LGAICLJun 7, 2024

MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learning

arXiv:2406.06620v412 citationsHas Code
Originality Incremental advance
AI Analysis

This addresses the problem of modality bias in medical AI for improved diagnostic accuracy, though it is incremental as it builds on existing adapter-based methods.

The paper tackles the bias in existing medical time series-text multimodal learning by proposing a novel textual-temporal paradigm that allows either modality to be primary, resulting in MedualTime, which achieves 8% accuracy and 12% F1 improvements in supervised settings.

The recent rapid advancements in language models (LMs) have garnered attention in medical time series-text multimodal learning. However, existing contrastive learning-based and prompt-based LM approaches tend to be biased, often assigning a primary role to time series modality while treating text modality as secondary. We classify these approaches under a temporal-primary paradigm, which may overlook the unique and critical task-relevant information embedded in text modality like clinical reports, thus failing to fully leverage mutual benefits and complementarity of different modalities. To fill this gap, we propose a novel textual-temporal multimodal learning paradigm that enables either modality to serve as the primary while being enhanced by the other, thereby effectively capturing modality-specific information and fostering cross-modal interaction. In specific, we design MedualTime, a language model composed of dual adapters to implement temporal-primary and textual-primary modeling simultaneously. Within each adapter, lightweight adaptation tokens are injected into the top layers of LM to encourage high-level modality fusion. The shared LM pipeline by dual adapters not only achieves adapter alignment but also enables efficient fine-tuning, reducing computational resources. Empirically, MedualTime demonstrates superior performance on medical data, achieving notable improvements of 8% accuracy and 12% F1 in supervised settings. Furthermore, MedualTime's transferability is validated by few-shot label transfer experiments from coarse-grained to fine-grained medical data. https://github.com/start2020/MedualTime

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes