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.

Infections in Diabetic Foot Ulcers (DFUs) can cause severe complications, including tissue death and limb amputation, highlighting the need for accurate, timely diagnosis. Previous machine learning methods have focused on identifying infections by analyzing wound images alone, without utilizing additional metadata such as medical notes. In this study, we aim to improve infection detection by introducing Synthetic Caption Augmented Retrieval for Wound Infection Detection (SCARWID), a novel deep learning framework that leverages synthetic textual descriptions to augment DFU images. SCARWID consists of two components: (1) Wound-BLIP, a Vision-Language Model (VLM) fine-tuned on GPT-4o-generated descriptions to synthesize consistent captions from images; and (2) an Image-Text Fusion module that uses cross-attention to extract cross-modal embeddings from an image and its corresponding Wound-BLIP caption. Infection status is determined by retrieving the top-k similar items from a labeled support set. To enhance the diversity of training data, we utilized a latent diffusion model to generate additional wound images. As a result, SCARWID outperformed state-of-the-art models, achieving average sensitivity, specificity, and accuracy of 0.85, 0.78, and 0.81, respectively, for wound infection classification. Displaying the generated captions alongside the wound images and infection detection results enhances interpretability and trust, enabling nurses to align SCARWID outputs with their medical knowledge. This is particularly valuable when wound notes are unavailable or when assisting novice nurses who may find it difficult to identify visual attributes of wound infection.

The pressing need for objective measures in evaluating chronic pain in research and practice highlights the role that neuro information systems (NeuroIS) research plays in designing smart clinical decision support systems. A first step in such a research agenda involves identifying practical stimuli-task paradigms that can reliably detect chronic pain from physiological measures such as eye movements. In this study, we propose and test a new stimuli-task paradigm. Our results show that our proposed stimuli-task paradigm can detect differences in the information-processing behavior of people with and without chronic pain. The results also show that our proposed stimuli-task paradigm can reliably predict self-reported subjective pain experience from eye movements. These findings provide support for our proposed stimuli-task paradigm. They also show that the eye-tracking variables that we selected to test our proposed paradigm are effective in capturing the impact of chronic pain on visual attention, suggesting that eye movements have the potential to serve as reliable biomarkers of chronic pain. Hence, our results support the potential for eye movements to aid in efforts to develop smart information systems that can detect the presence and/or the severity of chronic pain from an individual's ocular behavior.

Chronic wounds affect 8.5 million Americans, particularly the elderly and patients with diabetes. These wounds can take up to nine months to heal, making regular care essential to ensure healing and prevent severe outcomes like limb amputations. Many patients receive care at home from visiting nurses with varying levels of wound expertise, leading to inconsistent care. Problematic, non-healing wounds should be referred to wound specialists, but referral decisions in non-clinical settings are often erroneous, delayed, or unnecessary. This paper introduces the Deep Multimodal Wound Assessment Tool (DM-WAT), a machine learning framework designed to assist visiting nurses in deciding whether to refer chronic wound patients. DM-WAT analyzes smartphone-captured wound images and clinical notes from Electronic Health Records (EHRs). It uses DeiT-Base-Distilled, a Vision Transformer (ViT), to extract visual features from images and DeBERTa-base to extract text features from clinical notes. DM-WAT combines visual and text features using an intermediate fusion approach. To address challenges posed by a small and imbalanced dataset, it integrates image and text augmentation with transfer learning to achieve high performance. In evaluations, DM-WAT achieved 77 F1 score, outperforming prior approaches. Score-CAM and Captum interpretation algorithms provide insights into specific parts of image and text inputs that influence recommendations, enhancing interpretability and trust.

Pressure ulcers (PUs) are a serious and prevalent healthcare concern. Accurate classification of PU severity (Stages I-IV) is essential for proper treatment but remains challenging due to subtle visual distinctions and subjective interpretation, leading to variability among clinicians. Prior AI-based approaches using Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) achieved promising accuracy but offered limited interpretability. We present FT-ARM (Fine-Tuned Agentic Reflection Multimodal model), a fine-tuned multimodal large language model (MLLM) with an agentic self-reflection mechanism for pressure ulcer severity classification. Inspired by clinician-style diagnostic reassessment, FT-ARM iteratively refines its predictions by reasoning over visual features and encoded clinical knowledge from text, enhancing both accuracy and consistency. On the publicly available Pressure Injury Image Dataset (PIID), FT-ARM, fine-tuned from LLaMA 3.2 90B, achieved 85

Smart clinician support systems using biomarkers such as patients' eye movements can significantly enhance the assessment of chronic pain which traditionally relies on subjective self-reports. This exploratory study expands research on eye-movement data as a potential biomarker for chronic pain assessment by investigating two relevant eye-movement metrics that have not been considered by the chronic pain literature: Fixation Inner Density (FID) and baseline-corrected Pupil Diameter (PD). Data was collected from participants with and without chronic pain as they answered pain-related surveys. Our results suggest that FID and PD can provide objective insights into attentional biases related to chronic pain, offering promising avenues for developing smart Clinician Decision Support Systems (CDSS) that use biomarkers to enhance pain assessment and management. Future research will focus on validating these preliminary results with larger sample sizes and exploring the scalability of these metrics for clinical applications.

Chronic wounds affect 8.5 million Americans, especially the elderly and patients with diabetes. As regular care is critical for proper healing, many patients receive care in their homes from visiting nurses and caregivers with variable wound expertise. Problematic, non-healing wounds should be referred to experts in wound clinics to avoid adverse outcomes such as limb amputations. Unfortunately, due to the lack of wound expertise, referral decisions made in non-clinical settings can be erroneous, delayed or unnecessary. This paper proposes the Deep Multimodal Wound Assessment Tool (DM-WAT), a novel machine learning framework to support visiting nurses by recommending wound referral decisions from smartphone-captured wound images and associated clinical notes. DM-WAT extracts visual features from wound images using DeiT-Base-Distilled, a Vision Transformer (ViT) architecture. Distillation-based training facilitates representation learning and knowledge transfer from a larger teacher model to DeiT-Base, enabling robust performance on our small wound image dataset of 205 wound images. DM-WAT extracts text features from clinical notes using DeBERTa-base, which comprehends context by disentangling content and position information from clinical notes. Visual and text features are combined using an intermediate fusion approach. To overcome the challenges posed by a small and imbalanced dataset, DM-WAT integrates image and text augmentation along with transfer learning via pre-trained feature extractors to achieve high performance. In rigorous evaluation, DM-WAT achieved an accuracy of 77% [Formula: see text]% and an F1 score of 70% [Formula: see text]%, outperforming the prior state of the art and all baseline single-modality and multimodal approaches. Additionally, to interpret DM-WAT's recommendations, the Score-CAM and Captum interpretation algorithms provided insights into the specific parts of the image and text inputs that the model focused on during decision-making.

Goal: Augment a small, imbalanced, wound dataset by using semi-supervised learning with a secondary dataset. Then utilize the augmented wound dataset for deep learning-based wound assessment. Methods: The clinically-validated Photographic Wound Assessment Tool (PWAT) scores eight wound attributes: Size, Depth, Necrotic Tissue Type, Necrotic Tissue Amount, Granulation Tissue type, Granulation Tissue Amount, Edges, Periulcer Skin Viability to comprehensively assess chronic wound images. A small corpus of 1639 wound images labeled with ground truth PWAT scores was used as reference. A Semi-Supervised learning and Progressive Multi-Granularity training mechanism were used to leverage a secondary corpus of 9870 unlabeled wound images. Wound scoring utilized the EfficientNet Convolutional Neural Network on the augmented wound corpus. Results: Our proposed Semi-Supervised PMG EfficientNet (SS-PMG-EfficientNet) approach estimated all 8 PWAT sub-scores with classification accuracies and F1 scores of about 90% on average, and outperformed a comprehensive list of baseline models and had a 7% improvement over the prior state-of-the-art (without data augmentation). We also demonstrate that synthetic wound image generation using Generative Adversarial Networks (GANs) did not improve wound assessment. Conclusions: Semi-supervised learning on unlabeled wound images in a secondary dataset achieved impressive performance for deep learning-based wound grading.

Goal: To accurately detect infections in Diabetic Foot Ulcers (DFUs) using photographs taken at the Point of Care (POC). Achieving high performance is critical for preventing complications and amputations, as well as minimizing unnecessary emergency department visits and referrals. Methods: This paper proposes the Guided Conditional Diffusion Classifier (ConDiff). This novel deep-learning framework combines guided image synthesis with a denoising diffusion model and distance-based classification. The process involves (1) generating guided conditional synthetic images by injecting Gaussian noise to a guide (input) image, followed by denoising the noise-perturbed image through a reverse diffusion process, conditioned on infection status and (2) classifying infections based on the minimum Euclidean distance between synthesized images and the original guide image in embedding space. Results: ConDiff demonstrated superior performance with an average accuracy of 81% that outperformed state-of-the-art (SOTA) models by at least 3%. It also achieved the highest sensitivity of 85.4%, which is crucial in clinical domains while significantly improving specificity to 74.4%, surpassing the best SOTA model. Conclusions : ConDiff not only improves the diagnosis of DFU infections but also pioneers the use of generative discriminative models for detailed medical image analysis, offering a promising approach for improving patient outcomes.

This article employs design ethnography to study the design process of a design science research (DSR) project conducted over eight years. The DSR project focuses on chronic wounds and how Information Technology (IT) might support the management of those wounds. Since this is a new and complex problem not previously addressed by IT, it requires an exploration and discovery process. As such, we found that traditional DSR methodologies were not well-suited to guiding the design process. Instead we discovered that focusing on search, and in particular, the coevolution of the problem and solution spaces, provides a much better focus for managing the DSR design process. The presentation of our findings from the ethnographic study includes a new representation for capturing the coevolving problem/solution spaces, an illustration of the search process and coevolving problem/solution spaces using the DSR project we studied, the need for changes in the purpose of DSR evaluation activities when using a search-focused design process, and how our proposed process extends and augments current DSR methodologies. Studying the DSR design process generates the knowledge that research project managers need for managing and guiding a DSR project, and contributes to our knowledge of the design process for research-oriented projects.

: The pressing need for objective measures in evaluating chronic pain in research and practice highlights the role that neuro information systems (NeuroIS) research plays in designing smart clinical decision support systems. A first step in such a research agenda involves identifying practical stimuli-task paradigms that can reliably detect chronic pain from physiological measures such as eye movements. In this study, we propose and test a new stimuli-task paradigm. Our results show that our proposed stimuli-task paradigm can detect differences in the information-processing behavior of people with and without chronic pain. The results also show that our proposed stimuli-task paradigm can reliably predict self-reported subjective pain experience from eye movements. These findings provide support for our proposed stimuli-task paradigm. They also show that the eye-tracking variables that we selected to test our proposed paradigm are effective in capturing the impact of chronic pain on visual attention, suggesting that eye movements have the potential to serve as reliable biomarkers of chronic pain. Hence, our results support the potential for eye movements to aid in efforts to develop smart information systems that can detect the presence and/or the severity of chronic pain from an individual’s ocular behavior.

Automatic assessment of wounds using smartphones can facilitate the tracking of healing progress outside the clinic. Prior work proposed SS-PMG-EfficientNets, a state-of-the-art, multi-scale, convolutional neural network architecture for accurate wound assessment. However, the model was previously only trained and evaluated on high-quality wound images captured in controlled environments. This study systematically evaluated the effects of low-quality images on SS-PMG-EfficientNets, finding that the model's performance and consistency are reduced when input wound images are blurry or captured in adverse lighting (too bright or too dark), two factors previously identified as the most prevalent issues in crowdsourced images. Specifically, SS-PMG-EfficientNet was first trained on three high-quality wound datasets containing images labeled with Photographic Wound Assessment Tool (PWAT) wound healing scores, stages of pressure injury wounds, and wound types, respectively. The model was then evaluated on a test wound dataset that was augmented with real-world image luminance, blur, and image compression effects and found that wound assessment accuracy decreased by up to 27%. To improve model performance, we propose a method for instant image quality assessment on the smartphone, enabling low-quality wound images to be rejected immediately after image capture so that the nurse or patient can be prompted to recapture the image. Our evaluation of the proposed image quality assessment and rejection method showed that it increases average accuracy from 73 % to 87%.

Chronic pain is a multifaceted complex experience that is often captured with self-reported measures. While subjective self-reported measures capture pain from a patient’s point of view, they are limited in information richness. Collecting eye movements when completing self-reported subjective pain measures provides valuable insight about information processing and decision behavior. This information can improve the information richness of self-reported pain measures by providing a broader view of an individual’s pain experience. How people process information and make decisions when completing pain measures can also help to investigate the cognitive-evaluative aspects of chronic pain, which in turn can provide insight for developing eye-tracking biomarkers of chronic pain, and by doing so help develop smart clinician support technologies. Our preliminary results show that people with chronic pain expended significantly more cognitive effort than their pain-free counterparts when completing three self-reported pain measures that are widely used in clinical settings. These results are promising because they suggest that eye movements may serve as valuable information to accompany self-reported pain scores and thus enable effective assessment and management of chronic pain. The results also suggest that eye movements may serve as suitable biomarkers of chronic pain.

This study employs the circuits of power framework to analyze how power relationships affect the use of Information Systems (IS) in the social inclusion context.This research majorly contributes to social inclusion research in IS by examining how the power relationships influence the use of IS and how IS design can address complex power relationships and enable social inclusion.

Goal: Chronic wounds affect 6.5 million Americans. Wound assessment via algorithmic analysis of smartphone images has emerged as a viable option for remote assessment. Methods: We comprehensively score wounds based on the clinically-validated Photographic Wound Assessment Tool (PWAT), which comprehensively assesses clinically important ranges of eight wound attributes: Size, Depth, Necrotic Tissue Type, Necrotic Tissue Amount, Granulation Tissue type, Granulation Tissue Amount, Edges, Periulcer Skin Viability. We proposed a DenseNet Convolutional Neural Network (CNN) framework with patch-based context-preserving attention to assess the 8 PWAT attributes of four wound types: diabetic ulcers, pressure ulcers, vascular ulcers and surgical wounds. Results: In an evaluation on our dataset of 1639 wound images, our model estimated all 8 PWAT sub-scores with classification accuracies and F1 scores of over 80%. Conclusions: Our work is the first intelligent system that autonomously grades wounds comprehensively based on criteria in the PWAT rubric, alleviating the significant burden that manual wound grading imposes on wound care nurses.

Periodic assessment is necessary to evaluate the healing prog-ress of chronic wounds. Image analyses using computer vision algorithms have recently emerged as a viable alternative that has been demonstrated by prior work. However, the performance of such image analysis methods degrade on captured in adverse illumination, which is common in many indoor environments. To mitigate these lighting problems, High Dynamic Range (HDR) image enhancement techniques can be used to mitigate over- and under-exposure issues and preserve the details of scenes captured in non-ideal illumination. In this paper, we address over- and under-exposure simultaneously using a deep learning-based bi-directional illumination enhancement network that is able to generate over- and under-exposed images that are then fused into a final image with enhanced illumination. In rigorous evaluations using metrics including structure similarity, peak signal-noise ratio and changes in segmentation accuracy, our proposed method outperformed the state-of-the-art (SSIM scores \(0.76\pm 0.04\)/\(0.69\pm 0.08\) on bright/dark images, PSNR scores \(28.60\pm 0.70\) on dark images and DSC scores \(0.76\pm 0.09\)/\(0.74\pm 0.09\) on bright/dark images).

Recent advances in machine learning (ML) algorithms have motivated their use for automated Decision Support Systems (DSS). In healthcare domain, ML-based DSS enable providers to analyze large amounts of patient data and complex images quickly. However, providers find it difficult to interpret ML predictions due to their 'black box' reasonings. To facilitate meaningful interpretations, ML-based DSS should include explanation facilities as recommended in information systems ( IS) research. For example, a wound care DSS should allow providers to understand the reasoning (e.g., amount and presence of unhealthy tissues) behind referral decisions. We present a ML-based DSS that provides global (reliance on domain knowledge) and local (reasoning for predicting an instance) explanations for wound care decisions. We use Shapley explanations for a logistic regression (trained on wound visual features) which outperformed other classifiers when predicting referral decisions (F-1 =0.938) and demonstrate its applicability in a wound care use-scenario. Findings suggest similar approach can be applied for other complex decision problems.

A key requirement for the successful adoption of clinical decision support systems (CDSS) is their ability to provide users with reliable explanations for any given recommendation which can be challenging for some tasks such as wound management decisions. Despite the abundance of decision guidelines, wound non-expert (novice hereafter) clinicians who usually provide most of the treatments still have decision uncertainties. Our goal is to evaluate the use of a Wound CDSS smartphone App that provides explanations for recommendations it produces. The App utilizes wound images taken by the novice clinician using smartphone camera. This study experiments with two proposed variations of rule-tracing explanations called verbose-based and gist-based. Deriving upon theories of decision making, and unlike prior literature that says rule-tracing explanations are only preferred by novices, we hypothesize that, rule-tracing explanations are preferred by both clinicians but in different forms: novices prefer verbose-based rule-tracing and experts prefer gist-based rule-tracing.

Chronic wounds affect 6.5 million Americans, are complex conditions to manage and cost 28–32 billion annually. Although digital solutions exist for non-expert clinicians to accurately segment tissues, analyze affected tissues or efficiently document their wound assessment results, there exists a lack of decision support for non-expert clinicians who usually provide most wound assessments and care decisions at the point of care (POC). We designed a machine learning (ML) system that can accurately predict wound care decisions based on labeled wound image data. The care decisions we predict are based on guidelines for standard wound care and are labeled as: continue the treatment, request a change in treatment, or refer patient to a specialist. In this paper, we demonstrate how our final ML solution using XGboost (XGB) algorithm achieved on average an overall performance of F-1 = .782 using labels given by an expert and a novice decision maker. The key contribution of our research lies in the ability of the ML artifact to use only those wound features (predictors) that require less expertise for novice users when examining wounds to make standard of care decisions (predictions).