Is Clinical Text Enough? A Multimodal Study on Mortality Prediction in Heart Failure Patients
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917380240703488 |
|---|---|
| author | Khettari, Oumaima El Barthet, Virgile Hocquet, Guillaume Weller, Joconde Morin, Emmanuel Zweigenbaum, Pierre |
| author_facet | Khettari, Oumaima El Barthet, Virgile Hocquet, Guillaume Weller, Joconde Morin, Emmanuel Zweigenbaum, Pierre |
| contents | Accurate short-term mortality prediction in heart failure (HF) remains challenging, particularly when relying on structured electronic health record (EHR) data alone. We evaluate transformer-based models on a French HF cohort, comparing text-only, structured-only, multimodal, and LLM-based approaches. Our results show that enriching clinical text with entity-level representations improves prediction over CLS embeddings alone, and that supervised multimodal fusion of text and structured variables achieves the best overall performance. In contrast, large language models perform inconsistently across modalities and decoding strategies, with text-only prompts outperforming structured or multimodal inputs. These findings highlight that entity-aware multimodal transformers offer the most reliable solution for short-term HF outcome prediction, while current LLM prompting remains limited for clinical decision support. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_01924 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Is Clinical Text Enough? A Multimodal Study on Mortality Prediction in Heart Failure Patients Khettari, Oumaima El Barthet, Virgile Hocquet, Guillaume Weller, Joconde Morin, Emmanuel Zweigenbaum, Pierre Computation and Language Accurate short-term mortality prediction in heart failure (HF) remains challenging, particularly when relying on structured electronic health record (EHR) data alone. We evaluate transformer-based models on a French HF cohort, comparing text-only, structured-only, multimodal, and LLM-based approaches. Our results show that enriching clinical text with entity-level representations improves prediction over CLS embeddings alone, and that supervised multimodal fusion of text and structured variables achieves the best overall performance. In contrast, large language models perform inconsistently across modalities and decoding strategies, with text-only prompts outperforming structured or multimodal inputs. These findings highlight that entity-aware multimodal transformers offer the most reliable solution for short-term HF outcome prediction, while current LLM prompting remains limited for clinical decision support. |
| title | Is Clinical Text Enough? A Multimodal Study on Mortality Prediction in Heart Failure Patients |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.01924 |