Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners

Manh Pham Hung, Aaqib Saeed, Dong Ma
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49277-49291, 2025.

Abstract

The accurate interpretation of Electrocardiogram (ECG) signals is pivotal for diagnosing cardiovascular diseases. Integrating ECG signals with accompanying textual reports further holds immense potential to enhance clinical diagnostics by combining physiological data and qualitative insights. However, this integration faces significant challenges due to inherent modality disparities and the scarcity of labeled data for robust cross-modal learning. To address these obstacles, we propose D-BETA, a novel framework that pre-trains ECG and text data using a contrastive masked auto-encoder architecture, uniquely combining generative and boosted discriminative capabilities for robust cross-modal representations. This is accomplished through masked modality modeling, specialized loss functions, and an improved negative sampling strategy tailored for cross-modal alignment. Extensive experiments on five public datasets across diverse downstream tasks demonstrate that D-BETA significantly outperforms existing methods, achieving an average AUC improvement of 15% in linear probing with only one percent of training data and 2% in zero-shot performance without requiring training data over state-of-the-art models. These results highlight the effectiveness of D-BETA, underscoring its potential to advance automated clinical diagnostics through multi-modal representations.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-pham-hung25a, title = {Boosting Masked {ECG}-Text Auto-Encoders as Discriminative Learners}, author = {Pham Hung, Manh and Saeed, Aaqib and Ma, Dong}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {49277--49291}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/pham-hung25a/pham-hung25a.pdf}, url = {https://proceedings.mlr.press/v267/pham-hung25a.html}, abstract = {The accurate interpretation of Electrocardiogram (ECG) signals is pivotal for diagnosing cardiovascular diseases. Integrating ECG signals with accompanying textual reports further holds immense potential to enhance clinical diagnostics by combining physiological data and qualitative insights. However, this integration faces significant challenges due to inherent modality disparities and the scarcity of labeled data for robust cross-modal learning. To address these obstacles, we propose D-BETA, a novel framework that pre-trains ECG and text data using a contrastive masked auto-encoder architecture, uniquely combining generative and boosted discriminative capabilities for robust cross-modal representations. This is accomplished through masked modality modeling, specialized loss functions, and an improved negative sampling strategy tailored for cross-modal alignment. Extensive experiments on five public datasets across diverse downstream tasks demonstrate that D-BETA significantly outperforms existing methods, achieving an average AUC improvement of 15% in linear probing with only one percent of training data and 2% in zero-shot performance without requiring training data over state-of-the-art models. These results highlight the effectiveness of D-BETA, underscoring its potential to advance automated clinical diagnostics through multi-modal representations.} }
Endnote
%0 Conference Paper %T Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners %A Manh Pham Hung %A Aaqib Saeed %A Dong Ma %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-pham-hung25a %I PMLR %P 49277--49291 %U https://proceedings.mlr.press/v267/pham-hung25a.html %V 267 %X The accurate interpretation of Electrocardiogram (ECG) signals is pivotal for diagnosing cardiovascular diseases. Integrating ECG signals with accompanying textual reports further holds immense potential to enhance clinical diagnostics by combining physiological data and qualitative insights. However, this integration faces significant challenges due to inherent modality disparities and the scarcity of labeled data for robust cross-modal learning. To address these obstacles, we propose D-BETA, a novel framework that pre-trains ECG and text data using a contrastive masked auto-encoder architecture, uniquely combining generative and boosted discriminative capabilities for robust cross-modal representations. This is accomplished through masked modality modeling, specialized loss functions, and an improved negative sampling strategy tailored for cross-modal alignment. Extensive experiments on five public datasets across diverse downstream tasks demonstrate that D-BETA significantly outperforms existing methods, achieving an average AUC improvement of 15% in linear probing with only one percent of training data and 2% in zero-shot performance without requiring training data over state-of-the-art models. These results highlight the effectiveness of D-BETA, underscoring its potential to advance automated clinical diagnostics through multi-modal representations.
APA
Pham Hung, M., Saeed, A. & Ma, D.. (2025). Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:49277-49291 Available from https://proceedings.mlr.press/v267/pham-hung25a.html.

Related Material