# From Image Interpretation to Clinical Reasoning: Upstream Physician-Context-Aware Multimodal Learning with Causal Reinforcement Learning

arXiv: https://arxiv.org/abs/2609.38924 · HTML: https://mlsanity.com/paper/2609.38924/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 25 of 25)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning](https://mlsanity.com/paper/2506.07044/) (2025)
- [NVILA: Efficient Frontier Visual Language Models](https://mlsanity.com/paper/2412.04468/) (2024)
- [ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models](https://mlsanity.com/paper/2310.10505/) (2023)
- [CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formats](https://mlsanity.com/paper/2405.19538/) (2024)
- [LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation](https://mlsanity.com/paper/2305.11490/) (2023)
- [Code as Reward: Empowering Reinforcement Learning with VLMs](https://mlsanity.com/paper/2402.04764/) (2024)
- [CXR-LLAVA: a multimodal large language model for interpreting chest X-ray images](https://mlsanity.com/paper/2310.18341/) (2023)
- [Weakly Supervised Lesion Localization With Probabilistic-CAM Pooling](https://mlsanity.com/paper/2005.14480/) (2020)
- [Chest-Diffusion: A Light-Weight Text-to-Image Model for Report-to-CXR Generation](https://mlsanity.com/paper/2407.00752/) (2024)
- [Co-Reinforcement Learning for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2505.17534/) (2025)
- [FactCheXcker: Mitigating Measurement Hallucinations in Chest X-ray Report Generation Models](https://mlsanity.com/paper/2411.18672/) (2024)
- [Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning](https://mlsanity.com/paper/2406.03234/) (2024)
- [Reducing Hallucinations of Medical Multimodal Large Language Models with Visual Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.15040/) (2025)
- [Uncovering Knowledge Gaps in Radiology Report Generation Models through Knowledge Graphs](https://mlsanity.com/paper/2408.14397/) (2024)
- [Trustworthy Medical Imaging with Large Language Models: A Study of Hallucinations Across Modalities](https://mlsanity.com/paper/2508.07031/) (2025)
- [Prompt-Guided Generation of Structured Chest X-Ray Report Using a Pre-trained LLM](https://mlsanity.com/paper/2404.11209/) (2024)
- [PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation Models](https://mlsanity.com/paper/2509.15607/) (2025)

## Abstract (arXiv)

Major adverse cardiovascular events (MACE) remain the leading cause of mortality worldwide. Opportunistic screening using routinely acquired clinical data offers a scalable approach for identifying high-risk individuals before acute events occur. Although chest X-rays (CXRs) capture latent cardiovascular biomarkers and clinical histories provide complementary patient context, existing medical vision-language models are primarily optimized for radiology interpretation rather than prognostic reasoning. We propose a causal reinforcement learning framework for multimodal clinical reasoning that integrates CXRs and physician-authored clinical histories for opportunistic MACE prediction. The framework introduces (1) a role-decoupled dual-LLM architecture that separates reasoning from risk prediction, (2) a dual-action causal reinforcement learning policy for evidence selection and reasoning optimization, and (3) causal token pruning to learn compact multimodal representations. Evaluated on an internal cohort, an emergency department cohort, and the external MIMIC dataset, the proposed framework consistently outperformed unimodal baselines and state-of-the-art medical vision-language models, achieving AUROCs of 0.720, 0.760, and 0.845, respectively. It also substantially improved reasoning quality, achieving higher GREEN scores and higher expert preference while maintaining robust predictive performance across diverse patient populations.