Medical
-
VABAR: A Variational Automation Benchmark for Agentic Robotics
2026-11-04 18:38:01Shuangyu Xie, Kaiyuan Chen, Uksang Yoo, Xinyue Zhu, Meadow Shen, Jaimyn Drake, Eugen Solowjow, Lionel Gulich, Alexander Millane, Rafael Cathomen, Tuur Stuyck, Sangeeta Subramanian, Yichao Pan, Bruce McGowan, Michael Benedict, Linxi Fan, Yuke Zhu, Spencer Huang, Ken GoldbergAbstract
For robots to operate reliably in commercial and industrial applications, they must persistently perform specific tasks with known variations in object shape and pose. We call this Variational Automation (VA) to differentiate these settings from fixed automation. Inspired by recent papers on Agentic Robotics, where pretrained LLM and VLM coding agents combine interpretable robot programming with the open-world adaptability of model free policies, we propose a general set of agentic robotics benchmark design criteria that includes accessibility, repeatability, diversity, relevance to agentic robotics and practical applications, physical realizability, resistance to benchmark saturation, and computational efficiency. We instantiate these principles in six manipulation task classes spanning industrial, medical, and infrastructure applications: tool sorting, tool hanging, gear meshing, syringe packing, cable insertion, and cable routing. We introduce the Variational Automation Benchmark for Agentic Robotics (VABAR), an open, easily replicable, simulation-based manipulation benchmark to systematically evaluating agentic robotics systems. Built fully on open-source tools, VABAR features detailed implementations using the Newton physics engine, standardized task variations, difficulty tiers, success metrics, and a library of 33 generalizable skills with human-authored programmatic reference solutions. We provide initial baseline evaluations using an open agentic manipulation harness, Graph-as-Policy (GaP), and Isaac Lab Arena.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06881
PDF
-
Trick-or-Treat: Adversarial Evaluation of Multimodal Medical Reasoning with Synthetic Images
2026-11-04 15:13:35Oishi Banerjee, Eujin Lee, Sung Eun Kim, Alexandra N. Willauer, Christine Y. Zhou, Zhizhou Yang, Pranav RajpurkarAbstract
We used medical image synthesis to create a challenging multimodal evaluation framework that exposes hallucination behaviors in frontier models. Evaluating multimodal reasoning has historically been difficult because existing medical datasets rarely pair different image modalities, such as radiographs and external clinical photographs. To address this gap, we introduce Trick-or-Treat, an adversarial multimodal medical benchmark that pairs real chest radiographs with synthetic clinical photographs to challenge models' cross-modal reasoning. For each of a wide range of conditions, we created two pairs of images, where the pairs share a single chest radiograph but contain different external photographs. In matched pairs, the chest radiograph and photograph both contain findings suggesting the same disease (e.g., varicella pneumonia suggested by lung opacities and crusted skin lesions seen in chickenpox). In mismatched pairs, the photograph depicts an alternative clinical finding that would not lead to the same unifying diagnosis (e.g. replacing crusted skin lesions with ordinary acne). Synthetic photograph generation allows clinical findings to be varied while the person's features and photographic setting stay consistent, reducing confounding. In an investigation of three frontier models, we found that models hallucinated clinically significant photograph findings in 45-57.5% of mismatched pairs, up from 25-37.5% for the same photographs shown alone. When faced with mismatched pairs, models tended to ignore mismatches and instead hallucinated findings that better matched the radiograph (e.g. misreading acne as crusted skin lesions to justify diagnosing chickenpox). Trick-or-Treat both demonstrates concerning error pattern in frontier models' medical reasoning and provides a proof of concept for the use of synthetic images in adversarial multimodal evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06631
PDF
-
Within-Family EfficientNet Scaling under Fixed-Resolution Transfer Learning for Spectral-Domain Optical Coherence Tomography Retinal Disease Classification
Abstract
Background/Objectives: CNNs perform well in retinal disease classification from spectral-domain optical coherence tomography (SD-OCT), but whether EfficientNet's natural-image scaling hierarchy transfers to medical-image transfer learning at fixed resolution remains unclear. This study evaluates EfficientNet-B0-B7 for four-class SD-OCT classification and accuracy-efficiency trade-offs. Methods: Eight ImageNet-pretrained variants (4.05-64.10M instantiated backbone parameters) were evaluated at 224x224 on the Kermany dataset. Grayscale images were replicated to RGB and processed using model-embedded preprocessing and augmentation. Training comprised frozen-backbone head training followed by partial fine-tuning. Metrics covered classification, discrimination, efficiency, and visual analyses. Results: Test accuracy varied non-monotonically from 95.93% (B0) to 96.95% (B1); B7 achieved 96.73%. B1 had the highest accuracy and Drusen F1 (0.8780), while B7 had Drusen F1 of 0.8720 and the highest Drusen recall (0.9177). Drusen had the lowest F1 across all variants and contributed 82.2% of the summed squared deviation in class-specific F1; class ranking remained Normal > CNV > DME > Drusen. The OCT accuracy ranking differed from the reported ImageNet hierarchy, where B7 ranked first. The accuracy-to-parameter ratio fell from 19.82 to 1.48 percentage points per million total parameters. The final train-test gap had a weak, non-significant association with test accuracy (r = 0.26, p = 0.53). Conclusions: Larger EfficientNet variants did not consistently improve SD-OCT classification. B1 achieved the highest accuracy and Drusen F1, whereas B7 showed a secondary accuracy recovery at greater model size and CPU latency, indicating task and protocol dependent scaling effects. As cross-partition duplicates have not been independently audited, results are conditional on the supplied split.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06452
PDF
-
Text-Only Domain Adaptation for Low-Resource Medical ASR: Shallow Fusion and Density Ratio Rescoring for Hausa
2026-11-03 23:32:33Oche David Ankeli, Hassan Adelani Luqman, Theodora Ngozi Egbunike, Joshua Gottschalk, Bonaventure F. P. DossouAbstract
Automatic speech recognition (ASR) systems often struggle with specialised medical vocabulary, especially in low-resource languages where domain-specific speech data are scarce. We investigate text-only domain adaptation for Hausa medical ASR using the fixed MMS-1B-FL102 acoustic model and two decoding-time language-model fusion methods: Shallow Fusion (SF) and the Density Ratio Approach (DRA). A 4-gram KenLM trained on 19,421 Hausa health sentences serves as the medical target model, while a 75,372-sentence general-domain model provides the source prior for DRA. Evaluation uses 250 recordings of 25 physician-reviewed prompts from 10 speakers across six northern Nigerian states. Under prompt-disjoint five-fold cross-validation, SF and DRA reduce WER from 29.56% to 23.55% and 23.33%, respectively. Both significantly outperform greedy decoding (p < 0.001), while their difference is not significant (p = 0.423). However, general-LM-only SF achieves 23.96% WER, indicating that the medical LM's additional improvement over a general LM is modest. Medical Term Error Rate also improves under fusion, but does not establish a distinct medical-domain advantage. These findings demonstrate that lightweight, text-only language-model fusion can improve Hausa medical ASR without additional domain-specific speech collection.
Abstract (translated)
URL
https://arxiv.org/abs/2611.05744
PDF
-
Mitigating Spurious Invariance in Contrastive Learning: A Probabilistic Self-Supervised Learning Framework for Medical Image Analysis
2026-11-03 23:10:04Wei Wei, Yading YuanAbstract
Owing to the prohibitive cost of manual annotation for enormous medical images, self-supervised learning (SSL) has gained substantial attention and shown promise in various medical imaging tasks. Among SSL approaches, contrastive learning has emerged as a prominent one, encouraging models to encode semantic information that remains invariant between different augmented views. However, this invariance can be spurious for medical images, as subtle but critical medical features can be suppressed during augmentations. In this paper, we mitigate this issue by encoding the learned feature embeddings as probability distributions rather than fixed vectors, thus capturing a richer and more nuanced spectrum of information. Furthermore, we propose a unified probabilistic framework that seamlessly integrates multiple SSL approaches. Our method achieves superior performance over the state-of-the-art SSL methods on various downstream tasks across multiple datasets, including medical image segmentation and classification. We further validate the method through additional analyses of robustness to stronger augmentations, label efficiency under limited fine-tuning labels, and computational trade-offs. The code is released at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.05734
PDF
-
DiabAgent: Toward Agentic Physiological Control
2026-11-02 18:41:02Chengxi Li, Shaoxuan Li, Deyao Hong, Qingle Liu, Yi Huang, Puheng Bian, Minzhi Xu, Lanyue Zhang, Mingze Sun, Xin Li, Calvin Xiao, Shengyuan Wang, Huan-ang Gao, Jiazheng Xu, Kaisen Yang, Hongning WangAbstract
As pretraining scales, medical language models have advanced rapidly in clinical question answering. Their ability to achieve effective physiological control through sustained intervention still lacks systematic quantitative evaluation. Type 1 diabetes provides a concrete setting: impaired insulin secretion creates dependence on exogenous insulin, with dosing continually adjusted using information about meals, exercise, illness, and glucose measurements. We introduce DiabAgent, a research suite for agentic physiological control comprising the Agentic Physiological Control (APC) framework, the DiabetSim simulator, and the SweetBench benchmark. APC controls glucose through medical-device tools, using ongoing observations to infer individual states, accumulate personal experience, and choose treatment actions. We build DiabetSim to simulate different patients, events, and device conditions for scalable virtual testing and training. Using DiabetSim, we construct SweetBench by instantiating 32 scenario designs as 212 glucose-control tasks. With Claude Opus 5.5 and a fixed decision interval of one hour, APC achieves a COGI of 73.5, compared with 71.2 for the open-source closed-loop baseline OpenAPS. Ablations further show that individual adaptation and contextual information improve glucose control. Combining high-frequency rule-based control with lower-frequency agent decisions shows potential for balancing control performance and computational cost. Our work provides a framework, simulator, and evaluation foundation for agents to participate in human physiological control.
Abstract (translated)
URL
https://arxiv.org/abs/2611.03601
PDF
-
Tug of Watts: A study on the Energy - Accuracy Trade-off of Large Language Models on Medical Question Answering Tasks
2026-11-02 10:23:57Viju Sudhi, Giulio Billi, Andreea Scrob, Regina Stodden, Philipp CimianoAbstract
Large Language Models (LLMs) are increasingly used in medical question answering (QA) systems. While recent works aim at incrementally improving the downstream task accuracy, an empirical estimation of the models' energy consumption and the associated carbon footprints is often overlooked. In this study, we demonstrate how practitioners can estimate energy consumption and arrive at reliable emission estimates for medical QA tasks available in the OpenMedical-LLM leaderboard by investigating 13 LLMs from 3 model families ranging from 270M to 14B parameters. We discuss how one can critically interpret energy versus accuracy trade-offs for a set of models for a given task. With this work, we underline that reporting disjoint energy and accuracy metrics alone does not suffice for careful trade-off assessments, but it also demands systematic construction and interpretation of joint trade-off metrics. We envisage such studies aiding practitioners in adopting better and more efficient models for their task and helping them become active participants in building sustainable LLM pipelines.
Abstract (translated)
URL
https://arxiv.org/abs/2611.02889
PDF
-
Window-Aware Scheduling for Health Messaging under Platform Delivery Constraints: Evidence from an AI-Powered WhatsApp Maternal and Infant Health Chatbot in Nigeria
2026-11-02 09:34:22Jeremiah Moyondafoluwa Adepoju, Samuel Omolaiye, Thanni Adewuyi, AbdulQahhar Abimbola Okenla, Lily-Aimas Love, Adereni AbiodunAbstract
WhatsApp lets a business send free-form messages only within 24 hours of a user's last message; outside this customer service window, only pre-approved templates are delivered. Health chatbots inherit this rule, but its cost is rarely measured. We analyse 98,607 messages sent to 3,696 mothers by a WhatsApp maternal health chatbot in Nigeria, with a largely separate export as replication. No free-form message failed with the window open (0 of 35,500), and failure jumped by 93.0 percentage points (95% CI 87.0 to 99.1) at exactly 24 hours. Two flows produced 66.1% of failures, including an offer to speak with a medical professional that, as built, reached 0.3 in 100 mothers whose window had closed. We formalise window-aware scheduling as a decision problem with an action of known zero value. Model-based offline evaluation, with bounds for unconfirmed delivery, estimates that sending the offer as an approved template would reach 81.5 to 86.8 in 100 such mothers, against 16.6 for waiting and 11.6 for a reply prompt. In a calibrated simulation, tabular Q-learning converges to the same template rule and does not beat it in any of 13 stress tests, and opting out does not rise with message volume. The main gain comes from respecting the platform rule, and it needs no learning. All outcomes are deliveries, not health outcomes.
Abstract (translated)
URL
https://arxiv.org/abs/2611.02834
PDF
-
Accessed, never disclosed: Silent access to protected health information by medical artificial intelligence agents
2026-11-02 00:10:47Jae Wang Lee, Abhirup Banerjee, Yeong Chan LeeAbstract
Medical artificial intelligence agents should retrieve patient identifiers only when a task requires them, the data-minimization principle behind the HIPAA minimum necessary standard for protected health information (PHI). An agent can retrieve identifiers without revealing them. Such silent access remains invisible to evaluations that inspect only the output. We embedded canaries in synthetic patient records and linked each tool invocation to canary exposure in the final answers across five language models, four boundary levels, and seven attack frames for identifier-free clinical tasks. Three models invoked the PHI tools unnecessarily, whereas Claude Opus 4.8 and GPT-5.5 did not. Stronger boundaries reduced this access, and the residual access under the strictest policy was confined to frames in which the user overrode the policy or asserted approval. A pre-execution gate given the task-necessity criterion nearly eliminated this access. Output-only evaluation cannot verify minimum-necessary access; boundaries, gates, and access-log audits are required together.
Abstract (translated)
URL
https://arxiv.org/abs/2611.02319
PDF
-
MedPsy: State-of-the-Art Small Medical Language Models for Efficient Edge Deployment
2026-11-01 15:52:32Davide Vitabile, Alexandro Buffa, Akshay Nambiar, Amril NazirAbstract
Medical language models promise expert clinical support, but the strongest open-source LLMs remain too large for private edge-device deployment, while compact medical models still trail substantially on knowledge-intensive and real-world healthcare tasks. Reasoning models that fit edge memory budgets can produce long reasoning traces, increasing sequential decoding, end-to-end latency, energy consumption, and KV-cache memory pressure. We present MedPsy, a family of text-only 1.7B and 4B medical language models designed for edge deployment, targeting this accuracy-generation-efficiency trade-off. Our recipe combines a synthetic medical data pipeline over biology, medicine, and health seeds with chain-of-thought targets from a 235B medical-focused LLM teacher; a four-stage post-training curriculum comprising two SFT stages followed by two RL stages with hard-sample mining; and an edge deployment evaluation spanning multiple GGUF quantization variants and real-device inference on laptop and smartphone hardware. On seven closed-ended medical benchmarks, MedPsy-4B surpasses MedGemma-1.5-4B by 19.34 points and matches MedGemma-27B while being 6.75x smaller; MedPsy-1.7B outperforms MedGemma-1.5-4B by 11.42 points despite being less than half its size. On HealthBench-Hard, MedPsy-4B surpasses MedGemma-27B by 15.33 points, while MedPsy-1.7B surpasses it by 11.66 points despite being ~16x smaller. Beyond accuracy, MedPsy reduces average response length by 1.7x (1.7B) and 3.2x (4B) versus its Qwen3 backbones, while Q4_K_M quantization preserves the aggregate score within 1 point of BF16 with ~69% lower disk footprint. In real-device inference, MedPsy-4B's shorter generations translate into 75% lower median end-to-end latency and estimated energy per answer than its Qwen3 backbone at matched quantization, while peak RAM remains below 5 GB across our tested laptop and smartphone configurations.
Abstract (translated)
URL
https://arxiv.org/abs/2611.02011
PDF
-
Accounting for Irregular State Transitions through Belief Estimation in Online Medical Consultation
2026-11-01 03:05:59Mingzhe Lu, Xiangru Chen, Jian Qin, Yunpeng Li, Xihan GaoAbstract
While online medical consultation broadens access, unprompted patient disclosures and topic shifts frequently disrupt clinician inquiry, leaving clinical states progressively revealed. We characterize these dynamics using both existing evaluation metrics and task-specific interaction metrics designed in this work. Through an empirical study across 16 medical dialogue datasets, we show that authentic online interactions exhibit substantially lower contextual continuity and higher unpredictability than offline and simulated benchmarks. We propose PRISM (Policy Reasoning with Inferred States for Medicine), a framework inspired by partially observable Markov decision processes that decouples latent state estimation from action selection to address drifting dialogue trajectories. Specifically, PRISM factorizes clinical triage into belief estimation, policy optimization, and response realization. By maintaining an evolving posterior belief over consultation states and conditioning action selection on the maximum a posteriori state, PRISM advances clinical goals while accommodating patient-initiated shifts. Extensive evaluations show that PRISM substantially outperforms frontier LLMs and clinical agents, achieving a 22.40 percentage point gain in clinical decision accuracy alongside decisive improvements in response generation, surpassing the strongest baseline by 5.51 points in BERTScore_F1. Furthermore, ablation studies show that providing oracle consultation states consistently boosts response quality across all evaluated baselines by guiding their action reasoning, yielding average gains of 5.58 points in BERTScore_F1.
Abstract (translated)
URL
https://arxiv.org/abs/2611.01474
PDF
-
Are Fake Citations a Form of Reward Hacking? A Pre-Registered Study of Post-Training and Citation Cues
Abstract
Post-trained language models fabricate citations at high rates. We ask whether that is reward hacking: scoring well on a proxy for scholarship while doing worse on what it stands for. We ran four pre-registered experiments on 900 frozen questions (US federal case law, computationally adjacent scientific literature, and medical literature) across twelve open-weights checkpoints covering four post-training stages of three model families, then refit on fifteen. The clearest result holds the weights fixed and changes only the prompt. Asking for citations raises fabrication sharply in post-trained checkpoints and not in base ones: a 47.8-point interaction on twelve checkpoints (Holm-adjusted p = 2e-34) and 41.5 points on fifteen, in all three domains. A length-matched control separates the citation cue from a demand for a longer answer, so the effect is specific to citations, not verbosity. Post-training also raises fabrication overall, from 4.8% to 56.7%, but our registered prediction that it would rise most where fabrication is most tempting did not hold. A preference model trained only on surface citation features prefers post-trained output 86% of the time, and holding citation count fixed shows it rewards quantity. Our answer: possibly, but not proven. Post-trained models produce fabricated citations at far higher rates when asked for sources, and a naive evaluator that counts sources without checking them would prefer their output for citing more. But the targeted pattern we registered did not appear, and plain instruction-following could explain the same results. Proving that the reward causes fabrication needs an experiment that changes the reward during training, which this study does not do. Pre-registration: doi:https://doi.org/10.17605/OSF.IO/S53HY. Code and data: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2611.01313
PDF
-
MedAstra: ASR-less Speech Retrieval with Diagnostic Grounding for Medical QA
2026-10-31 21:00:22Elahe Khatibi, Ziyu Wang, Amir M. RahmaniAbstract
Spoken medical question answering can fail when automatic speech recognition (ASR) corrupts a clinically important term before retrieval. We present MedAstra, a framework that maps frozen WavLM speech representations through a lightweight adapter into a frozen E5 text embedding space. This enables a dense retrieval path that accepts a waveform without a query transcript. Retrieved passages and speech-linked textual metadata support answer generation with entity alternatives, diagnostic contrasts, relation heuristics, and bounded retrieval refinement. ASR-less refers to the initial speech retrieval interface; lexical retrieval, string-based entity correction, and the text generator require textual inputs. The deterministic speech embedding does not constitute a calibrated model of acoustic uncertainty. Reported retrieval results reach 87.6 Recall@10 for the speech-only retriever and 90.4 for the hybrid configuration, compared with 81.0 for transcript-first dense retrieval. Medical QA and ablations provide descriptive system comparisons, with input-provenance and evaluation limitations stated explicitly. We distinguish controlled synthetic acoustic tests from real clinical speech, qualify component attribution, and specify the remaining comparisons needed to assess speech-only QA and clinical generalization.
Abstract (translated)
URL
https://arxiv.org/abs/2611.01261
PDF
-
Labadain-MedQA: A Tetun Medical QA Dataset for Fine-Tuning and Evaluating Large Language Models
2026-10-31 13:36:05Gabriel de Jesus, S\'ergio NunesAbstract
Advances in large language models (LLMs) have created opportunities for cross-lingual transfer of medical knowledge from high-resource to low-resource languages to support access to healthcare information. However, medical question-answering (QA) datasets for fine-tuning and evaluating LLMs remain scarce for Tetun. To address this gap, we translated MedAlpaca's Medical Flashcards and WikiDoc Patient Information collections into Tetun using Gemini 2.5 Flash, producing 39,077 medical QA pairs. Translation quality was assessed on 50 randomly sampled QA pairs (100 documents) using automatic metrics against human reference translations and evaluations by two native Tetun-speaking healthcare professionals, focusing on medical accuracy and Tetun fluency. Human translations achieved higher mean ratings than LLM-generated translations for both criteria (4.43/5 vs. 4.02/5), with statistically significant differences (Wilcoxon signed-rank test, p < 0.001). To assess downstream utility, we fine-tuned Gemma and Llama variants on the translated MedAlpaca dataset using parameter-efficient fine-tuning (PEFT) and evaluated them on 325 Tetun-translated United States Medical Licensing Examination multiple-choice questions. Gemma 4 12B fine-tuned using QLoRA achieved relative improvements in mean accuracy of 10.79% with 4-bit NormalFloat (NF4) inference and 10.42% after merging the LoRA adapters into the BF16 base model, compared with the corresponding base models. These results highlight the viability of automatic dataset translation for Tetun medical QA and the effectiveness of PEFT in enhancing model performance. The datasets, models, and evaluation resources are accessible at this https URL to support reproducible research on Tetun medical QA and facilitate machine translation, cross lingual, and multilingual research.
Abstract (translated)
URL
https://arxiv.org/abs/2611.00935
PDF
-
From Small to Large: Assessing Medical Reasoning, Benchmark Contamination, and Model Size in Language Models
2026-10-30 23:23:42Navapat Nananukul, Mayank KejriwalAbstract
Large language models (LLMs) now answer medical exam questions at or above expert level, but it is unclear whether such scores reflect clinical competence, or are instead affected by the format of the questions being asked (e.g., multiple-choice versus open-ended), prior exposure to the benchmarks, and the difficulty of the questions. These benchmarks are also public and widely used online, which may be resulting in LLM memorization. Models may perform better on questions that they have seen before. It is also not evident whether smaller models, which are more locally deployable in HIPAA-compliant hospital settings, have achieved human performance. In this study, we evaluate fourteen current models from six leading providers, one smaller and one larger model from each provider with two additional open-weight models, on 3,076 questions from four medical benchmarks (MedQA-USMLE, MedMCQA, PubMedQA, and MedBullets) under standard multiple choice, the same questions with the answer choices withheld, and reconstruction of a hidden question from its choices alone. In the standard multiple-choice setting, the strongest models exceed the human-expert baseline on MedQA-USMLE and PubMedQA, but the smaller models trail their larger models by 8.7 percentage points and only two of the six pass the human-expert bar on the licensing examination. Withholding the answer choices, however, makes every model struggle: mean accuracy falls from 82.3% to 50.9%, and the two largest drops belong to the medically specialised models. On memorization, the strongest models reconstruct one question in four from the answer choices alone, yet accuracy holds on the questions they cannot reconstruct. We further weigh accuracy against inference cost and test whether ensembling several models improves medical question answering.
Abstract (translated)
URL
https://arxiv.org/abs/2611.00460
PDF
-
GazeRIB: Systematic Evaluation of Multi-Reader Gaze-Guided Chest X-ray Learning
2026-10-30 17:59:59Nattakorn Kittisut, Roy M. Gabriel, Marly van Assen, Mohammadreza Zandehshahvar, Carlo N. De Cecco, Elizabeth A. Krupinski, Ali AdibiAbstract
Radiologists' visual attention can supervise medical image learning, but how reader panel composition affects its value remains untested. We evaluated GazeRIB (Gaze-guided Radiologist-Informed Blackout), which masks unviewed regions during training and uses unmasked images at inference. Eight experts repeatedly read the same 80 chest X-rays (CXRs). We compared individual readers with three-, five- and eight-reader panels across seven architectures and 10 seeds, evaluating 910 models on a separate 2,897-CXR cohort for four-class severity prediction. Every panel improved macro F1 over the no-gaze baseline by 5.33-7.47 percentage points (pp; Bonferroni-adjusted p < 0.007); no individual reader reached significance on this endpoint. Three readers captured 73-80% of the eight-reader gain in macro F1, the area under the receiver-operating-characteristic curve (ROC-AUC) and the area under the precision-recall curve (AU-PRC). On external validation without retraining, all four panels improved ROC-AUC on SIIM-FISABIO-RSNA by +1.93 to +4.24 pp (p <= 0.004); on MIMIC-Eye no panel differed significantly from baseline, whereas the single-reader average declined (-1.40 pp, p = 0.008). Reader composition therefore influenced performance, although transfer depended on the cohort.
Abstract (translated)
URL
https://arxiv.org/abs/2610.42152
PDF
-
Variational decomposition autoencoding improves disentanglement of latent representations
2026-10-30 16:15:53Ioannis N. Ziogas, Aamna Al Shehhi, Ahsan H. Khandoker, Leontios J. HadjileontiadisAbstract
Understanding the structure of complex, nonstationary, high-dimensional time-evolving signals is a central challenge in scientific data analysis. In many domains, such as speech and biomedical signal processing, the ability to learn disentangled and interpretable representations is critical for uncovering latent generative mechanisms. Traditional approaches to unsupervised representation learning, including variational autoencoders (VAEs), often struggle to capture the temporal and spectral diversity inherent in such data. Here we introduce variational decomposition autoencoding (VDA), a framework that incorporates a strong structural bias toward signal decomposition into variational representation learning. VDA is instantiated through variational decomposition autoencoders (DecVAEs), i.e., encoder-only neural networks that perform latent autoencoding at the level of distributions to learn multiple latent subspaces aligned with time-frequency characteristics. We evaluate DecVAEs on simulated data and three publicly available scientific datasets, spanning speech recognition, dysarthric speech evaluation, and emotional speech classification. DecVAEs improve on VAE-based methods in disentanglement quality and robustness, and their latent subspaces become factor-specific when the generative factors have distinct spectral signatures. These findings position decomposition-aware architectures as potential tools for extracting structured representations from speech, and potentially from other dynamic signals with factors exhibiting distinct spectral signatures, with applications in clinical diagnostics, human-computer interaction, and adaptive neurotechnologies.
Abstract (translated)
URL
https://arxiv.org/abs/2601.06844
PDF
-
Different Models, Shared Failures: Auditing Frozen-Encoder Pools for Medical Segmentation
2026-10-30 14:21:52Eunseob Choi, Kyeonghun Kim, Hyuk-Jae Lee, Nam-Joon KimAbstract
Average segmentation accuracy and model count do not reveal whether models fail on the same cases. We present CoFailMed, an audit of correlated failures in pretrained-encoder pools for medical segmentation. Across five 2D tasks, we evaluate 11 public pretrained encoders (a controlled sample, not a census) using frozen features and separately trained $1\times 1$ readouts with four seeds per encoder. Shared-checkpoint pairs have the highest mean per-case Dice correlation. An expanded 17-encoder analysis shows that distinct checkpoints within the same encoder family remain more correlated than cross-family pairs. At the pooled 33rd-percentile Dice threshold, four-member pools drawn from distinct encoders have mean effective sizes of 1.56-2.92, estimated from failure correlations in pools with enough failures and passes per member. In the primary pool, richer readouts and fine-tuning narrow the Dice-correlation gap between pairs sharing a checkpoint (or the DINOv2-B/S release) and all other pairs. Yet dependence between different encoders can increase, and fine-tuning does not consistently increase effective pool size at 33rd-percentile thresholds recomputed for each training recipe. A smaller between-group gap can coexist with greater dependence. Pool evaluation should therefore report absolute dependence and threshold-specific effective size alongside accuracy and nominal pool size. The CoFailMed release provides aligned per-case traces, analysis scripts and study code to reproduce the central audit results.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41790
PDF
-
Clinical-Protocol-Aware Cyber Resilience for Connected Clinical Technologies Under AI-Enabled Adversarial Conditions
2026-10-30 14:18:39Pranav Patel, Siva Kannathasan, Prerak Patel, Jigar Patel, Vansh Patel, Sheel PatelAbstract
Healthcare increasingly relies on connected medical devices, clinical information systems, cloud services, and distributed-care technologies, creating cybersecurity risks across clinical workflows. AI-enabled capabilities can accelerate vulnerability discovery and attack-path analysis, increasing the need to limit compromise propagation. This paper proposes a clinical-protocol-aware cyber-resilience framework based on bounded clinical micro-networks and controlled interconnections. The framework integrates clinical factors into cybersecurity design, management, and evaluation, covering prevention, containment, and incident response. A parameterized Monte Carlo simulation distinguishes technical cyber exposure from modeled clinical consequence. Experiments investigate architectural connectivity, adversarial capability, security controls, protocol dependency, risk alignment, communication directionality, lifecycle integration, and response timing. Under the simulation assumptions, connected architecture increases mean cyber exposure by 56.3% relative to segmented architecture, while combined prevention and containment reduce exposure by 60.1% relative to no controls. Increasing protocol dependency raises the modeled clinical-impact index from 1.021 to 7.567 without changing mean cyber exposure, demonstrating that technical exposure and clinical consequence can diverge. Risk-alignment experiments further indicate higher modeled clinical impact when greater technical risk corresponds to greater clinical significance. The findings support comparative architectural analysis, not calibrated estimates of real-world cyber risk, control effectiveness, or patient harm. The framework provides a clinical-context-aware approach to security-boundary design, control prioritization, and coordinated containment in connected healthcare environments.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41784
PDF
-
Measuring What Matters: A Causal Reliance Score for Histopathology Image Segmentation
2026-10-30 14:05:19Samuel Thomas, Daniel Tweneboah Anyimadu, Ahmed Karam Eldaly, Somaia Elsheikh, Mohammed M. AbdelsameaAbstract
Reliable histopathology segmentation requires models that rely on pathology-relevant structures rather than spurious background correlations. In this work, we argue that improving architectures alone is insufficient if models continue to rely on spurious correlations rather than pathology-relevant features. We introduce a causality-inspired evaluation framework based on controlled interventions that explicitly probes model sensitivity to foreground tissue structure and background/domain variation. Building on this, we propose the Causal Reliance Score (CRS), a metric that quantifies the relative sensitivity of model predictions to foreground perturbation versus background/domain variation under controlled interventions. To support this analysis, we design augmentation strategies that act as implicit counterfactual interventions during training, encouraging invariance to nuisance factors while preserving morphology. We demonstrate how these interventions reveal behavioural differences between models that are not captured by standard metrics such as Dice or IoU. While we instantiate our framework using a self-supervised transformer (CAUSE-ViT), the primary contribution of this work is not a new architecture, but a principled intervention-based methodology and evaluation metric for auditing model behaviour in medical image segmentation. Our results suggest that evaluating model behaviour through counterfactual interventions is essential for developing reliable and clinically robust medical image segmentation systems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41763
PDF
