Evaluation of Medical Vision Language Models HuluMed and MedGemma, and general purpose chatbots Gemma 3, ChatGPT Plus, and Claude Pro on real previously unseen wound images
Authors: Yunzhe Xue, Mohammed Saim Ahmed Quadri, Neal Panse, Justin W. Ady, Usman Roshan
Organizations: Department of Data Science, New Jersey Institute of Technology, Newark, NJ, USA · Department of Computer Science, New Jersey Institute of Technology, Newark, NJ, USA · Vascular and Endovascular Surgery, Robert Wood Johnson Hospital, New Brunswick, NJ, USA
Chronic wound assessment remains a clinically challenging task that requires accurate interpretation of wound morphology, tissue composition, vascular characteristics, and infection risk. Recent advances in Vision-Language Models (VLMs) have introduced the possibility of automated multimodal wound analysis through image understanding combined with clinical reasoning. This study evaluates the performance of several general-purpose and medically specialized open-source and proprietary VLMs for clinical wound assessment using an expanded, curated dataset of 20 clinically diverse wounds spanning vascular, surgical, ischemic, venous, lymphedema, and amputation-related etiologies. Six VLMs were evaluated using a structured twelve-question clinical framework covering wound classification, infection risk, vascular intervention recommendations, debridement urgency, wound therapy selection, and advanced management planning. Across 20 wound cases and 240 clinician-graded wound-analysis decisions, ChatGPT achieved the highest overall performance with 174/240 correct responses (72.50%), followed by Claude with 149/240 (62.08%). Among the open-source and medically specialized models, HuluMed achieved the strongest performance with 96/240 correct responses (40.00%), followed by Gemma 3 (81/240, 33.75%), MedGemma 4B (62/240, 25.83%), and MedGemma 27B (42/240, 17.50%). The findings suggest that frontier general-purpose multimodal systems currently demonstrate substantially stronger wound-analysis performance than medically specialized alternatives, highlighting the continued importance of broad multimodal reasoning capabilities alongside domain-specific medical knowledge. Although current VLMs demonstrate promising potential for clinical decision support, substantial limitations remain in advanced wound-management reasoning, procedural planning, and autonomous clinical reliability.
Assessing chronic wound infection from photographs is challenging because visual appearance varies across wound etiologies, anatomical locations, and imaging conditions. Prior image-based deep learning methods have mainly focused on classification with limited interpretability, despite the need for evidence-grounded explanations to support point-of-care decision making. We present Infection-Reasoner, a compact 4B-parameter reasoning vision-language model for chronic wound infection classification and rationale generation. To address the scarcity of expert-labeled wound images with reasoning annotations, Infection-Reasoner is trained using a two-stage pipeline: (1) reasoning distillation, in which GPT-5.1 generates chain-of-thought rationales for unlabeled wound images to initialize wound-specific reasoning in a smaller student model (Qwen3-VL-4B-Thinking), and (2) reinforcement learning post-training with Group Relative Policy Optimization on a small labeled infection dataset to refine classification reasoning. On a held-out heterogeneous wound dataset, Infection-Reasoner achieved 86.8% accuracy, 86.4% sensitivity, and 87.1% specificity, outperforming several strong baselines, including GPT-5.1. Rationale quality was further evaluated using both multimodal large language model (MLLM) judges and wound expert review. Across four MLLM judges, visual-support agreement scores ranged from 0.722 to 0.903, while expert review rated 61.8% of rationales as Correct and 32.4% as Partially Correct.
Wound image classification is often treated as a task-specific supervised learning problem, requiring substantial amounts of manually labelled data and retraining when the label space or deployment setting changes. This study evaluated whether small multimodal language models (SMLMs) can provide a training-free alternative for wound classification through retrieval-based in-context learning (ICL). Experiments used two public wound-image datasets: the Kaggle wound dataset (1469 images, 10 classes) and the Medetec dataset (560 images, 9 classes). Eleven SMLMs from the Qwen 3.5, Ministral 3, and Gemma 4 families were evaluated under zero-shot prompting and few-shot prompting with random support examples, embedding-based k-nearest-neighbour (kNN) retrieval, and kNN retrieval followed by maximal marginal relevance reranking (MMR). Retrieval-only weighted-kNN controls, support-set reduction experiments, and support-context size sweeps were used to assess the effects of retrieval, model scale, and prompt length. Query-conditioned ICL consistently outperformed zero-shot and random few-shot prompting. On the Kaggle dataset, the best result was achieved by Qwen 3.5 27B with kNN+MMR, reaching 0.872 accuracy and 0.871 F1 score. On Medetec, Qwen 3.5 27B with kNN+MMR reached 0.678 accuracy and 0.670 F1. Larger models exceeded matched weighted-kNN controls, indicating use of retrieved examples beyond nearest-neighbour voting. Retrieval-based ICL degraded modestly under support-set reduction, and most gains saturated with 8-10 support images. Retrieval-based ICL allows SMLMs to perform adaptable wound image classification without task-specific retraining. Compact retrieved contexts may support practical and privacy-conscious deployment, although performance remains dependent on model scale, retrieval strategy, and dataset difficulty.
High-stakes clinical use of large vision-language models (LVLMs) requires reasoning that is grounded in visual evidence and clinical knowledge, not just correct final answers. We introduce OpenMedReason, a large-scale, open multimodal medical reasoning corpus comprising approximately 450K image-question-answer instances whose reasoning traces are primarily derived from curated biomedical, human-authored scientific articles. OpenMedReason provides high-fidelity supervision beyond synthetic chains of thought, covering diverse medical domain vision modalities such as radiological scans, microscopic images, visible light photographs, charts, and others. We complement it with OpenMedReason-Bench, a held-out benchmark that allows fine-grained evaluation of LVLMs along three complementary axes of capability, including perception, medical knowledge, and rationale, enabling diagnostic evaluation beyond final-answer accuracy. OpenMedReason is a rich training resource that exhibits its effectiveness in both supervised fine-tuning (SFT) and reinforcement-based alignment. Training with OpenMedReason yields a 20% average improvement in VQA accuracy over the base model and achieves performance within 4.2% of the strongest comparable-scale medical LVLMs. Fine-grained performance analysis confirms that the gains are not concentrated in any single axis: OpenMedReason improves perception, medical knowledge, and rationale jointly, and its reasoning traces are preferred over those of the base model in 86.1% of pairwise comparisons. We release the code and dataset at huggingface.co/datasets/neginb/OpenMedReason.
Negin Baghbanzadeh, Pritam Sarkar, Michael Colacci +6