Enhancing Cardiovascular Disease Prediction through Multi-Modal Self-Supervised Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Girlanda, Francesco, Demler, Olga, Menze, Bjoern, Davoudi, Neda
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929585735598080
author Girlanda, Francesco
Demler, Olga
Menze, Bjoern
Davoudi, Neda
author_facet Girlanda, Francesco
Demler, Olga
Menze, Bjoern
Davoudi, Neda
contents Accurate prediction of cardiovascular diseases remains imperative for early diagnosis and intervention, necessitating robust and precise predictive models. Recently, there has been a growing interest in multi-modal learning for uncovering novel insights not available through uni-modal datasets alone. By combining cardiac magnetic resonance images, electrocardiogram signals, and available medical information, our approach enables the capture of holistic status about individuals' cardiovascular health by leveraging shared information across modalities. Integrating information from multiple modalities and benefiting from self-supervised learning techniques, our model provides a comprehensive framework for enhancing cardiovascular disease prediction with limited annotated datasets. We employ a masked autoencoder to pre-train the electrocardiogram ECG encoder, enabling it to extract relevant features from raw electrocardiogram data, and an image encoder to extract relevant features from cardiac magnetic resonance images. Subsequently, we utilize a multi-modal contrastive learning objective to transfer knowledge from expensive and complex modality, cardiac magnetic resonance image, to cheap and simple modalities such as electrocardiograms and medical information. Finally, we fine-tuned the pre-trained encoders on specific predictive tasks, such as myocardial infarction. Our proposed method enhanced the image information by leveraging different available modalities and outperformed the supervised approach by 7.6% in balanced accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2411_05900
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Cardiovascular Disease Prediction through Multi-Modal Self-Supervised Learning
Girlanda, Francesco
Demler, Olga
Menze, Bjoern
Davoudi, Neda
Computer Vision and Pattern Recognition
Machine Learning
Accurate prediction of cardiovascular diseases remains imperative for early diagnosis and intervention, necessitating robust and precise predictive models. Recently, there has been a growing interest in multi-modal learning for uncovering novel insights not available through uni-modal datasets alone. By combining cardiac magnetic resonance images, electrocardiogram signals, and available medical information, our approach enables the capture of holistic status about individuals' cardiovascular health by leveraging shared information across modalities. Integrating information from multiple modalities and benefiting from self-supervised learning techniques, our model provides a comprehensive framework for enhancing cardiovascular disease prediction with limited annotated datasets. We employ a masked autoencoder to pre-train the electrocardiogram ECG encoder, enabling it to extract relevant features from raw electrocardiogram data, and an image encoder to extract relevant features from cardiac magnetic resonance images. Subsequently, we utilize a multi-modal contrastive learning objective to transfer knowledge from expensive and complex modality, cardiac magnetic resonance image, to cheap and simple modalities such as electrocardiograms and medical information. Finally, we fine-tuned the pre-trained encoders on specific predictive tasks, such as myocardial infarction. Our proposed method enhanced the image information by leveraging different available modalities and outperformed the supervised approach by 7.6% in balanced accuracy.
title Enhancing Cardiovascular Disease Prediction through Multi-Modal Self-Supervised Learning
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2411.05900