Few-Label Multimodal Modeling of SNP Variants and ECG Phenotypes Using Large Language Models for Cardiovascular Risk Stratification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911219748700160 |
|---|---|
| author | Menon, Niranjana Arun Li, Yulong Farooq, Iqra Ahmed, Sara Awais, Muhammad Razzak, Imran |
| author_facet | Menon, Niranjana Arun Li, Yulong Farooq, Iqra Ahmed, Sara Awais, Muhammad Razzak, Imran |
| contents | Cardiovascular disease (CVD) risk stratification remains a major challenge due to its multifactorial nature and limited availability of high-quality labeled datasets. While genomic and electrophysiological data such as SNP variants and ECG phenotypes are increasingly accessible, effectively integrating these modalities in low-label settings is non-trivial. This challenge arises from the scarcity of well-annotated multimodal datasets and the high dimensionality of biological signals, which limit the effectiveness of conventional supervised models. To address this, we present a few-label multimodal framework that leverages large language models (LLMs) to combine genetic and electrophysiological information for cardiovascular risk stratification. Our approach incorporates a pseudo-label refinement strategy to adaptively distill high-confidence labels from weakly supervised predictions, enabling robust model fine-tuning with only a small set of ground-truth annotations. To enhance the interpretability, we frame the task as a Chain of Thought (CoT) reasoning problem, prompting the model to produce clinically relevant rationales alongside predictions. Experimental results demonstrate that the integration of multimodal inputs, few-label supervision, and CoT reasoning improves robustness and generalizability across diverse patient profiles. Experimental results using multimodal SNP variants and ECG-derived features demonstrated comparable performance to models trained on the full dataset, underscoring the promise of LLM-based few-label multimodal modeling for advancing personalized cardiovascular care. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16536 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Few-Label Multimodal Modeling of SNP Variants and ECG Phenotypes Using Large Language Models for Cardiovascular Risk Stratification Menon, Niranjana Arun Li, Yulong Farooq, Iqra Ahmed, Sara Awais, Muhammad Razzak, Imran Quantitative Methods Artificial Intelligence Machine Learning Cardiovascular disease (CVD) risk stratification remains a major challenge due to its multifactorial nature and limited availability of high-quality labeled datasets. While genomic and electrophysiological data such as SNP variants and ECG phenotypes are increasingly accessible, effectively integrating these modalities in low-label settings is non-trivial. This challenge arises from the scarcity of well-annotated multimodal datasets and the high dimensionality of biological signals, which limit the effectiveness of conventional supervised models. To address this, we present a few-label multimodal framework that leverages large language models (LLMs) to combine genetic and electrophysiological information for cardiovascular risk stratification. Our approach incorporates a pseudo-label refinement strategy to adaptively distill high-confidence labels from weakly supervised predictions, enabling robust model fine-tuning with only a small set of ground-truth annotations. To enhance the interpretability, we frame the task as a Chain of Thought (CoT) reasoning problem, prompting the model to produce clinically relevant rationales alongside predictions. Experimental results demonstrate that the integration of multimodal inputs, few-label supervision, and CoT reasoning improves robustness and generalizability across diverse patient profiles. Experimental results using multimodal SNP variants and ECG-derived features demonstrated comparable performance to models trained on the full dataset, underscoring the promise of LLM-based few-label multimodal modeling for advancing personalized cardiovascular care. |
| title | Few-Label Multimodal Modeling of SNP Variants and ECG Phenotypes Using Large Language Models for Cardiovascular Risk Stratification |
| topic | Quantitative Methods Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2510.16536 |