed in the 4th quartile when compared with the 1st quartile (9.84% vs.2.85%, P<0.001).Immunofluorescence staining indicated that indoleamine-pyrrole 2,3-dioxygenase (IDO1) was located in the CD68 positive staining area of thrombi from STEMI patients and Kyn was induced in the early phase after myocardial infarction. Kyn could trigger inflammation and oxidative stress of macrophage cells by activation of the Sirt3-acSOD2/IL-1β signaling pathway in vitro.ConclusionsPlasma Kyn levels were positively associated with the occurrence of STEMI. Kyn could induce macrophage cells inflammation and oxidative stress by activating the Sirt3-acSOD2/IL-1β pathway following myocardial ischemia injury. Kyn could be a robust biomarker for STEMI prognosis and reduction of Kyn could be beneficial in STEMI patients.
| S-EPMC9667794 | biostudies-literature
Project description:Acute myocardial infarction (AMI) or heart attack is a significant global health threat and one of the leading causes of death. The evolution of machine learning has greatly revamped the risk stratification and death prediction of AMI. In this study, an integrated feature selection and machine learning approach was used to identify potential biomarkers for early detection and treatment of AMI. First, feature selection was conducted and evaluated before all classification tasks with machine learning. Full classification models (using all 62 features) and reduced classification models (using various feature selection methods ranging from 5 to 30 features) were built and evaluated using six machine learning classification algorithms. The results showed that the reduced models performed generally better (mean AUPRC via random forest (RF) algorithm for recursive feature elimination (RFE) method ranges from 0.8048 to 0.8260, while for random forest importance (RFI) method, it ranges from 0.8301 to 0.8505) than the full models (mean AUPRC via RF: 0.8044). The most notable finding of this study was the identification of a five-feature model that included cardiac troponin I, HDL cholesterol, HbA1c, anion gap, and albumin, which had achieved comparable results (mean AUPRC via RF: 0.8462) as to the models that containing more features. These five features were proven by the previous studies as significant risk factors for AMI or cardiovascular disease and could be used as potential biomarkers to predict the prognosis of AMI patients. From the medical point of view, fewer features for diagnosis or prognosis could reduce the cost and time of a patient as lesser clinical and pathological tests are needed.
| S-EPMC10191821 | biostudies-literature
Project description:MotivationA gradient boosting decision tree (GBDT) is a powerful ensemble machine-learning method that has the potential to accelerate biomarker discovery from high-dimensional molecular data. Recent algorithmic advances, such as extreme gradient boosting (XGB) and light gradient boosting (LGB), have rendered the GBDT training more efficient, scalable and accurate. However, these modern techniques have not yet been widely adopted in discovering biomarkers for censored survival outcomes, which are key clinical outcomes or endpoints in cancer studies.ResultsIn this paper, we present a new R package 'Xsurv' as an integrated solution that applies two modern GBDT training frameworks namely, XGB and LGB, for the modeling of right-censored survival outcomes. Based on our simulations, we benchmark the new approaches against traditional methods including the stepwise Cox regression model and the original gradient boosting function implemented in the package 'gbm'. We also demonstrate the application of Xsurv in analyzing a melanoma methylation dataset. Together, these results suggest that Xsurv is a useful and computationally viable tool for screening a large number of prognostic candidate biomarkers, which may facilitate future translational and clinical research.Availability and implementation'Xsurv' is freely available as an R package at: https://github.com/topycyao/Xsurv.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC10060728 | biostudies-literature
Project description:Background A lack of explainability in published machine learning (ML) models limits clinicians’ understanding of how predictions are made, in turn undermining uptake of the models into clinical practice. Objective The purpose of this study was to develop explainable ML models to predict in-hospital mortality in patients hospitalized for myocardial infarction (MI). Methods Adult patients hospitalized for an MI were identified in the National Inpatient Sample between January 1, 2012, and September 30, 2015. The resulting cohort comprised 457,096 patients described by 64 predictor variables relating to demographic/comorbidity characteristics and in-hospital complications. The gradient boosting algorithm eXtreme Gradient Boosting (XGBoost) was used to develop explainable models for in-hospital mortality prediction in the overall cohort and patient subgroups based on MI type and/or sex. Results The resulting models exhibited an area under the receiver operating characteristic curve (AUC) ranging from 0.876 to 0.942, specificity 82% to 87%, and sensitivity 75% to 87%. All models exhibited high negative predictive value ≥0.974. The SHapley Additive exPlanation (SHAP) framework was applied to explain the models. The top predictor variables of increasing and decreasing mortality were age and undergoing percutaneous coronary intervention, respectively. Other notable findings included a decreased mortality risk associated with certain patient subpopulations with hyperlipidemia and a comparatively greater risk of death among women below age 55 years. Conclusion The literature lacks explainable ML models predicting in-hospital mortality after an MI. In a national registry, explainable ML models performed best in ruling out in-hospital death post-MI, and their explanation illustrated their potential for guiding hypothesis generation and future study design.
| S-EPMC10435947 | biostudies-literature
Project description:Autism spectrum disorders (ASDs) are neurodevelopmental disorders characterized by behavioral alterations and currently affect about 1% of children. Significant genetic factors and mechanisms underline the causation of ASD. Indeed, many affected individuals are diagnosed with chromosomal abnormalities, submicroscopic deletions or duplications, single-gene disorders or variants. However, a range of metabolic abnormalities has been highlighted in many patients, by identifying biofluid metabolome and proteome profiles potentially usable as ASD biomarkers. Indeed, next-generation sequencing and other omics platforms, including proteomics and metabolomics, have uncovered early age disease biomarkers which may lead to novel diagnostic tools and treatment targets that may vary from patient to patient depending on the specific genomic and other omics findings. The progressive identification of new proteins and metabolites acting as biomarker candidates, combined with patient genetic and clinical data and environmental factors, including microbiota, would bring us towards advanced clinical decision support systems (CDSSs) assisted by machine learning models for advanced ASD-personalized medicine. Herein, we will discuss novel computational solutions to evaluate new proteome and metabolome ASD biomarker candidates, in terms of their recurrence in the reviewed literature and laboratory medicine feasibility. Moreover, the way to exploit CDSS, performed by artificial intelligence, is presented as an effective tool to integrate omics data to electronic health/medical records (EHR/EMR), hopefully acting as added value in the near future for the clinical management of ASD.
| S-EPMC7504551 | biostudies-literature
Project description:Despite remarkable progress in proteomic methods, including improved detection limits and sensitivity, these methods have not yet been established in routine clinical practice. The main limitations, which prevent their integration into clinics, are high cost of equipment, the need for highly trained personnel, and last, but not least, the establishment of reliable and accurate protein biomarkers or panels of protein biomarkers for detection of neoplasms. Furthermore, the complexity and heterogeneity of most solid tumours present obstacles in the discovery of specific protein signatures, which could be used for early detection of cancers, for prediction of disease outcome, and for determining the response to specific therapies. However, cancer proteome, as the end-point of pathological processes that underlie cancer development and progression, could represent an important source for the discovery of new biomarkers and molecular targets for tailored therapies.
| S-EPMC3914447 | biostudies-other
Project description:Metabolomics is emerging as a powerful tool for studying metabolic processes, identifying crucial biomarkers responsible for metabolic characteristics and revealing metabolic mechanisms, which construct the content of discovery metabolomics. The crucial biomarkers can be used to reprogram a metabolome, leading to an aimed metabolic strategy to cope with alteration of internal and external environments, naming reprogramming metabolomics here. The striking feature on the similarity of the basic metabolic pathways and components among vastly different species makes the reprogramming metabolomics possible when the engineered metabolites play biological roles in cellular activity as a substrate of enzymes and a regulator to other molecules including proteins. The reprogramming metabolomics approach can be used to clarify metabolic mechanisms of responding to changed internal and external environmental factors and to establish a framework to develop targeted tools for dealing with the changes such as controlling and/or preventing infection with pathogens and enhancing host immunity against pathogens. This review introduces the current state and trends of discovery metabolomics and reprogramming metabolomics and highlights the importance of reprogramming metabolomics.
| S-EPMC4537470 | biostudies-literature
Project description:Metabolomics is increasingly being applied towards the identification of biomarkers for disease diagnosis, prognosis and risk prediction. Unfortunately among the many published metabolomic studies focusing on biomarker discovery, there is very little consistency and relatively little rigor in how researchers select, assess or report their candidate biomarkers. In particular, few studies report any measure of sensitivity, specificity, or provide receiver operator characteristic (ROC) curves with associated confidence intervals. Even fewer studies explicitly describe or release the biomarker model used to generate their ROC curves. This is surprising given that for biomarker studies in most other biomedical fields, ROC curve analysis is generally considered the standard method for performance assessment. Because the ultimate goal of biomarker discovery is the translation of those biomarkers to clinical practice, it is clear that the metabolomics community needs to start "speaking the same language" in terms of biomarker analysis and reporting-especially if it wants to see metabolite markers being routinely used in the clinic. In this tutorial, we will first introduce the concept of ROC curves and describe their use in single biomarker analysis for clinical chemistry. This includes the construction of ROC curves, understanding the meaning of area under ROC curves (AUC) and partial AUC, as well as the calculation of confidence intervals. The second part of the tutorial focuses on biomarker analyses within the context of metabolomics. This section describes different statistical and machine learning strategies that can be used to create multi-metabolite biomarker models and explains how these models can be assessed using ROC curves. In the third part of the tutorial we discuss common issues and potential pitfalls associated with different analysis methods and provide readers with a list of nine recommendations for biomarker analysis and reporting. To help readers test, visualize and explore the concepts presented in this tutorial, we also introduce a web-based tool called ROCCET (ROC Curve Explorer & Tester, http://www.roccet.ca). ROCCET was originally developed as a teaching aid but it can also serve as a training and testing resource to assist metabolomics researchers build biomarker models and conduct a range of common ROC curve analyses for biomarker studies.
| S-EPMC3608878 | biostudies-literature
Project description:Cystic renal disease (CRD) comprises a heterogeneous group of genetic and acquired disorders. The cystic lesions are detected through imaging, either incidentally or after symptoms develop, due to an underlying disease process. In this study, we aim to study the metabolomic profiles of CRD patients for potential disease-specific biomarkers using unlabeled and labeled metabolomics using low and high-resolution mass spectrometry (MS), respectively. Dried-blood spot (DBS) and serum samples, collected from CRD patients and healthy controls, were analyzed using the unlabeled and labeled method. The metabolomics profiles for both sets of samples and groups were collected, and their data were processed using the lab's standard protocol. The univariate analysis showed (FDR p < 0.05 and fold change 2) was significant to show a group of potential biomarkers for CRD discovery, including uridine diphosphate, cystine-5-diphosphate, and morpholine. Several pathways were involved in CRD patients based on the metabolic profile, including aminoacyl-tRNA biosynthesis, purine and pyrimidine, glutathione, TCA cycle, and some amino acid metabolism (alanine, aspartate and glutamate, arginine and tryptophan), which have the most impact. In conclusion, early CRD detection and treatment is possible using a metabolomics approach that targets alanine, aspartate, and glutamate pathway metabolites.
| S-EPMC8389671 | biostudies-literature
Project description:Pathogenic and opportunistic free-living amoebae such as Acanthamoeba spp. can cause keratitis (Acanthamoeba keratitis [AK]), which may ultimately lead to permanent visual impairment or blindness. Acanthamoeba can also cause rare but usually fatal granulomatous amoebic encephalitis (GAE). Current therapeutic options for AK require a lengthy treatment with nonspecific drugs that are often associated with adverse effects. Recent developments in the field led us to target cAMP pathways, specifically phosphodiesterase. Guided by computational tools, we targeted the Acanthamoeba phosphodiesterase RegA. Computational studies led to the construction and validation of a homology model followed by a virtual screening protocol guided by induced-fit docking and chemical scaffold analysis using our medicinal and biological chemistry (MBC) chemical library. Subsequently, 18 virtual screening hits were prioritized for further testing in vitro against Acanthamoeba castellanii, identifying amoebicidal hits containing piperidine and urea imidazole cores. Promising activities were confirmed in the resistant cyst form of the amoeba and in additional clinical Acanthamoeba strains, increasing their therapeutic potential. Mechanism-of-action studies revealed that these compounds produce apoptosis through reactive oxygen species (ROS)-mediated mitochondrial damage. These chemical families show promise for further optimization to produce effective antiacanthamoebal drugs.
| S-EPMC7849001 | biostudies-literature