DAFTED: Decoupled Asymmetric Fusion of Tabular and Echocardiographic Data for Cardiac Hypertension Diagnosis

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Stym-Popper, Jérémie, Painchaud, Nathan, Rambour, Clément, Courand, Pierre-Yves, Thome, Nicolas, Bernard, Olivier
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908547813474304
author Stym-Popper, Jérémie
Painchaud, Nathan
Rambour, Clément
Courand, Pierre-Yves
Thome, Nicolas
Bernard, Olivier
author_facet Stym-Popper, Jérémie
Painchaud, Nathan
Rambour, Clément
Courand, Pierre-Yves
Thome, Nicolas
Bernard, Olivier
contents Multimodal data fusion is a key approach for enhancing diagnosis in medical applications. We propose an asymmetric fusion strategy starting from a primary modality and integrating secondary modalities by disentangling shared and modality-specific information. Validated on a dataset of 239 patients with echocardiographic time series and tabular records, our model outperforms existing methods, achieving an AUC over 90%. This improvement marks a crucial benchmark for clinical use.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15990
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DAFTED: Decoupled Asymmetric Fusion of Tabular and Echocardiographic Data for Cardiac Hypertension Diagnosis
Stym-Popper, Jérémie
Painchaud, Nathan
Rambour, Clément
Courand, Pierre-Yves
Thome, Nicolas
Bernard, Olivier
Computer Vision and Pattern Recognition
Multimodal data fusion is a key approach for enhancing diagnosis in medical applications. We propose an asymmetric fusion strategy starting from a primary modality and integrating secondary modalities by disentangling shared and modality-specific information. Validated on a dataset of 239 patients with echocardiographic time series and tabular records, our model outperforms existing methods, achieving an AUC over 90%. This improvement marks a crucial benchmark for clinical use.
title DAFTED: Decoupled Asymmetric Fusion of Tabular and Echocardiographic Data for Cardiac Hypertension Diagnosis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.15990