Interpretable Generative and Discriminative Learning for Multimodal and Incomplete Clinical Data
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915544736727040 |
|---|---|
| author | Belenguer-Llorens, Albert Sevilla-Salcedo, Carlos Mourao-Miranda, Janaina Gómez-Verdejo, Vanessa |
| author_facet | Belenguer-Llorens, Albert Sevilla-Salcedo, Carlos Mourao-Miranda, Janaina Gómez-Verdejo, Vanessa |
| contents | Real-world clinical problems are often characterized by multimodal data, usually associated with incomplete views and limited sample sizes in their cohorts, posing significant limitations for machine learning algorithms. In this work, we propose a Bayesian approach designed to efficiently handle these challenges while providing interpretable solutions. Our approach integrates (1) a generative formulation to capture cross-view relationships with a semi-supervised strategy, and (2) a discriminative task-oriented formulation to identify relevant information for specific downstream objectives. This dual generative-discriminative formulation offers both general understanding and task-specific insights; thus, it provides an automatic imputation of the missing views while enabling robust inference across different data sources. The potential of this approach becomes evident when applied to the multimodal clinical data, where our algorithm is able to capture and disentangle the complex interactions among biological, psychological, and sociodemographic modalities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09513 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Interpretable Generative and Discriminative Learning for Multimodal and Incomplete Clinical Data Belenguer-Llorens, Albert Sevilla-Salcedo, Carlos Mourao-Miranda, Janaina Gómez-Verdejo, Vanessa Machine Learning Real-world clinical problems are often characterized by multimodal data, usually associated with incomplete views and limited sample sizes in their cohorts, posing significant limitations for machine learning algorithms. In this work, we propose a Bayesian approach designed to efficiently handle these challenges while providing interpretable solutions. Our approach integrates (1) a generative formulation to capture cross-view relationships with a semi-supervised strategy, and (2) a discriminative task-oriented formulation to identify relevant information for specific downstream objectives. This dual generative-discriminative formulation offers both general understanding and task-specific insights; thus, it provides an automatic imputation of the missing views while enabling robust inference across different data sources. The potential of this approach becomes evident when applied to the multimodal clinical data, where our algorithm is able to capture and disentangle the complex interactions among biological, psychological, and sociodemographic modalities. |
| title | Interpretable Generative and Discriminative Learning for Multimodal and Incomplete Clinical Data |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.09513 |