Early prediction of microvascular obstruction prior to percutaneous coronary intervention

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Early prediction of microvascular obstruction (MVO) occurrence in acute myocardial infarction (AMI) patients undergoing percutaneous coronary intervention (PCI) can facilitate personalized management and improve prognosis. This study developed a prediction model for MVO occurrence using preoperative clinical data and validated its performance in a prospective cohort. A total of 504 AMI patients were included, with 406 in the exploratory cohort and 98 in the prospective cohort. Feature selection was performed using random forest recursive feature elimination (RF-RFE), identifying five key predictors: High-Sensitivity Troponin T, Neutrophil Count, Creatine Kinase-MB, Fibrinogen, and Left Ventricular Ejection Fraction. Among the models developed, logistic regression demonstrated the highest predictive performance, achieving an AUC score of 0.800 in the exploratory cohort and 0.792 in the prospective cohort. This model has been integrated into a user-friendly online platform, providing a practical tool for guiding personalized perioperative management and improving patient prognosis.

Related collections

Most cited references 42

Record: found
Abstract: found
Article: not found

MissForest--non-parametric missing value imputation for mixed-type data.

Daniel J Stekhoven, Peter Bühlmann (2012)

Modern data acquisition based on high-throughput technology is often facing the problem of missing data. Algorithms commonly used in the analysis of such large-scale data often depend on a complete set. Missing value imputation offers a solution to this problem. However, the majority of available imputation methods are restricted to one type of variable only: continuous or categorical. For mixed-type data, the different types are usually handled separately. Therefore, these methods ignore possible relations between variable types. We propose a non-parametric method which can cope with different types of variables simultaneously. We compare several state of the art methods for the imputation of missing values. We propose and evaluate an iterative imputation method (missForest) based on a random forest. By averaging over many unpruned classification or regression trees, random forest intrinsically constitutes a multiple imputation scheme. Using the built-in out-of-bag error estimates of random forest, we are able to estimate the imputation error without the need of a test set. Evaluation is performed on multiple datasets coming from a diverse selection of biological fields with artificially introduced missing values ranging from 10% to 30%. We show that missForest can successfully handle missing values, particularly in datasets including different types of variables. In our comparative study, missForest outperforms other methods of imputation especially in data settings where complex interactions and non-linear relations are suspected. The out-of-bag imputation error estimates of missForest prove to be adequate in all settings. Additionally, missForest exhibits attractive computational efficiency and can cope with high-dimensional data. The package missForest is freely available from http://stat.ethz.ch/CRAN/. stekhoven@stat.math.ethz.ch; buhlmann@stat.math.ethz.ch

0 comments Cited 1394 times – based on 0 reviews      Review now

Record: found
Abstract: found
Article: found

Is Open Access

Machine learning algorithm validation with a limited sample size

Andrius Vabalas, Emma Gowen, Ellen Poliakoff … (2019)

Advances in neuroimaging, genomic, motion tracking, eye-tracking and many other technology-based data collection methods have led to a torrent of high dimensional datasets, which commonly have a small number of samples because of the intrinsic high cost of data collection involving human participants. High dimensional data with a small number of samples is of critical importance for identifying biomarkers and conducting feasibility and pilot work, however it can lead to biased machine learning (ML) performance estimates. Our review of studies which have applied ML to predict autistic from non-autistic individuals showed that small sample size is associated with higher reported classification accuracy. Thus, we have investigated whether this bias could be caused by the use of validation methods which do not sufficiently control overfitting. Our simulations show that K-fold Cross-Validation (CV) produces strongly biased performance estimates with small sample sizes, and the bias is still evident with sample size of 1000. Nested CV and train/test split approaches produce robust and unbiased performance estimates regardless of sample size. We also show that feature selection if performed on pooled training and testing data is contributing to bias considerably more than parameter tuning. In addition, the contribution to bias by data dimensionality, hyper-parameter space and number of CV folds was explored, and validation methods were compared with discriminable data. The results suggest how to design robust testing methodologies when working with small datasets and how to interpret the results of other studies based on what validation method was used.

0 comments Cited 422 times – based on 0 reviews      Review now

Record: found
Abstract: found
Article: not found

The coronary circulation in acute myocardial ischaemia/reperfusion injury: a target for cardioprotection

Derek J Hausenloy, William M. Chilian, Filippo Crea … (2019)

The coronary circulation is both culprit and victim of acute myocardial infarction. The rupture of an epicardial atherosclerotic plaque with superimposed thrombosis causes coronary occlusion, and this occlusion must be removed to induce reperfusion. However, ischaemia and reperfusion cause damage not only in cardiomyocytes but also in the coronary circulation, including microembolization of debris and release of soluble factors from the culprit lesion, impairment of endothelial integrity with subsequently increased permeability and oedema formation, platelet activation and leucocyte adherence, erythrocyte stasis, a shift from vasodilation to vasoconstriction, and ultimately structural damage to the capillaries with eventual no-reflow, microvascular obstruction (MVO), and intramyocardial haemorrhage (IMH). Therefore, the coronary circulation is a valid target for cardioprotection, beyond protection of the cardiomyocyte. Virtually all of the above deleterious endpoints have been demonstrated to be favourably influenced by one or the other mechanical or pharmacological cardioprotective intervention. However, no-reflow is still a serious complication of reperfused myocardial infarction and carries, independently from infarct size, an unfavourable prognosis. MVO and IMH can be diagnosed by modern imaging technologies, but still await an effective therapy. The current review provides an overview of strategies to protect the coronary circulation from acute myocardial ischaemia/reperfusion injury. This article is part of a Cardiovascular Research Spotlight Issue entitled ‘Cardioprotection Beyond the Cardiomyocyte’, and emerged as part of the discussions of the European Union (EU)-CARDIOPROTECTION Cooperation in Science and Technology (COST) Action, CA16225.

0 comments Cited 112 times – based on 0 reviews      Review now

All references

Author and article information

Contributors

Zhuoqi Zhang: zhuoqizhang@sina.com

Shuyan Li: lishuyan@xzhmu.edu.cn

Boming Song: boming.song@xzhmu.edu.cn

Journal

Journal ID (nlm-ta): Sci Rep

Journal ID (iso-abbrev): Sci Rep

Title: Scientific Reports

Publisher: Nature Publishing Group UK (London )

ISSN (Electronic): 2045-2322

Publication date (Electronic): 19 March 2025

Publication date PMC-release: 19 March 2025

Publication date Collection: 2025

Volume: 15

Electronic Location Identifier: 9484

Affiliations

[1 ]Information Center, Chengdu Second People’s Hospital, ( https://ror.org/02q28q956) Chengdu, 610017 China

[2 ]Department of Cardiology, Huai’an First People’s Hospital, Nanjing Medical University, ( https://ror.org/00xpfw690) Huai’an, 223300 China

[3 ]Department of Cardiology, The Affiliated Hospital of Xuzhou Medical University, ( https://ror.org/011xhcs96) Xuzhou, 221002 Jiangsu China

[4 ]The First School of Clinical Medicine, Xuzhou Medical University, ( https://ror.org/035y7a716) Xuzhou, 221002 Jiangsu China

[5 ]School of Medical Information and Engineering, Xuzhou Medical University, ( https://ror.org/035y7a716) Xuzhou, 221002 Jiangsu China

Article

Publisher ID: 94528

DOI: 10.1038/s41598-025-94528-7

PMC ID: 11923210

PubMed ID: 40108375

SO-VID: 632ffc2e-e1c2-4b9e-b439-3d31678383d2

License:

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

History

Date received : 4 December 2024

Date accepted : 14 March 2025

Funding

Funded by: The Basic Science (Natural Science) of Higher Education Institutions in Jiangsu Province

Award ID: 21KJB510026

Award Recipient : Boming Song

Custom metadata

ScienceOpen disciplines: Uncategorized

Keywords: percutaneous coronary intervention,acute myocardial infarction,microvascular obstruction,machine learning,logistic regression,cardiology,bioinformatics

Data availability:

ScienceOpen disciplines: Uncategorized

Keywords: percutaneous coronary intervention, acute myocardial infarction, microvascular obstruction, machine learning, logistic regression, cardiology, bioinformatics

Early prediction of microvascular obstruction prior to percutaneous coronary intervention

Read this article at