Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2506.14986 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908411492302848 |
|---|---|
| author | Usdin, Maxime Kriara, Lito Craveiro, Licinio |
| author_facet | Usdin, Maxime Kriara, Lito Craveiro, Licinio |
| contents | Early multiple sclerosis (MS) disability progression prediction is challenging due to disease heterogeneity. This work predicts 48- and 72-week disability using sparse baseline clinical data and 12 weeks of daily digital Floodlight data from the CONSONANCE clinical trial. We employed state-of-the-art tabular and time-series foundation models (FMs), a custom multimodal attention-based transformer, and machine learning methods. Despite the difficulty of early prediction (AUROC 0.63), integrating digital data via advanced models improved performance over clinical data alone. A transformer model using unimodal embeddings from the Moment FM yielded the best result, but our multimodal transformer consistently outperformed its unimodal counterpart, confirming the advantages of combining clinical with digital data. Our findings demonstrate the promise of FMs and multimodal approaches to extract predictive signals from complex and diverse clinical and digital life sciences data (e.g., imaging, omics), enabling more accurate prognostics for MS and potentially other complex diseases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_14986 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Early Prediction of Multiple Sclerosis Disability Progression via Multimodal Foundation Model Benchmarks Usdin, Maxime Kriara, Lito Craveiro, Licinio Machine Learning Early multiple sclerosis (MS) disability progression prediction is challenging due to disease heterogeneity. This work predicts 48- and 72-week disability using sparse baseline clinical data and 12 weeks of daily digital Floodlight data from the CONSONANCE clinical trial. We employed state-of-the-art tabular and time-series foundation models (FMs), a custom multimodal attention-based transformer, and machine learning methods. Despite the difficulty of early prediction (AUROC 0.63), integrating digital data via advanced models improved performance over clinical data alone. A transformer model using unimodal embeddings from the Moment FM yielded the best result, but our multimodal transformer consistently outperformed its unimodal counterpart, confirming the advantages of combining clinical with digital data. Our findings demonstrate the promise of FMs and multimodal approaches to extract predictive signals from complex and diverse clinical and digital life sciences data (e.g., imaging, omics), enabling more accurate prognostics for MS and potentially other complex diseases. |
| title | Early Prediction of Multiple Sclerosis Disability Progression via Multimodal Foundation Model Benchmarks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2506.14986 |