PuSH - Publication Server of Helmholtz Zentrum München: Prediction of myocardial infarction using a combined generative adversarial network model and feature-enhanced loss function.

Navigation

Home

Deutsch

Research

Advanced Search

Browse by ...

... Journal

... Publication Type

... Research Data

... Publication Year

Publication overview

Support & Contact

Contact persons

Help

Data protection

Yu, S. ; Han, S. ; Shi, M. ; Harada, M. ; Ge, J. ; Li, X.* ; Cai, X.* ; Heier, M. ; Kastenmüller, G. ; Suhre, K.* ; Gieger, C. ; Koenig, W.* ; Rathmann, W.* ; Peters, A. ; Wang-Sattler, R.

Prediction of myocardial infarction using a combined generative adversarial network model and feature-enhanced loss function.

Metabolites 14:258 (2024)

Publ. Version/Full Text

DOI

PMC

	Open Access Gold

Abstract
Metrics
Extra information

Accurate risk prediction for myocardial infarction (MI) is crucial for preventive strategies, given its significant impact on global mortality and morbidity. Here, we propose a novel deep-learning approach to enhance the prediction of incident MI cases by incorporating metabolomics alongside clinical risk factors. We utilized data from the KORA cohort, including the baseline S4 and follow-up F4 studies, consisting of 1454 participants without prior history of MI. The dataset comprised 19 clinical variables and 363 metabolites. Due to the imbalanced nature of the dataset (78 observed MI cases and 1376 non-MI individuals), we employed a generative adversarial network (GAN) model to generate new incident cases, augmenting the dataset and improving feature representation. To predict MI, we further utilized multi-layer perceptron (MLP) models in conjunction with the synthetic minority oversampling technique (SMOTE) and edited nearest neighbor (ENN) methods to address overfitting and underfitting issues, particularly when dealing with imbalanced datasets. To enhance prediction accuracy, we propose a novel GAN for feature-enhanced (GFE) loss function. The GFE loss function resulted in an approximate 2% improvement in prediction accuracy, yielding a final accuracy of 70%. Furthermore, we evaluated the contribution of each clinical variable and metabolite to the predictive model and identified the 10 most significant variables, including glucose tolerance, sex, and physical activity. This is the first study to construct a deep-learning approach for producing 7-year MI predictions using the newly proposed loss function. Our findings demonstrate the promising potential of our technique in identifying novel biomarkers for MI prediction.

Altmetric

Additional Metrics?

[➜Log in]

Edit extra informations Login

Publication type Article: Journal article

Document type Scientific Article

Corresponding Author

Keywords Gan For Feature-enhanced ; Gfe Loss Function ; Feature Enhancement ; Generative Adversarial Networks ; Limited And Imbalanced Incident Cases ; Myocardial Infarction ; Prediction; Population; Disease; Risk; Outcomes; Profile; Kora

ISSN (print) / ISBN 2218-1989

e-ISSN 2218-1989

Journal Metabolites

Quellenangaben Volume: 14, Issue: 5, Article Number: 258

Publisher MDPI

Publishing Place St Alban-anlage 66, Ch-4052 Basel, Switzerland

Non-patent literature Publications

Reviewing status Peer reviewed

Institute(s) Institute of Translational Genomics (ITG)
Institute of Epidemiology II (EPI2)
Institute of Computational Biology (ICB)

Grants Innovative Medicines Initiative 2 Joint Undertaking (JU)