Healthcare

Chatbot usage has increased, including in fields for which they were never developed for--notably mental health support. To that end, we introduce Validations of Ethical and Responsible AI in Mental Health (VERA-MH), a novel clinically-validated evaluation for safety of chatbots in the context of mental health support. The first iteration of VERA-MH focuses on Suicidal Ideation (SI) risks, by assessing how well chatbots can responds to users that might be in crisis. VERA-MH is comprised of three steps: conversation simulation, conversation judging and model rating. First, to simulate conversations with the chatbot under evaluation, another chatbot is tasked with role-playing users based on specific personas. Such user personas have been developed under clinical guidance, to make sure that, among others, multiple risk factors, demographic characteristics and disclosure factors were represented. In the judging step, a second support model is used as an LLM-as-a-Judge, together with a clinically-developed rubric. The rubric is structured as a flow, with a single Yes/No question asked each time, to improve answers' consistency and highlight models' failure modes. In the last stage, results of each conversation are aggregated to present the final evaluation of the chatbot. Together with the framework, we present the result of the evaluations for four leading LLM providers.

Most existing medical dialogue systems operate in a single-turn question--answering paradigm or rely on template-based datasets, limiting conversational realism and multilingual applicability. We introduce IndicMedDialog, a parallel multi-turn medical dialogue dataset spanning English and nine Indic languages: Assamese, Bengali, Gujarati, Hindi, Marathi, Punjabi, Tamil, Telugu, and Urdu. The dataset extends MDDial with LLM-generated synthetic consultations, translated using TranslateGemma, verified by native speakers, and refined through a script-aware post-processing pipeline to correct phonetic, lexical, and character-spacing errors. Building on this dataset, we fine-tune IndicMedLM via parameter-efficient adaptation of a quantized small language model, incorporating optional patient pre-context to personalise multi-turn symptom elicitation. We evaluate against zero-shot multilingual baselines, conduct systematic error analysis across ten languages, and validate clinical plausibility through medical expert evaluation.

The existing methods for evaluating the medical knowledge of Large Language Models (LLMs) are largely based on atemporal examination-style benchmarks, while in reality, medical knowledge is inherently dynamic and continuously evolves as new evidence emerges and treatments are approved. Consequently, evaluating medical knowledge without a temporal context may provide an incomplete assessment of whether LLMs can accurately reason about time-specific medical knowledge. Moreover, most medical data are historical, requiring the models not only to recall the correct knowledge, but also to know when that knowledge is correct. To bridge the gap, we built TempoMed-Bench, the first-of-its-kind benchmark for evaluating the temporal awareness of the LLMs in the medical domain through evolving guideline knowledge. Based on the TempoMed-Bench, our evaluation analysis first reveals that LLMs lack temporal awareness in medical knowledge through the key findings: (1) model performance on up-to-date medical knowledge exhibits a gradual linear decline over time rather than a sharp knowledge-cutoff behavior, suggesting that parametric medical knowledge is not strictly bounded by knowledge cutoffs; (2) LLMs consistently struggle more with recalling outdated historical medical knowledge than with up-to-date recommendations: accuracy of historical knowledge is only 25.37%-53.89% of up-to-date knowledge, indicating potential knowledge forgetting effects during training; and (3) LLMs often exhibit temporally inconsistent behaviors, where predictions fluctuate irregularly across neighboring years. We also show that the temporal awareness problem is a challenge that cannot be easily solved when integrated with agentic search tools (-3.15%-14.14%). This work highlights an important yet underexplored challenge and motivates future research on developing LLMs that can better encode time-specific medical knowledge.

Clinical decision-support systems are expert systems whose recommendations clinicians act on directly, yet they are usually cleared on one aggregate accuracy number from a held-out test set. That number says nothing about input reliability under encoding shifts, subgroup gaps, threshold sensitivity, or operational feasibility. We present RISED, a pre-deployment evaluation framework operationalising five dimensions (Reliability, Inclusivity, Sensitivity, Equity, Deployability) through BCa bootstrap 95% confidence intervals, literature-grounded thresholds, and Holm-Bonferroni-corrected PASS / FAIL / INCONCLUSIVE verdicts; Equity is a proxy-dependence diagnostic rather than a gating test. Applied to seven cohorts spanning 35 years (n from 303 to 99,492), RISED surfaces failures invisible to AUROC: on Diabetes 130, Reliability passes by three orders of magnitude (PSS = 0.0004) while Inclusivity (AUC parity gap = 0.262) and Sensitivity (max threshold-flip rate 49.1%) fail decisively; both NHIS cohorts reproduce this. NHANES 2021-2023, with a complete feature profile, achieves INCONCLUSIVE verdicts; BRFSS 2024 produces the suite's most severe Sensitivity failure (max threshold-flip rate 64.2%) after instrument rotation removed hypertension and cholesterol. The pattern recurs on credit- and income-prediction cohorts, confirming domain-agnosticity; a multi-model check shows the failures are data-driven, not model-specific. RISED ships as an open-source Python package complementing TRIPOD+AI, FUTURE-AI, and Fairlearn with the structured numerical evidence those standards require but do not prescribe.

Inverse reinforcement learning (IRL), which infers reward functions from demonstrations, is a valuable tool for modeling and understanding decision-making behavior. Many variants of IRL have been developed to capture complexities of human decision-making, such as subjective beliefs, imperfect planning, and dynamic goals. However, an often-overlooked issue in real-world behavioral datasets is that the recorded data may be missing observations that were available to the original decision-maker. In use-inspired settings such as healthcare, this can make expert actions appear suboptimal, even when they were near-optimal given the information available at the time. As a result, the rewards learned by standard IRL may be misleading. In this paper, we identify the minimal perturbations to the recorded observations needed for the expert's actions to appear optimal. We develop a practical algorithm for this problem and demonstrate its utility for quantifying the possible extent of missing observations in behavioral datasets through extensive experiments on synthetic navigation tasks, a cancer treatment simulator, and ICU treatment data.

Longitudinal clinical notes contain rich evidence of how patients evolve over time, but converting this signal into training supervision for clinical prediction remains challenging. We extend Foresight Learning to clinical prediction by converting time-ordered MIMIC-III notes into examples consisting of past patient context, a natural-language question about a possible future event, and a label resolved from later documentation. This process yields 6,900 prediction examples from 702 admissions across medications, procedures, organ support, microbiology, and mortality. A small LoRA adapter trained on these examples improves over the prompted base model, reducing expected calibration error from 0.1269 to 0.0398 and Brier score from 0.199 to 0.145, while slightly outperforming GPT-5 point estimates on held-out questions. The approach enables reusable clinical prediction supervision from longitudinal notes without hand-engineered structured features or endpoint-specific classifiers.

Foundation diffusion models can generate photorealistic natural images, but adapting them to medical imaging remains challenging. In medical adaptation, limited labeled data can exacerbate hallucination-like and clinically implausible synthesis, while existing metrics such as FID or Inception Score do not quantify per-image alignment with pathology-relevant criteria. We introduce the Clinical Alignment Score (CAS), a foundation-model-based proxy for clinical alignment that evaluates generated images along four complementary dimensions beyond visual fidelity. Building on CAS, we propose Clinical Reward-Aligned Finetuning (CRAFT), a reward-based adaptation framework that transfers medical knowledge from multimodal large language models and vision-language models through label-conditioned prompt enrichment, clinical checklists, and differentiable reward optimization. Across four diverse modalities, CRAFT improves CAS and downstream classification performance over strong adaptation baselines. Beyond average CAS gains, CRAFT reduces the empirical low-alignment tail below a real-image reference threshold by 5.5-34.7% points relative to the strongest baseline, corresponding to a 20.4% average relative reduction across datasets. These results indicate fewer hallucination-like generations under CAS, and are corroborated by out-of-family evaluator evaluation, structured checklist auditing, memorization analysis, and a blinded physician preference study on CheXpert.

Evaluating large language models (LLMs) in the biomedical domain requires benchmarks that can distinguish reasoning from pattern matching and remain discriminative as model capabilities improve. Existing biomedical question answering (QA) benchmarks are limited in this respect. Multiple-choice formats can allow models to succeed through answer elimination rather than inference, while widely circulated exam-style datasets are increasingly vulnerable to performance saturation and training data contamination. Multi-hop reasoning, defined as the ability to integrate information across multiple sources to derive an answer, is central to clinically meaningful tasks such as diagnostic support, literature-based discovery, and hypothesis generation, yet remains underrepresented in current biomedical QA benchmarks. MedHopQA is a disease-centered multi-hop reasoning benchmark consisting of 1,000 expert-curated question-answer pairs introduced as a shared task at BioCreative IX. Each question requires synthesis of information across two distinct Wikipedia articles, and answers are provided in an open-ended free-text format. Gold annotations are augmented with ontology-grounded synonym sets from MONDO, NCBI Gene, and NCBI Taxonomy to support both lexical and concept-level evaluation. MedHopQA was constructed through a structured process combining human annotation, triage, iterative verification, and LLM-as-a-judge validation. To reduce leaderboard gaming and contamination risk, the 1,000 scored questions are embedded within a publicly downloadable set of 10,000 questions, with answers withheld, on a CodaBench leaderboard. MedHopQA provides both a benchmark and a reusable framework for constructing future biomedical QA datasets that prioritize compositional reasoning, saturation resistance, and contamination resistance as core design constraints.

Multi-hop question answering (QA) remains a significant challenge in the biomedical domain, requiring systems to integrate information across multiple sources to answer complex questions. To address this problem, the BioCreative IX MedHopQA shared task was designed to benchmark in multi-hop reasoning for large language models (LLMs). We developed a novel dataset of 1,000 challenging QA pairs spanning diseases, genes, and chemicals, with particular emphasis on rare diseases. Each question was constructed to require two-hop reasoning through the integration of information from two distinct Wikipedia pages. The challenge attracted 48 submissions from 13 teams. Systems were evaluated using both surface string comparison and conceptual accuracy (MedCPT score). The results showed a substantial performance gap between baseline LLMs and enhanced systems. The top-ranked submission achieved an 89.30% F1 score on the MedCPT metric and an 87.30% exact match (EM) score, compared with 67.40% and 60.20%, respectively, for the zero-shot baseline. A central finding of the challenge was that retrieval-augmented generation (RAG) and related retrieval-based strategies were critical for strong performance. In addition, concept-level evaluation improved answer assessment when correct responses differed in surface form. The MedHopQA dataset is publicly available to support continued progress in this important area. Challenge materials: https://www.ncbi.nlm.nih.gov/research/bionlp/medhopqa and benchmark https://www.codabench.org/competitions/7609/

This paper examines what it means for a medical AI system to be right by grounding the question in a specific clinical context: the automatic classification of plasma cells in digitized bone marrow smears for the diagnosis of multiple myeloma. Drawing on philosophy of science and research ethics, the paper argues that correctness in medical AI is not a singular property reducible to benchmark performance, but a multi-dimensional concept involving the availability of expertly labeled medical datasets, the explainability and interpretability of model outputs, the clinical meaningfulness of evaluation metrics, and the distribution of accountability in human-AI workflows. As such, the paper develops this argument through four interrelated themes: the instability of ground truth labels, the opacity of overconfident AI, the inadequacy of standard clinical metrics, and the risk of automation bias in time-pressured clinical settings.

The large-scale deployment of personalized healthcare agents demands memory mechanisms that are exceptionally precise, safe, and capable of long-term clinical tracking. However, existing benchmarks primarily focus on daily open-domain conversations, failing to capture the high-stakes complexity of real-world medical applications. Motivated by the stringent production requirements of an industry-leading health management agent serving tens of millions of active users, we introduce MedMemoryBench. We develop a human-agent collaborative pipeline to synthesize highly realistic, long-horizon medical trajectories based on clinically grounded, synthetic patient archetypes. This process yields a massive, expertly validated dataset comprising approximately 2,000 sessions and 16,000 interaction turns. Crucially, MedMemoryBench departs from traditional static evaluations by pioneering an "evaluate-while-constructing" streaming assessment protocol, which precisely mirrors dynamic memory accumulation in production environments. Furthermore, we formalize and systematically investigate the critical phenomenon of memory saturation, where sustained information influx actively degrades retrieval and reasoning robustness. Comprehensive benchmarking reveals severe bottlenecks in mainstream architectures, particularly concerning complex medical reasoning and noise resilience. By exposing these fundamental flaws, MedMemoryBench establishes a vital foundation for developing robust, production-ready medical agents.

Clinical check-up reports are multimodal documents that combine page layouts, tables, numerical biomarkers, abnormality flags, imaging findings, and domain-specific terminology. Such heterogeneous evidence is difficult for laypersons to interpret and translate into concrete follow-up actions. Although large language models show promise in medical summarisation and triage support, their ability to generate safe, prioritised, and patient-oriented actions from multimodal check-up reports remains under-benchmarked. We present \textbf{Checkup2Action}, a multimodal clinical check-up report dataset and benchmark for structured \textit{Action Card} generation. Each card describes one clinically relevant issue and specifies its priority, recommended department, follow-up time window, patient-facing explanation, and questions for clinicians, while avoiding diagnostic or treatment-prescriptive claims. The dataset contains 2,000 de-identified real-world check-up reports covering demographic information, physical examinations, laboratory tests, cardiovascular assessments, and imaging-related evidence. We formulate checkup-to-action generation as a constrained structured generation task and introduce an evaluation protocol covering issue coverage and precision, priority consistency, department and time recommendation accuracy, action complexity, usefulness, readability, and safety compliance. Experiments with general-purpose and medical large language models reveal clear trade-offs between issue coverage, action correctness, conciseness, and safety alignment. Checkup2Action provides a new multimodal benchmark for evaluating patient-oriented reasoning over clinical check-up reports.

Stain variation across hospitals degrades histopathology models at deployment. Existing augmentation methods perturb color spaces with arbitrary hyperparameters, lacking both a principled budget and coverage guarantees for unseen centers. We propose \textbf{C}alibrated \textbf{A}dversarial \textbf{S}tain \textbf{A}ugmentation (\textbf{CASA}), which performs adversarial augmentation in the Macenko stain parameter space with a budget calibrated from multi-center statistics via the DKW inequality. On Camelyon17-WILDS (5 seeds), CASA achieves $93.9\% \pm 1.6\%$ slide-level accuracy -- outperforming HED-strong ($88.4\% \pm 7.3\%$), RandStainNA ($85.2\% \pm 6.7\%$), and ERM ($63.9\% \pm 11.3\%$) -- with the highest worst-group accuracy ($84.9\% \pm 0.9\%$) among all 10 compared methods.

Medical imaging research has spent a decade getting very good at one thing: producing per-voxel masks. Masks tell us size, volume, and location, and a decade of clinical infrastructure rests on those outputs. Yet the report a radiologist writes contains almost nothing a mask can express. We argue that medical imaging research should adopt medical image parsing as its central output: a structured representation in which entities, attributes, and relationships are emitted together and mutually consistent. Entities are the named structures and findings, present or absent. Attributes describe those entities, capturing things like margin regularity, enhancement pattern, or severity grade. Relationships connect them, naming where one structure sits relative to another, what abuts what, and what has changed since the prior scan. A good parse satisfies three properties, in order: (1) decision (the parse names the right things in the current image), (2) reconstruction (its content is rich enough to regenerate that image), and (3) prediction (its content is rich enough to forecast how the patient state will evolve). Quantitative measurements are derived from this content; they are not predicted alongside it. To test how close the field is to producing such an output, we audit eleven representative systems against the three parsing primitives plus closure. None emits a well-formed parse. Entities are largely solved. Attributes, relationships, and closure remain near-empty. The path forward is not a new architecture. It is a commitment to a richer output, and to training signals that reward it. Segmentation taught models to measure. Parsing asks them to explain.

We introduce AcuityBench, a benchmark for evaluating whether language models identify the appropriate urgency of care from user medical presentations. Existing health benchmarks emphasize medical question answering, broad health interactions, or narrow workflow-specific triage tasks, but they do not offer a unified evaluation of acuity identification across these settings. AcuityBench addresses this gap by harmonizing five public datasets spanning user conversations, online forum posts, clinical vignettes, and patient portal messages under a shared four-level acuity framework ranging from home monitoring to immediate emergency care. The benchmark contains 914 cases, including 697 consensus cases for standard accuracy evaluation and 217 physician-confirmed ambiguous cases for uncertainty-aware evaluation. It supports two complementary task formats: explicit four-way classification in a QA setting, and free-form conversational responses evaluated with a rubric-based judge anchored to the same framework. Across 12 frontier proprietary and open-weight models, we find substantial variation in clear-case acuity accuracy and error direction. Comparing task formats reveals a systematic tradeoff: conversational responses reduce over-triage but increase under-triage relative to QA, especially in higher-acuity cases. In ambiguous cases, no model closely matches the distribution of physician judgments, and model predictions are more concentrated than expert clinical uncertainty. We also compare expert and model adjudication on a subset of maximally ambiguous cases, using those cases to examine the role of clinical uncertainty in label disagreement. Together, these results position acuity identification as a distinct safety-critical capability and show that AcuityBench enables systematic comparison and stress-testing of how well models guide users to the right level of care in real-world health use.

Treating and preventing Human Immunodeficiency Virus (HIV) remains a critical global health challenge. While antiretroviral therapy provides a path toward viral suppression -- effectively eliminating an individual's transmission risk -- systemic resource constraints limit the reach of intervention efforts. This work addresses the strategic distribution of intensive resources among virally unsuppressed individuals to minimize the expected cascade of new infections within a transmission network. We formalize this challenge as a novel constrained optimization problem where we have resources to "treat" $k$ out of a set $\mathbf{P}$ of virally unsuppressed individuals, and establish its theoretical connections to existing computational literature. We then propose Cascade-Aware Suppression of Transmission (CAST), a polynomial-time $(δ, ε)$-approximation algorithm that achieves a $2\sqrt{|\mathbf{P}|}$ approximation ratio by leveraging connections to the Minimum-$k$-Union (MkU) problem and Hoeffding-style concentration bounds. Extensive evaluations on real-world HIV networks demonstrate that CAST outperforms standard public health and computer science baselines. Furthermore, we show that CAST is empirically robust across diverse infectious disease networks, varied edge probability initializations, and settings involving imperfect network data.

Existing medical-agent benchmarks deliver imaging as pre-selected samples, never as an environment the agent must navigate. We introduce ABRA, a radiology-agent benchmark in which the agent operates an OHIF viewer and an Orthanc DICOM server through twenty-one function-calling tools that span slice navigation, windowing, series selection, pixel-coordinate annotation, and structured reporting. ABRA contains 655 programmatically generated tasks across three difficulty tiers and eight types (viewer control, metadata QA, vision probe, annotation, longitudinal comparison, BI-RADS reporting, and oracle variants of annotation and BI-RADS reporting), drawn from LIDC-IDRI, Duke Breast Cancer MRI, and NLST New-Lesion LongCT. Each episode is scored along Planning, Execution, and Outcome (Bluethgen et al., 2025) by task-type-specific automatic scorers. Ten current models, five closed-weight and five open-weight, reach at least 89% Execution on real annotation but only 0-25% Outcome; on the paired oracle variant where a simulated detector supplies the finding, Outcome on the same task reaches 69-100% across the models evaluated, localising the bottleneck to perception rather than tool orchestration. Code, task generators, and scorers are released at https://github.com/Luab/ABRA

Reasoning benchmarks measure clinical performance on clean inputs. We evaluate the step before reasoning: retrieval over real EHR notes, where negation, temporality, and family-versus-patient attribution can flip a correct answer to a wrong one. EpiKG carries an assertion label and a temporality tag with every fact in a patient knowledge graph, then routes retrieval by question intent. ClinicalBench is a 400-question test over 43 MIMIC-IV patients across 9 assertion-sensitive categories. A 7-condition ablation tests each piece of EpiKG across six LLMs (Claude Opus 4.6, GPT-OSS 20B, MedGemma 27B, Gemma 4 31B, MedGemma 1.5 4B, Qwen 3.5 35B). Three physicians blindly adjudicated 100 paired items. The author-blind primary endpoint, leave-author-out paired exact McNemar on 50 unanimous-strict items rated by two external physicians, yields +22.0 percentage points (95 percent Newcombe CI [+5.1, +31.5], p=0.0192). The architectural novelty, intent-aware KG-RAG over a Contriever dense-RAG baseline (C2b to C4g_kw on the change-excluded n=362 endpoint), is +8.84 percentage points (paired McNemar p=1.79e-3); +12.43 percentage points under oracle intent. Sensitivities agree directionally: three-rater physician majority +24.0 percentage points (subject to single-author circularity); deterministic keyword reproducibility proxy +39.5 percentage points. Across the six models, the gain shrinks as the LLM-alone baseline rises (beta=-1.123, r=-0.921, p=0.009). With n=6 this looks more like regression to the mean than encoding substituting for model size. Physician adjudication identified 56 percent of auto-generated reference answers as defective, a methodological finding indicating that NLP-pipeline clinical-QA benchmarks require physician adjudication to be usable. ClinicalBench, the frozen evaluator, three-rater adjudication data, and the EpiKG output stack are publicly released.

Automated question answering (QA) over electronic health records (EHRs) demands precise evidence retrieval, faithful answer generation, and explicit grounding of answers in clinical notes. In this work, we present Neural1.5, our method for the ArchEHR-QA 2026 shared task at CL4Health@LREC 2026, which comprises four subtasks: question interpretation, evidence identification, answer generation, and evidence alignment. Our approach decouples the task into independent, modular stages and employs DSPy"s MIPROv2 optimizer to automatically discover high-performing prompts, jointly tuning instructions and few-shot demonstrations for each stage. Within every stage, self-consistency voting over multiple stochastic inference runs suppresses spurious errors and improves reliability, while stage-specific verification mechanisms (e.g., self-reflection and chain-of-verification for alignment) further refine output quality. Among all teams that participated in all four subtasks, our method ranks second overall (mean rank 4.00), placing 4th, 1st, 4th, and 7th on Subtasks 1-4, respectively. These results demonstrate that systematic, per-stage prompt optimization combined with self-consistency mechanisms is a cost-effective alternative to model fine-tuning for multifaceted clinical QA.

Self-verification, re-invoking the same vision language model (VLM) in a fresh context to check its own generated answer, is increasingly used as a default safety layer for medical visual question answering (VQA). We argue that this practice is fundamentally unreliable. We introduce [METHOD NAME], a diagnostic framework for mapping the reliability boundary of medical VLM self-verification by decomposing verifier behavior into discrimination capability and agreement bias. Because the verifier and answer generator are capacity-coupled, the verifier can overly agree with the generator, creating a verification mirage: a regime with both high verifier error and high agreement bias, driven by false acceptance of incorrect answers. Evaluating six open-weight VLMs across five medical VQA datasets and seven medical tasks, we find that this boundary is strongly task-conditioned. Knowledge-intensive clinical tasks fall deepest into the mirage, simpler tasks are more resistant, and perceptual tasks lie in between. Verification also fails to provide an independent safety signal: logistic mixed-effects analysis shows that verifier error and agreement bias become more likely when the generator is wrong, while saliency analyses show that verifiers under-attend to image evidence relative to generators, a phenomenon we call the lazy verifier. Cross-verification reduces but does not eliminate the mirage. Moreover, when verification is reused in multi-turn actor-verifier loops, most initially wrong answers become locked in by false verification. Since our experiments use clean benchmarks, the observed reliability boundary likely underestimates failures in real clinical deployment.

Joint-embedding predictive architectures (JEPA) learn representations by predicting in latent space, as in computer vision; retaining the action-conditioned predictor at inference turns them into latent world models, enabling planning in robotics (V-JEPA 2-AC). Bringing this design to EHR patient trajectories---a predictor that simulates a patient's trajectory in latent space---has not been explored. We use an LLM as the encoder, reading the hourly record as text, avoiding feature engineering and vocabulary harmonisation. But an LLM adapted by supervised fine-tuning does not organise its latent space around physiological dynamics, and freezing it to train the predictor, as in V-JEPA 2-AC, leaves the encoder unaware of the rollout signal: the predictor degrades under rollout. We instead co-train encoder and predictor under one latent-prediction objective, grounding the encoder in the dynamics its predictor must follow. Naïve co-training, however, is unstable: the untrained predictor drags the encoder toward collapse, and the predictor's rollout diverges as its target space moves. We present Clin-JEPA, a five-phase curriculum that stably co-trains an LLM encoder with a latent trajectory predictor on MIMIC-IV. Three evaluations support the design: (1) under 48-hour autoregressive rollout the co-trained predictor degrades least (predictor degradation $\times$1.06, against $\times$1.23--1.36 for two-stage designs and $\times$6.3--66 for curriculum ablations) while the co-trained encoder resolves the progression of patient state most sharply (largest state displacement); (2) the co-trained encoder separates deteriorating from stable patients in its latent space with Cohen's $d{=}1.59$, against $\leq$0.50 for two-stage encoders; (3) one set of embeddings serves 34 downstream tasks across three benchmarks, outperforming strong per-task tuned baselines and a pretrained EHR foundation model.

Cancer screening is a reasoning task. A radiologist observes findings, compares them to prior scans, integrates clinical context, and reaches a diagnostic conclusion confirmed by pathology. We present RadThinking, a Visual Question Answering (VQA) dataset that makes this reasoning explicit and trainable. RadThinking releases VQA pairs at three difficulty tiers. Foundation VQAs are atomic perception questions. Single-step reasoning VQAs apply one clinical rule. Compositional VQAs require multi-step chain-of-thought to reach a guideline category such as LI-RADS-5. For every compositional VQA, we release the chain of foundation VQAs that solves it. The chain follows the rules of the governing clinical reporting standard. The dataset spans 20,362 CT scans from 9,131 patients across 43 cancer groups, plus 2,077 verified healthy controls with >1-year follow-up. To our knowledge, RadThinking is the first cancer-screening VQA corpus that stratifies questions by reasoning depth and grounds compositions in clinical reporting standards. The foundation tier supplies atomic perception supervision. The compositional tier supplies chain-of-thought data and verifiable rewards for reinforcement-learning recipes such as DeepSeek-R1 and OpenAI o1. RadThinking enables systematic training and evaluation of whether AI systems can reason about cancer, not merely detect it.

Data-driven medical AI is traditionally formulated as a discriminative mapping from input $X$ to output $Y$ via a learned function $f$, which does not generalize well across heterogeneous data and modalities encountered in real-world clinical settings. In this work, we propose a fundamentally different, generative paradigm. We model the joint distribution $P(X,Y)$ using diffusion models and reframe inference as a test-time output optimization problem. By guiding the generative process to match observed inputs, our framework enables flexible, gradient-based conditioning at inference time without architectural changes or retraining, effectively supporting arbitrary and previously unseen combinations of observations. Extensive experiments demonstrate strong performance across standard and cross-modality medical image segmentation, few-shot segmentation with only 2 or 4 training samples, degraded-input segmentation, shape completion from sparse and partial observations, and zero-shot application to demonstrate generality. To support these evaluations, we curated and released a large-scale text-shape dataset derived from MedShapeNet. Our results highlight the versatility of generative joint modeling as a foundation for reusable, task-agnostic medical AI systems.

Medical image segmentation models can perform unevenly across subgroups. Most existing fairness methods focus on improving average subgroup performance, implicitly treating each subgroup as internally homogeneous. However, this can hide difficult cases within a subgroup, where high-loss samples are obscured by the subgroup mean. We call this problem \textbf{intra-group hidden failure}. To solve this, we propose \textbf{DuetFair} mechanism, a dual-axis fairness framework that jointly considers inter-subgroup adaptation and intra-subgroup robustness. Based on DuetFair, we introduce \textbf{FairDRO}, which combines distribution-aware mixture-of-experts (dMoE) with subgroup-conditioned distributionally robust optimization (DRO) loss aggregation. This design allows the model to adapt across subgroups while also reducing hidden failures within each subgroup. We evaluate FairDRO on three medical image segmentation benchmarks with varying degrees of within-group heterogeneity. FairDRO achieves the best equity-scaled performance on Harvard-FairSeg and improves worst-case subgroup performance on HAM10000 under both age- and race-based grouping schemes. On the 3D radiotherapy target cohort, FairDRO further improves worst-group Dice by 3.5 points ($\uparrow 6.0\%$) under the tumor-stage grouping and by 4.1 points ($\uparrow 7.4\%$) under the institution grouping over the strongest baseline.

Training AI models for computational pathology currently requires access to expensive whole-slide-image datasets, GPU infrastructure, deep expertise in machine learning, and substantial engineering effort. We present CellDX AI Autopilot, a platform that lets users -- from pathologists with no ML background to ML practitioners running many parallel experiments -- train, evaluate, and deploy whole-slide image classifiers through natural language interaction with an AI agent. The platform provides a structured set of agent skills that guide the user through dataset curation, automated hyperparameter tuning, multi-strategy model comparison, and human-in-the-loop deployment, all on a pre-built dataset of over 32,000 cases and 66,000 H&E-stained whole-slide images with pre-extracted features. We describe the agent skill architecture, the underlying Multiple Instance Learning (MIL) training framework supporting four classification strategies, and an iterative pairwise hyperparameter search (grid or seeded random) that reduces tuning cost by over 30x compared to exhaustive search. CellDX AI Autopilot is, to our knowledge, the first system to expose pathology-specialized agent skills and a pathology-specialized training platform to general-purpose AI agents (e.g. any LLM-based agent runtime), delivering end-to-end automated model training without requiring the agent itself to be domain-specific. The platform addresses both the ML-expertise bottleneck that limits adoption in diagnostic pathology and the engineering bottleneck that limits how many experiments a researcher can run cost-effectively.

In high-stakes domains such as healthcare, the reliability of Large Language Models (LLMs) is critical, particularly when generating clinical insights from incident reports. This study proposes a tag-based few-shot example selection method for prompting LLMs to generate background/causal factors and preventive measures from details of the medical incidents. For our experiments, we use the Japanese Medical Incident Dataset (JMID), a structured dataset of 3,884 real-world medical accident and near-miss reports. These reports are variably annotated with a wide range of tags--some include descriptive information (e.g., "medications," "blood transfusion therapy"). We compare three few-shot example selection strategies--random sampling, cosine similarity-based selection, and our proposed tag-based method--using GPT-4o and LLaMA 3.3. Results show that the tag-based approach achieves the highest precision and most stable generation behavior, while similarity-based selection often leads to unintended outputs and safety filter activation. These findings suggest that selecting examples based on human-interpretable dataset tags can improve generation precision and stability in clinical LLM applications.

Large vision-language models (VLMs) demonstrate strong performance in medical image understanding, but frequently generate clinically plausible yet incorrect statements, raising significant safety concerns. Existing medical hallucination benchmarks primarily focus on 2D imaging with one-shot diagnostic questions, offering limited insight into whether predictions are grounded in correct localization and abnormality identification, allowing critical reasoning errors to remain hidden behind seemingly correct diagnoses. We introduce Med-StepBench, the first large-scale benchmark for step-wise hallucination detection in 3D oncological PET/CT, comprising over 12,000 images and more than 1,000,000 image-statement pairs across volumetric and multi-view 2D data, which decomposes clinical reasoning into four expert-designed diagnostic stages. Using clinician-verified annotations, we perform the first step-level evaluation of general-purpose and medical VLMs, revealing systematic failure modes obscured by aggregate accuracy metrics. Furthermore, we show that current VLMs are highly susceptible to adversarial yet clinically plausible intermediate explanations, which significantly amplify hallucinations despite contradictory visual evidence. Together, our findings highlight fundamental limitations in grounding multi-step clinical reasoning and establish Med-StepBench as a rigorous benchmark for developing safer and more reliable medical VLMs.

Reinforcement learning (RL) in healthcare has had mixed results, with reward sparsity, unreliable off-policy evaluation, and deployment-simulation gap as recurring failure modes. We argue that chronic disease management is structurally a more tractable RL setting than the acute-care problems the field has primarily studied, but only if the problem is formalized to exploit chronic care's properties. We propose such a formalization. The agent's objective is to compress time-to-control (TTC) under a tiered reward calibrated to the CMS ACCESS Model. Two quantities from our companion preference-learning paper [Singh et al. 2026] enter as load-bearing structural elements: the execution intensity εbounds action availability under a constrained Markov Decision Process, and the clinician capability κweights offline-data transitions during RL training. Together they couple preference learning and RL into a two-loop architecture. We present simulation results on synthetic state machines for hypertension and type 2 diabetes. Capability-weighted offline RL outperforms uniform-weighted offline RL and the behavior policy by 15 percentage points on T2D TTC; the uniform-weighted formulation (the standard in existing healthcare RL) underperforms even the heterogeneous behavior policy. \Epsilon-aware policies generalize across deployment regimes while ε-naive policies do not.

Despite the central role of sensor-derived measurements such as imaging traits and plasma biomarkers in biomedical research and clinical practice, existing generative models for disease prediction largely depend on event-level representations from hospital and registry data. Given the multi-factorial nature of human disease, the absence of explicit modeling of social determinants of health (SDoH), even in the limited form of ICD-coded proxies (chapters Z and V--Y in ICD-10), limits the capacity for personalized disease modeling and clinical decision support. To address this limitation, we propose a generative model with ICD-coded proxies of SDoH for \textit{in silico} modeling of disease reasoning, a conditioned latent diffusion framework that establishes the connection between multi-organ sensor data with tokenized healthcare events. Specifically, we introduce a novel geometric diffusion model to characterize the temporal evolution of complex data representation such as brain networks (region-to-region connectivity encoded in a graph), in parallel with diffusion models for tabular data from other organ systems. Together, we integrate the generative model with digitalized SDoH proxies (coined \modelname{}) for simulated intervention and reasoning of future disease trajectories. We conduct extensive experiments on the UK Biobank (UKB) dataset, which contains organ-specific imaging traits, including brain (44,834), heart (23,987), liver (28,722), and kidney (32,155), along with nearly 500k medical history sequences (age range: 25$\sim$89 years). Our \modelname{} achieves significant improvements over state-of-the-art human disease autoregressive models and imaging trait generative baselines.

Representation learning in electronic health records (EHR) has largely followed paradigms inherited from natural language processing, relying on sequence modeling and reconstruction based objectives that treat clinical labels as ground truth. However, real world clinical supervision is inherently weak, arising from heterogeneous, noisy, and institution specific labeling processes such as billing codes, heuristic phenotypes, and incomplete annotations. In this work, we propose WISTERIA, a weakly supervised representation learning framework that models labels as stochastic observations of an underlying latent clinical state. Instead of optimizing against a single supervision signal, WISTERIA constructs multiple weak supervision operators and learns representations by enforcing consistency across their induced label distributions. This multi view formulation induces an implicit denoising mechanism, allowing the model to recover clinically meaningful structure by reconciling disagreement between noisy labelers. We further incorporate ontology aware regularization in the label space to impose semantic structure over supervision signals. Empirically, WISTERIA improves predictive performance across standard EHR benchmarks, demonstrates strong robustness to label noise, and exhibits superior cross institutional generalization compared to sequence based pretraining objectives. These results suggest that explicitly modeling the supervision process rather than treating labels as fixed targets provides a more appropriate inductive bias for learning robust and clinically meaningful representations from EHR data.