Dataset Information

Using Anti-Malondialdehyde Modified Peptide Autoantibodies to Import Machine Learning for Predicting Coronary Artery Stenosis in Taiwanese Patients with Coronary Artery Disease.

ABSTRACT: Machine learning (ML) algorithms have been applied to predicting coronary artery disease (CAD). Our purpose was to utilize autoantibody isotypes against four different unmodified and malondialdehyde (MDA)-modified peptides among Taiwanese with CAD and healthy controls (HCs) for CAD prediction. In this study, levels of MDA, MDA-modified protein (MDA-protein) adducts, and autoantibody isotypes against unmodified peptides and MDA-modified peptides were measured with enzyme-linked immunosorbent assay (ELISA). To improve the performance of ML, we used decision tree (DT), random forest (RF), and support vector machine (SVM) coupled with five-fold cross validation and parameters optimization. Levels of plasma MDA and MDA-protein adducts were higher in CAD patients than in HCs. IgM anti-IGKC^76-99 MDA and IgM anti-A1AT^284-298 MDA decreased the most in patients with CAD compared to HCs. In the experimental results of CAD prediction, the decision tree classifier achieved an area under the curve (AUC) of 0.81; the random forest classifier achieved an AUC of 0.94; the support vector machine achieved an AUC of 0.65 for differentiating between CAD patients with stenosis rates of 70% and HCs. In this study, we demonstrated that autoantibody isotypes imported into machine learning algorithms can lead to accurate models for clinical use.

SUBMITTER: Hsu YC

PROVIDER: S-EPMC8229983 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundCoronary artery stenosis induces heart diseases including acute coronary syndrome (ACS). Some studies reported the ceramide species are associated with the ACS and major adverse cardia and cerebrovascular events (MACE). However, few studies investigated the association between plasma ceramide levels and the severity of stenosis, together with the onset of diseases. This aim of the present study was to investigate the association betweencertain ceramide species, coronary artery stenosis and acute coronary syndrome.MethodsFive hundred fifty-three patients with definite or suspected CAD were recruited and received angiography. Subjects were assigned into 4 groups according to the severity of coronary artery stenosis. The measurements of 4 plasma ceramide species, namely, Cer (d18:1/16:0), Cer (d18:1/18:0), Cer (d18:1/24:1), Cer (d18:1/24:0) were carried out by Liquid chromatography-tandem mass spectrometry (LC-MS/MS) and the ratio of Cer (d18:1/16:0), Cer (d18:1/18:0) and Cer (d18:1/24:1) to Cer (18:1/24:0), respectively, were calculated as index to evaluate the association between plasma ceramides levels and coronary artery stenosis. Multiple logistic regression analysis was used to establish the prognostic model for the prediction of ACS risk.ResultsAfter the adjustment by multiple clinical risk factors including age, gender, pre-existing myocardial/cerebral infarction, hemoglobin A1c% (HbA1c%), smoking and the diagnosis during index hospitalization, multiple logistic regression analysis showed that the high ratio of Cer (d18:1/24:1) to Cer (d18:1/24:0), female gender, HbA1c%, unstable angina (UAP) and acute myocardial infarction (AMI) diagnosis (compared with atherosclerosis) during index hospitalization were associated with more severe coronary artery stenosis. Furthermore, the prognostic model was established after adjustment of risk factors and the area under curve (AUC) of receiver operating characteristics (ROC) for the prognostic model was 0.732 and 95% CI was 0.642-0.822.ConclusionThe severity of coronary artery stenosis is associated with high ratio of Cer (d18:1/24:1) to Cer (d18:1/24:0), female gender, HbA1c% and AMI. Although the reported prognostic model showed a good discrimination, further investigation on long term MACE is needed to evaluate the role of ceramide for the prediction of MACE risk.

Project description:Purpose Predictive analytics (PA) is a new trending approach in the field of healthcare that uses machine learning to build a prediction model using supervised learning algorithms. Isolated coronary artery bypass grafting (iCABG), an open-heart surgery, is commonly performed in the treatment of coronary heart disease. Aim The aim of this study was to develop and evaluate a model to predict postoperative length of stay (PLoS) for iCABG patients using supervised machine learning techniques, and to identify the features with the highest contribution to the model. Methods This is a retrospective study that uses historic data of adult patients who underwent isolated CABG (iCABG). After initial data pre-processing, data imputation using the kNN method was applied. The study used five prediction models using Naïve Bayes, Decision Tree, Random Forest, Logistic Regression and k Nearest Neighbor algorithms. Data imbalance was managed using the following widely used methods: oversampling, undersampling, “Both”, and random over-sampling examples (ROSE). The features selection process was conducted using the Boruta method. Two techniques were applied to examine the performance of the models, (70%, 30%) split and cross-validation, respectively. Models were evaluated by comparing their performance using AUC and other metrics. Results In the final dataset, six distinct features and 621 instances were used to develop the models. A total of 20 models were developed using R statistical software. The model generated using Random Forest with “Both” resampling method and cross-validation technique was deemed the best fit (AUC=0.81; F1 score=0.82; and recall=0.82). Attributes found to be highly predictive of PLoS were pulmonary artery systolic, age, height, EuroScore II, intra-aortic balloon pump used, and complications during operation. Conclusion This study demonstrates the significance and effectiveness of building a model that predicts PLoS for iCABG patients using patient specifications and pre-/intra-operative measures.

Project description:Rationale & objectiveThe presence of calcified plaques in the coronary arteries is associated with cardiovascular mortality and is a hallmark of chronic kidney failure, but it is unclear whether this is associated with the same degree of coronary artery stenosis as in patients without kidney disease. We compared the relationship of coronary artery calcification (CAC) and stenosis between dialysis patients and patients without chronic kidney disease (CKD).Study designObservational cohort study.Setting & participants127 dialysis patients and 447 patients without CKD with cardiovascular risk factors underwent cardiac computed tomography (CT), consisting of non-contrast-enhanced CT and CT angiography. CAC score and degree of coronary artery stenosis were assessed by independent readers.PredictorDialysis treatment.OutcomeAssociation between calcification and stenosis.Analytical approachLogistic regression to determine the association between CAC score and the presence of stenosis in a matched cohort and, in the full cohort, testing for the interaction of dialysis status with this relationship.Results112 patients were matched from each cohort, totaling 224 patients, using propensity scores for dialysis, balancing numerous cardiovascular risk factors. Median CAC score was 210 (IQR, 19-859) in dialysis patients and 58 (IQR, 0-254) in patients without CKD; 35% of dialysis patients and 36% of patients without CKD had coronary artery stenosis ≥ 50%. Per each 100-unit higher CAC score, the matched dialysis cohort had significantly lower ORs for stenosis than the non-CKD cohort, 0.67 (95% CI, 0.52-0.83) for stenosis ≥ 50% and 0.75 (95% CI, 0.62-0.90) for stenosis ≥ 70%.LimitationsNo comparison with the gold standard fractional flow reserve.ConclusionsDialysis patients have higher risk for coronary artery stenosis with higher CAC scores, but this risk is comparatively lower than in patients without CKD with similar CAC scores. In dialysis patients, a high CAC score can easily be found without significant stenosis. Our data enable "translation" of degree of calcification to the probability of coronary stenosis in dialysis patients.

Dataset Information

Using Anti-Malondialdehyde Modified Peptide Autoantibodies to Import Machine Learning for Predicting Coronary Artery Stenosis in Taiwanese Patients with Coronary Artery Disease.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets