ViSTA: A Simple Bridge Extends Visual Alignment to Clinical Time-Series Understanding in Multimodal LLMs
On the map: Multimodal LLMs / vision-language models → Medical vision-language models
Abstract (arXiv)
Clinical prediction models estimate risk from patient measurements, while large language models support medical text understanding and question answering. Yet their language capabilities do not ensure accurate prediction from structured, high-dimensional clinical time series. Improving this ability would connect risk estimation with flexible questions about a patient's evolving condition. We introduce ViSTA, a compact adapter that incorporates irregular numerical measurements into a pretrained vision-language model's chart representations. It learns corrections to visual tokens while leaving all pretrained parameters unchanged. On MIMIC-IV, ViSTA has the highest mean scores among the compared adaptations on all four metrics for acute kidney injury and mortality prediction across models with 2-9 billion parameters. With 0.516 million trainable parameters, the 2-billion-parameter model reaches an area under the ROC curve of 0.7376 for acute kidney injury, compared with GPT-5.6 Sol's 0.7380 with text input and high reasoning effort. Training for temporal question answering yields 69.27% accuracy at 4 billion parameters with over 90% fewer trainable parameters than low-rank adaptation using charts or numerical text, at a 2.82-4.88 percentage-point accuracy gap. ViSTA extends pretrained language models to numerical prediction and temporal questions.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 18 of its 28 references that are in the map. First posted on arXiv 25 Sep 2026.
Builds on
18 of 28 references.
References · 18
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
- 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
- 2022Large Language Models Encode Clinical Knowledgecited by 1,807
- 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
- 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
- 2023Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarizationcited by 244
- 2025Time-MQA: Time Series Multi-Task Question Answering with Context Enhancementcited by 74
- 2019ConCare: Personalized Clinical Feature Embedding via Capturing the Healthcare Contextcited by 56
- 2024Scaling Laws for Forgetting When Fine-Tuning Large Language Modelscited by 36
- 2025ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Datasetcited by 35
- 2024ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaborationcited by 23
- 2024ClinicRealm: Re-evaluating Large Language Models with Conventional Machine Learning for Non-Generative Clinical Prediction Taskscited by 8
6 more
- 2025From Images to Signals: Are Large Vision Models Useful for Time Series Analysis?cited by 7
- 2025CaTS-Bench: Can Language Models Describe Time Series?cited by 7
- 2023VITA: 'Carefully Chosen and Weighted Less' Is Better in Medication Recommendationcited by 6
- 2025MLLM4TS: Leveraging Vision and Multimodal Language Models for General Time-Series Analysiscited by 4
- 2026CLIR-Bench: Benchmarking Multimodal Question Answering over Irregular Clinical Time Seriescited by 4
- 2026Augmenting Clinical Decision-Making with an Interactive and Interpretable AI Copilot: A Real-World User Study with Clinicians in Nephrology and Obstetricscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Large Language Models as Unified Multimodal Learners for Clinical Prediction
- 2026A Cost-Effective Multimodal LLM Reasoning Framework for Question Answering over Irregular Clinical Time Series
- 2026MMTClinic: Multimodal, Multilingual Time Series Question Answering and Reasoning Benchmark for Clinical Domain
- 2026From Hazard Functions to Language Space: Cox-Supervised Distillation of Survival Risk into a Large Language Model
- 2024The Limited Impact of Medical Adaptation of Large Language and Vision-Language Models
- 2025Multimodal Retrieval-Augmented Generation with Large Language Models for Medical VQA
- 2025Knowing or Guessing? Robust Medical Visual Question Answering via Joint Consistency and Contrastive Learning
- 2026M2G-LLM: Enhancing Clinical Prediction via Multimodal Graph Reasoning and LLM Context Injection