Abstract-- Aligning 3D scene graphs is a crucial initial step for several applications in robot navigation and embodied perception. Current methods in 3D scene graph alignment often rely on single-modality point cloud data and struggle with incomplete or noisy input. We introduce SGAligner++, a cross-modal, language-aided framework for 3D scene graph alignment. Our method addresses the challenge of aligning partially overlapping scene observations across heterogeneous modalities by learning a unified joint embedding space, enabling accurate alignment even under low-overlap conditions and sensor noise. By employing lightweight unimodal encoders and attention-based fusion, SGAligner++ enhances scene understanding for tasks such as visual localization, 3D reconstruction, and navigation, while ensuring scalability and minimal computational overhead. Extensive evaluations on real-world datasets demonstrate that SGAligner++ outperforms state-of-the-art methods by up to 40% on noisy real-world reconstructions, while enabling cross-modal generalization.

Diabetic retinopathy (DR) is a leading cause of blindness worldwide, and AI systems can expand access to fundus photography screening. Current FDA-cleared systems primarily provide binary referral outputs, where this minimal output may limit clinical trust and utility. Yet, determining the most effective output format to enhance clinician-AI performance is an empirical challenge that is difficult to assess at scale. We evaluated multimodal large language models (MLLMs) for DR detection and their ability to simulate clinical AI assistance across different output types. Two models were tested on IDRiD and Messidor-2: GPT-4o, a general-purpose MLLM, and MedGemma, an open-source medical model. Experiments included: (1) baseline evaluation, (2) simulated AI assistance with synthetic predictions, and (3) actual AI-to-AI collaboration where GPT-4o incorporated MedGemma outputs. MedGemma outperformed GPT-4o at baseline, achieving higher sensitivity and AUROC, while GPT-4o showed near-perfect specificity but low sensitivity. Both models adjusted predictions based on simulated AI inputs, but GPT-4o's performance collapsed with incorrect ones, whereas MedGemma remained more stable. In actual collaboration, GPT-4o achieved strong results when guided by MedGemma's descriptive outputs, even without direct image access (AUROC up to 0.96). These findings suggest MLLMs may improve DR screening pipelines and serve as scalable simulators for studying clinical AI assistance across varying output configurations. Open, lightweight models such as MedGemma may be especially valuable in low-resource settings, while descriptive outputs could enhance explainability and clinician trust in clinical workflows.

Decades' advances in digital health technologies, such as electronic health records, have largely streamlined routine clinical processes. Yet, most these systems are still hard to learn and use: Clinicians often face the burden of managing multiple tools, repeating manual actions for each patient, navigating complicated UI trees to locate functions, and spending significant time on administration instead of caring for patients. The recent rise of large language model (LLM) based agents demonstrates exceptional capability in coding and computer operation, revealing the potential for humans to interact with operating systems and software not by direct manipulation, but by instructing agents through natural language. This shift highlights the need for an abstraction layer, an agent-computer interface, that translates human language into machine-executable commands. In digital healthcare, however, requires a more domain-specific abstractions that strictly follow trusted clinical guidelines and procedural standards to ensure safety, transparency, and compliance. To address this need, we present \textbf{MedicalOS}, a unified agent-based operational system designed as such a domain-specific abstract layer for healthcare. It translates human instructions into pre-defined digital healthcare commands, such as patient inquiry, history retrieval, exam management, report generation, referrals, treatment planning, that we wrapped as off-the-shelf tools using machine languages (e.g., Python, APIs, MCP, Linux). We empirically validate MedicalOS on 214 patient cases across 22 specialties, demonstrating high diagnostic accuracy and confidence, clinically sound examination requests, and consistent generation of structured reports and medication recommendations. These results highlight MedicalOS as a trustworthy and scalable foundation for advancing workflow automation in clinical practice.

Diabetic Retinopathy (DR) is a leading cause of vision loss in working-age individuals. Early detection of DR can reduce the risk of vision loss by up to 95%, but a shortage of retinologists and challenges in timely examination complicate detection. Artificial Intelligence (AI) models using retinal fundus photographs (RFPs) offer a promising solution. However, adoption in clinical settings is hindered by low-quality data and biases that may lead AI systems to learn unintended features. To address these challenges, we developed RAIS-DR, a Responsible AI System for DR screening that incorporates ethical principles across the AI lifecycle. RAIS-DR integrates efficient convolutional models for preprocessing, quality assessment, and three specialized DR classification models. We evaluated RAIS-DR against the FDA-approved EyeArt system on a local dataset of 1,046 patients, unseen by both systems. RAIS-DR demonstrated significant improvements, with F1 scores increasing by 5-12%, accuracy by 6-19%, and specificity by 10-20%. Additionally, fairness metrics such as Disparate Impact and Equal Opportunity Difference indicated equitable performance across demographic subgroups, underscoring RAIS-DR's potential to reduce healthcare disparities. These results highlight RAIS-DR as a robust and ethically aligned solution for DR screening in clinical settings. The code, weights of RAIS-DR are available at https://gitlab.com/inteligencia-gubernamental-jalisco/jalisco-retinopathy with RAIL.

Large language models (LLMs) have the potential to address social and behavioral determinants of health by transforming labor intensive workflows in resource-constrained settings. Creating LLM-based applications that serve the needs of underserved communities requires a deep understanding of their local context, but it is often the case that neither LLMs nor their developers possess this local expertise, and the experts in these communities often face severe time/resource constraints. This creates a disconnect: how can one engage in meaningful co-design of an LLM-based application for an under-resourced community when the communication channel between the LLM developer and domain expert is constrained? We explored this question through a real-world case study, in which our data science team sought to partner with social workers at a safety net hospital to build an LLM application that summarizes patients' social needs. Whereas prior works focus on the challenge of prompt tuning, we found that the most critical challenge in this setting is the careful and precise specification of \what information to surface to providers so that the LLM application is accurate, comprehensive, and verifiable. Here we present a novel co-design framework for settings with limited access to domain experts, in which the summary generation task is first decomposed into individually-optimizable attributes and then each attribute is efficiently refined and validated through a multi-tier cascading approach.

Large language models (LLMs) can simulate clinical reasoning based on natural language prompts, but their utility in ophthalmology is largely unexplored. This study evaluated GPT-4's ability to interpret structured textual descriptions of retinal fundus photographs and simulate clinical decisions for diabetic retinopathy (DR) and glaucoma screening, including the impact of adding real or synthetic clinical metadata. We conducted a retrospective diagnostic validation study using 300 annotated fundus images. GPT-4 received structured prompts describing each image, with or without patient metadata. The model was tasked with assigning an ICDR severity score, recommending DR referral, and estimating the cup-to-disc ratio for glaucoma referral. Performance was evaluated using accuracy, macro and weighted F1 scores, and Cohen's kappa. McNemar's test and change rate analysis were used to assess the influence of metadata. GPT-4 showed moderate performance for ICDR classification (accuracy 67.5%, macro F1 0.33, weighted F1 0.67, kappa 0.25), driven mainly by correct identification of normal cases. Performance improved in the binary DR referral task (accuracy 82.3%, F1 0.54, kappa 0.44). For glaucoma referral, performance was poor across all settings (accuracy ~78%, F1 <0.04, kappa <0.03). Metadata inclusion did not significantly affect outcomes (McNemar p > 0.05), and predictions remained consistent across conditions. GPT-4 can simulate basic ophthalmic decision-making from structured prompts but lacks precision for complex tasks. While not suitable for clinical use, LLMs may assist in education, documentation, or image annotation workflows in ophthalmology.

Chest radiography is widely used in diagnostic imaging. However, perceptual errors -- especially overlooked but visible abnormalities -- remain common and clinically significant. Current workflows and AI systems provide limited support for detecting such errors after interpretation and often lack meaningful human--AI collaboration. We introduce RADAR (Radiologist--AI Diagnostic Assistance and Review), a post-interpretation companion system. RADAR ingests finalized radiologist annotations and CXR images, then performs regional-level analysis to detect and refer potentially missed abnormal regions. The system supports a "second-look" workflow and offers suggested regions of interest (ROIs) rather than fixed labels to accommodate inter-observer variation. We evaluated RADAR on a simulated perceptual-error dataset derived from de-identified CXR cases, using F1 score and Intersection over Union (IoU) as primary metrics. RADAR achieved a recall of 0.78, precision of 0.44, and an F1 score of 0.56 in detecting missed abnormalities in the simulated perceptual-error dataset. Although precision is moderate, this reduces over-reliance on AI by encouraging radiologist oversight in human--AI collaboration. The median IoU was 0.78, with more than 90% of referrals exceeding 0.5 IoU, indicating accurate regional localization. RADAR effectively complements radiologist judgment, providing valuable post-read support for perceptual-error detection in CXR interpretation. Its flexible ROI suggestions and non-intrusive integration position it as a promising tool in real-world radiology workflows. To facilitate reproducibility and further evaluation, we release a fully open-source web implementation alongside a simulated error dataset. All code, data, demonstration videos, and the application are publicly available at https://github.com/avutukuri01/RADAR.

In this work, we unveil and study idiosyncrasies in Large Language Models (LLMs) -- unique patterns in their outputs that can be used to distinguish the models. To do so, we consider a simple classification task: given a particular text output, the objective is to predict the source LLM that generates the text. We evaluate this synthetic task across various groups of LLMs and find that simply fine-tuning existing text embedding models on LLM-generated texts yields excellent classification accuracy. Notably, we achieve 97.1% accuracy on held-out validation data in the five-way classification problem involving ChatGPT, Claude, Grok, Gemini, and DeepSeek. Our further investigation reveals that these idiosyncrasies are rooted in word-level distributions. These patterns persist even when the texts are rewritten, translated, or summarized by an external LLM, suggesting that they are also encoded in the semantic content. Additionally, we leverage LLM as judges to generate detailed, open-ended descriptions of each model's idiosyncrasies. Finally, we discuss the broader implications of our findings, particularly for training on synthetic data and inferring model similarity. Code is available at https://github.com/locuslab/llm-idiosyncrasies.

Referral workflow inefficiencies, including misaligned referrals and delays, contribute to suboptimal patient outcomes and higher healthcare costs. In this study, we investigated the possibility of predicting procedural needs based on primary care diagnostic entries, thereby improving referral accuracy, streamlining workflows, and providing better care to patients. A de-identified dataset of 2,086 orthopedic referrals from the University of Texas Health at Tyler was analyzed using machine learning models built on Base General Embeddings (BGE) for semantic extraction. To ensure real-world applicability, noise tolerance experiments were conducted, and oversampling techniques were employed to mitigate class imbalance. The selected optimum and parsimonious embedding model demonstrated high predictive accuracy (ROC-AUC: 0.874, Matthews Correlation Coefficient (MCC): 0.540), effectively distinguishing patients requiring surgical intervention. Dimensionality reduction techniques confirmed the model's ability to capture meaningful clinical relationships. A threshold sensitivity analysis identified an optimal decision threshold (0.30) to balance precision and recall, maximizing referral efficiency. In the predictive modeling analysis, the procedure rate increased from 11.27% to an optimal 60.1%, representing a 433% improvement with significant implications for operational efficiency and healthcare revenue. The results of our study demonstrate that referral optimization can enhance primary and surgical care integration. Through this approach, precise and timely predictions of procedural requirements can be made, thereby minimizing delays, improving surgical planning, and reducing administrative burdens. In addition, the findings highlight the potential of clinical decision support as a scalable solution for improving patient outcomes and the efficiency of the healthcare system.

Objective: This study proposes a Natural Language Processing pipeline to evaluate prescription appropriateness in Italian referrals, where reasons for prescriptions are recorded only as free text, complicating automated comparisons with guidelines. The pipeline aims to derive, for the first time, a comprehensive summary of the reasons behind these referrals and a quantification of their appropriateness. While demonstrated in a specific case study, the approach is designed to generalize to other types of examinations. Methods: Leveraging embeddings from a transformer-based model, the proposed approach clusters referral texts, maps clusters to labels, and aligns these labels with existing guidelines. We present a case study on a dataset of 496,971 referrals, consisting of all referrals for venous echocolordopplers of the lower limbs between 2019 and 2021 in the Lombardy Region. A sample of 1,000 referrals was manually annotated to validate the results. Results: The pipeline exhibited high performance for referrals' reasons (Prec=92.43%, Rec=83.28%) and excellent results for referrals' appropriateness (Prec=93.58%, Rec=91.52%) on the annotated subset. Analysis of the entire dataset identified clusters matching guideline-defined reasons - both appropriate and inappropriate - as well as clusters not addressed in the guidelines. Overall, 34.32% of referrals were marked as appropriate, 34.07% inappropriate, 14.37% likely inappropriate, and 17.24% could not be mapped to guidelines. Conclusions: The proposed pipeline effectively assessed prescription appropriateness across a large dataset, serving as a valuable tool for health authorities. Findings have informed the Lombardy Region's efforts to strengthen recommendations and reduce the burden of inappropriate referrals.