TRACER is a training‑free multimodal harness that builds minute‑level action records from continuous video and merges them with clinical data into hourly reports, enabling an LLM agent to query and inspect both modalities. In evaluation, TRACER achieved up to 84.8% accuracy on action detection and 61.0% accuracy on clinician‑informed QA, outperforming the strongest baseline. Across 280 patients and ~60,000 camera‑hours, TRACER detected significantly less purposeful activity in patients with a positive delirium assessment compared to those without (p < 0.0001).
arXiv:2607. 01751v1 Announce Type: cross Abstract: Existing medical video benchmarks primarily evaluate whether a model produces the correct answer, but rarely assess whether it answers at the right time.
arXiv:2605.11533v4 Announce Type: replace Abstract: Routine clinical check-up reports combine laboratory measurements, physiological assessments, imaging findings and visually structured information,...
The paper introduces structured evidence routing for incident risk prediction using multimodal longitudinal electronic health records (EHRs). It proposes a router‑predictor‑reviewer workflow that condenses full patient records into compact summaries and targeted evidence slices, enabling a predictor to generate evidence‑linked risk assessments that a reviewer can critique. Experiments on five one‑year incident diagnosis tasks show that the method matches the AUROC of established supervised EHRSHOT baselines and remains competitive on AUPRC, while providing a patient‑specific evidence trail.
arXiv:2506. 04831v3 Announce Type: replace Abstract: Forecasting how a patient's condition is likely to evolve, including possible deterioration, recovery, treatment needs, and care transitions, could support more proactive and personalized care, but requires modeling heterogeneous and longitudinal electronic health record (EHR) data.
arXiv:2607. 09982v1 Announce Type: new Abstract: Electronic health record (EHR) data are inherently multimodal, and leveraging multiple modalities can improve predictive performance.
arXiv:2605.06537v2 Announce Type: replace Abstract: Medical multimodal large language models (MLLMs) have advanced image understanding and short-video analysis, but real clinical review often require...
In clinical practice, patients often undergo multiple imaging examinations over successive visits, yielding longitudinal data. Modeling such temporal information is crucial for reliable assessment of disease progression and treatment response.
arXiv:2607. 09142v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in online medical consultation, yet existing benchmarks remain poorly aligned with real clinical practice.
arXiv:2608. 14157v1 Announce Type: new Abstract: Mechanical ventilation is a critical life-support intervention, requiring dynamic adjustments to ventilator settings as a patient's condition evolves.
arXiv:2607. 25933v1 Announce Type: cross Abstract: Clinical diagnostic evaluation should not only assess whether models can provide correct diagnoses, but also reflect the realities of clinical practice, including progressive disclosure of multimodal information, dynamic updating of diagnostic hypotheses, and continuous refinement of clinical reasoning.
arXiv:2607. 09880v1 Announce Type: cross Abstract: Clinical time series are central to patient monitoring, risk assessment, and clinical decision support.
ActiveMedAgent is a cost‑aware framework that guides multimodal medical AI to acquire diagnostic evidence sequentially, mirroring clinical practice of escalating from cheap to costly tests. It uses a frozen vision‑language model to track diagnosis probabilities, scores each potential acquisition by diagnostic utility minus cost, and trains a lightweight MLP controller offline to decide when to request more evidence or to stop. Experiments on three benchmarks show that trajectory‑based policy learning outperforms unguided acquisition and full‑modality baselines, revealing an information overload effect where the agent can correctly diagnose with fewer channels than the full‑modality approach.