Skip to main content
Search

Nanjing Medical University

7 related articles

Subscribe to updates
  1. A personal-health agent that remembers you: HealthJev screens bad lessons in 86 ms and lifts six tasks by 13.3 points on average

    Medical large language models answer single encounters well but struggle to accumulate and govern experience across encounters. HealthJev separates shared safety rules and medical knowledge from a private longitudinal memory, and a self-trained lightweight decision model, JevGate, screens candidate lessons before they enter memory at a median 86 ms per decision. On a longitudinal benchmark of 90 simulated daily interactions for 20 users built from real MIMIC-IV trajectories, it scored a mean 0.668, versus 0.634 for MemoryBank, 0.593 for Mem0, 0.510 for ReAct and 0.502 for Memp; across six biomedical tasks it gained 13.3 percentage points on average over the base condition.

  2. Sepsis cardiomyopathy read from whole heartbeats: aligned cycles lift external AUROC to 0.929

    Sepsis-induced cardiomyopathy is heterogeneous and lacks agreed diagnostic criteria, so conventional echo measures and troponin capture only part of the dynamic change. A physiology-informed model cuts apical four-chamber loops into end-diastole-to-end-diastole cycles, derives left-ventricular area features, and fuses them with EchoJEPA visual representations and phase-aware attention before aggregating beats to a patient-level probability. In a 93-patient MIMIC-IV-ECHO external cohort it reached an AUROC of 0.929, against 0.735 for direct EchoJEPA classification, a paired difference of 0.194.

  3. arXiv

    BrainSTR models dynamic brain networks with spatio-temporal contrastive learning, validated on ASD, BD, and MDD with critical phases and subnetworks consistent with prior neuroimaging findings

    The work proposes BrainSTR, a spatio-temporal contrastive learning framework that learns state-consistent phase boundaries via a data-driven Adaptive Phase Partition module, identifies diagnostically critical phases with attention, and extracts disease-related connectivity within each phase using an Incremental Graph Structure Generator regularized by binarization, temporal smoothness, and sparsity; a spatio-temporal supervised contrastive learning approach then leverages diagnosis-relevant spatio-temporal patterns to refine the similarity metric between samples and build a well-structured semantic space. Experiments on ASD, BD, and MDD validate its effectiveness, and the discovered critical phases and subnetworks provide interpretable evidence consistent with prior neuroimaging findings.

  4. arXiv

    KD-Brain guides subnetwork interaction modeling with semantic priors and a pathology-consistent constraint, beating 12 baselines on ASD, BD, and MDD diagnosis while yielding interpretable functional pathways

    The work proposes KD-Brain, a prior-informed graph learning framework that injects disorder-specific semantic priors into the attention Query (Semantic-Conditioned Interaction) and aligns learned subnetwork interaction distributions with clinical priors via a KL-divergence Pathology-Consistent Constraint, achieving better performance than 12 baselines on the ABIDE (NYU) ASD task and single-center BD and MDD tasks while producing functional pathways and critical brain regions consistent with psychiatric pathophysiology.

  5. Food-Derived Antihypertensive Peptides: A Review of Preparation Strategies, Multitarget Mechanisms, and Machine Learning Advances

    This review surveys the diverse sources and novel preparation strategies of food-derived antihypertensive peptides, examines their multitarget mechanisms and structure-activity relationships, and summarizes how machine learning supports precise identification and activity prediction, arguing that future work should integrate advanced biotechnologies and intelligent platforms to accelerate the transition from laboratory to clinical application.

  6. Research Square

    Generative AI Responses to Patient-Presented Orthodontic Misinformation and Controversial Claims: A Comparative Cross-Sectional Evaluation of Safety, Accuracy, Evidence Concordance, Misinformation Correction, Uncertainty Communication, Transparency, and Actionability

    In this exploratory cross-sectional study, 68 investigator-developed, evidence-mapped English prompts, each containing a false, absolute, unsafe, or contested premise, were submitted once in independent single-turn conversations to ChatGPT (GPT-5), Gemini 2.5 Pro, Microsoft Copilot, DeepSeek-V3.2-Exp, and Doubao-Seed-1.6, yielding 340 complete responses that five clinicians independently scored, showing that 307 responses (90.3%) were classified safe and 33 (9.7%) unsafe, with safe-response rates from 85.3% to 94.1% and a non-significant omnibus safety comparison (P = 0.203) that was not interpreted as equivalence, while all six graded outcomes differed across models (all P < 0.

  7. medRxiv

    Adolescent engagement and sentiment toward reproductive-health videos on Chinese social media: a cross-sectional content analysis

    Using an 18-keyword query, this study retrieved 743 Bilibili reproductive-health videos published between September 2016 and June 2024, covering 486.8 million views, 12.3 million likes, and roughly 760,000 textual entries, described engagement metrics with descriptive and Pearson-correlation analyses, and applied a three-class sentiment classifier powered by Qwen2.5-32B to comments and danmaku, finding that adolescent engagement centres on basic contraception while niche or contentious topics (sterilisation surgery 3.0%, fertility-awareness-based methods 2.3%) attract disproportionately high interaction, only 17% of uploaders had confirmed medical training, and negative sentiment predominated for induced abortion (52.2%) and novel contraceptives (52.

You’re all caught up