{
  "generated_at": "2026-04-18T11:26:55.465019+08:00",
  "timezone": "Asia/Shanghai",
  "lookback_hours": 24,
  "sorting": {
    "default_sort_by": "hybrid",
    "summary": "hybrid (relevance first, published_at tie-break)",
    "weights": {
      "title_match_weight": 40,
      "summary_match_weight": 18,
      "doi_weight": 12,
      "pdf_weight": 8,
      "rich_summary_weight": 6,
      "metadata_weight": 4,
      "multi_source_weight": 10,
      "freshness_weight_cap": 24
    },
    "feeds": [
      {
        "name": "LLM",
        "sort_by": "hybrid"
      },
      {
        "name": "Vision",
        "sort_by": "hybrid"
      },
      {
        "name": "PubMed AI",
        "sort_by": "hybrid"
      },
      {
        "name": "OpenAlex AI",
        "sort_by": "hybrid"
      }
    ]
  },
  "highlights": [
    "主题「Benchmark」：命中 4 篇，覆盖 PubMed AI，代表论文包括 《Pretraining effective T5 generative models for clinical and biomedical applications.》、《MILU: a consensus ensemble benchmark for multimodal medical imaging lecture understanding.》。",
    "主题「Language Model」：命中 4 篇，覆盖 PubMed AI，代表论文包括 《Pretraining effective T5 generative models for clinical and biomedical applications.》、《MILU: a consensus ensemble benchmark for multimodal medical imaging lecture understanding.》。",
    "主题「Clinical」：命中 2 篇，覆盖 PubMed AI，代表论文包括 《Comparative performance of large language models and Drugs.com versus Lexicomp for antiseizure medication drug-drug interactions: A cross-sectional study with iterative prompting analysis.》、《An explainable multi-head attention network for healthcare IoT threat detection based on the MedDefender-MHAN framework.》。"
  ],
  "focus_items": [],
  "action_items": [],
  "topic_sections": [
    {
      "name": "Benchmark",
      "paper_count": 4,
      "feed_names": [
        "PubMed AI"
      ],
      "paper_titles": [
        "Pretraining effective T5 generative models for clinical and biomedical applications.",
        "MILU: a consensus ensemble benchmark for multimodal medical imaging lecture understanding.",
        "Weakly Supervised Composed Object Re-Identification With Large Models.",
        "An explainable multi-head attention network for healthcare IoT threat detection based on the MedDefender-MHAN framework."
      ],
      "key_points": [
        "《Pretraining effective T5 generative models for clinical and biomedical applications.》〔评测 / 数据 / 应用 / 方法〕：This paper presents a study of the impact of corpus selection and vocabulary design on the performance of T5-based language models in clinical and biomedical d…",
        "《MILU: a consensus ensemble benchmark for multimodal medical imaging lecture understanding.》〔评测 / 应用 / 方法〕：PURPOSE: Vision-language models (VLMs) are increasingly used to interpret multimodal educational materials, yet their reliability on diagram-, equation-, and t…"
      ]
    },
    {
      "name": "Language Model",
      "paper_count": 4,
      "feed_names": [
        "PubMed AI"
      ],
      "paper_titles": [
        "Pretraining effective T5 generative models for clinical and biomedical applications.",
        "MILU: a consensus ensemble benchmark for multimodal medical imaging lecture understanding.",
        "Comparative performance of large language models and Drugs.com versus Lexicomp for antiseizure medication drug-drug interactions: A cross-sectional study with iterative prompting analysis.",
        "Weakly Supervised Composed Object Re-Identification With Large Models."
      ],
      "key_points": [
        "《Pretraining effective T5 generative models for clinical and biomedical applications.》〔评测 / 数据 / 应用 / 方法〕：This paper presents a study of the impact of corpus selection and vocabulary design on the performance of T5-based language models in clinical and biomedical d…",
        "《MILU: a consensus ensemble benchmark for multimodal medical imaging lecture understanding.》〔评测 / 应用 / 方法〕：PURPOSE: Vision-language models (VLMs) are increasingly used to interpret multimodal educational materials, yet their reliability on diagram-, equation-, and t…"
      ]
    },
    {
      "name": "Clinical",
      "paper_count": 2,
      "feed_names": [
        "PubMed AI"
      ],
      "paper_titles": [
        "Comparative performance of large language models and Drugs.com versus Lexicomp for antiseizure medication drug-drug interactions: A cross-sectional study with iterative prompting analysis.",
        "An explainable multi-head attention network for healthcare IoT threat detection based on the MedDefender-MHAN framework."
      ],
      "key_points": [
        "《Comparative performance of large language models and Drugs.com versus Lexicomp for antiseizure medication drug-drug interactions: A cross-sectional study with iterative prompting analysis.》〔评测 / 数据 / 方法〕：BACKGROUND: Antiseizure medications (ASMs) are frequently co-prescribed and are associated with a high risk of clinically significant drug-drug interactions (D…",
        "《An explainable multi-head attention network for healthcare IoT threat detection based on the MedDefender-MHAN framework.》〔评测 / 数据 / 应用 / 方法〕：The rapid proliferation of Internet of Medical Things (IoMT) devices in healthcare environments has created critical cybersecurity vulnerabilities that demand…"
      ]
    }
  ],
  "template": "zh_daily_brief",
  "feeds": [
    {
      "name": "LLM",
      "key_points": [],
      "sort_by": "hybrid",
      "papers": []
    },
    {
      "name": "Vision",
      "key_points": [],
      "sort_by": "hybrid",
      "papers": []
    },
    {
      "name": "PubMed AI",
      "key_points": [
        "《Pretraining effective T5 generative models for clinical and biomedical applications.》〔评测 / 数据 / 应用 / 方法〕：This paper presents a study of the impact of corpus selection and vocabulary design on the performance of T5-based language models in clinical and biomedical d…",
        "《MILU: a consensus ensemble benchmark for multimodal medical imaging lecture understanding.》〔评测 / 应用 / 方法〕：PURPOSE: Vision-language models (VLMs) are increasingly used to interpret multimodal educational materials, yet their reliability on diagram-, equation-, and t…",
        "《Comparative performance of large language models and Drugs.com versus Lexicomp for antiseizure medication drug-drug interactions: A cross-sectional study with iterative prompting analysis.》〔评测 / 数据 / 方法〕：BACKGROUND: Antiseizure medications (ASMs) are frequently co-prescribed and are associated with a high risk of clinically significant drug-drug interactions (D…"
      ],
      "sort_by": "hybrid",
      "papers": [
        {
          "title": "Pretraining effective T5 generative models for clinical and biomedical applications.",
          "summary": "This paper presents a study of the impact of corpus selection and vocabulary design on the performance of T5-based language models in clinical and biomedical domains. We introduce five different T5-EHR models, each pretrained from scratch using different combinations of clinical and biomedical corpora alongside domain-specific vocabularies. We evaluated these models across a variety of clinical and biomedical tasks to quantify the impact of pretraining data and vocabulary tokenization choices on downstream performance. Our findings reveal the importance of aligning both pretraining corpus and vocabulary with the target domain. Models pretrained exclusively on clinical data achieve superior performance on clinical tasks, while adding biomedical data contributes only marginal gains in most cases, with a few exceptions. Similarly, the choice of vocabulary significantly influences model performance, with clinical-specific vocabularies outperforming general biomedical vocabularies in tasks requiring a deeper understanding of clinical language. Also, the T5 generative models perform competitively with state-of-the-art discriminative models on several biomedical benchmarks, demonstrating strong generalization to biomedical domain. Overall, these results emphasize that task-specific selection of corpus and vocabulary is essential for optimizing model performance in clinical and biomedical natural language processing (NLP).",
          "authors": [
            "Saad Althabiti",
            "Chuming Chen",
            "Sultan Alrowili",
            "Cathy Wu",
            "K Vijay-Shanker"
          ],
          "categories": [
            "Journal Article"
          ],
          "paper_id": "pubmed:41996418",
          "abstract_url": "https://pubmed.ncbi.nlm.nih.gov/41996418/",
          "pdf_url": null,
          "published_at": "2026-04-17T13:53:00+00:00",
          "updated_at": "2026-04-17T13:53:00+00:00",
          "source": "pubmed",
          "date_label": "Entered",
          "analysis": null,
          "tags": [
            "评测",
            "数据",
            "应用",
            "方法"
          ],
          "topics": [
            "Benchmark",
            "Language Model"
          ],
          "doi": "10.1371/journal.pone.0342610",
          "arxiv_id": null,
          "source_variants": [
            "pubmed"
          ],
          "source_urls": {
            "pubmed": "https://pubmed.ncbi.nlm.nih.gov/41996418/",
            "doi": "https://doi.org/10.1371/journal.pone.0342610"
          },
          "relevance_score": 108,
          "match_reasons": [
            "title matched \"clinical\"",
            "summary matched \"language model\"",
            "summary matched \"benchmark\"",
            "has DOI",
            "has rich summary",
            "has complete metadata"
          ],
          "feedback_status": null,
          "feedback_note": null,
          "feedback_next_action": null,
          "feedback_due_date": null,
          "feedback_snoozed_until": null,
          "feedback_review_interval_days": null,
          "canonical_id": "doi:10.1371/journal.pone.0342610"
        },
        {
          "title": "MILU: a consensus ensemble benchmark for multimodal medical imaging lecture understanding.",
          "summary": "PURPOSE: Vision-language models (VLMs) are increasingly used to interpret multimodal educational materials, yet their reliability on diagram-, equation-, and text-dense scientific lecture slides remains poorly understood. This work introduces Medical Imaging Lecture Understanding (MILU), a large-scale benchmark designed to characterize cross-model variability in structured understanding of real medical imaging lectures. APPROACH: MILU includes 23 lecture sets with 1117 slides. LLaVA-OneVision, InternVL3-14B, Qwen2-VL-7B, and Qwen3-VL-4B were evaluated using unified prompts to generate structured JSON. We assessed parsing coverage, pairwise agreement, lecture-level patterns, and how outputs aligned with a simple consensus ensemble to identify shared concepts and relations across slides and models effectively. RESULTS: All models produced valid JSON for most slides (92% to 99% coverage), but semantic agreement was extremely low. Pairwise concept Jaccard indices ranged from 0.03 to 0.09, and triple-level F 1 scores from 0.001 to 0.033. Lecture-level patterns revealed higher stability in mathematically structured lectures and lower stability in diagram-heavy content. The consensus ensemble showed modest alignment with individual models (concept Jaccard 0.056 to 0.179; triple F 1 0.014 to 0.044), exposing areas of consistent convergence while also highlighting systematic disagreement. CONCLUSIONS: MILU provides the first comprehensive benchmark for evaluating structured understanding of scientific lecture slides. The results show that current VLMs achieve high formatting reliability but low semantic consistency. MILU establishes a foundation for future expert-annotated benchmarks, diagram- and math-aware modeling, and improved methods for scientific lecture interpretation.",
          "authors": [
            "Md Motaleb Hossen Manik",
            "Md Zabirul Islam",
            "Ge Wang"
          ],
          "categories": [
            "Journal Article"
          ],
          "paper_id": "pubmed:41994492",
          "abstract_url": "https://pubmed.ncbi.nlm.nih.gov/41994492/",
          "pdf_url": null,
          "published_at": "2026-04-17T05:32:00+00:00",
          "updated_at": "2026-04-17T05:32:00+00:00",
          "source": "pubmed",
          "date_label": "Entered",
          "analysis": null,
          "tags": [
            "评测",
            "应用",
            "方法"
          ],
          "topics": [
            "Benchmark",
            "Language Model"
          ],
          "doi": "10.1117/1.jmi.13.6.062202",
          "arxiv_id": null,
          "source_variants": [
            "pubmed"
          ],
          "source_urls": {
            "pubmed": "https://pubmed.ncbi.nlm.nih.gov/41994492/",
            "doi": "https://doi.org/10.1117/1.JMI.13.6.062202"
          },
          "relevance_score": 82,
          "match_reasons": [
            "title matched \"benchmark\"",
            "summary matched \"language model\"",
            "has DOI",
            "has rich summary",
            "has complete metadata"
          ],
          "feedback_status": null,
          "feedback_note": null,
          "feedback_next_action": null,
          "feedback_due_date": null,
          "feedback_snoozed_until": null,
          "feedback_review_interval_days": null,
          "canonical_id": "doi:10.1117/1.jmi.13.6.062202"
        },
        {
          "title": "Comparative performance of large language models and Drugs.com versus Lexicomp for antiseizure medication drug-drug interactions: A cross-sectional study with iterative prompting analysis.",
          "summary": "BACKGROUND: Antiseizure medications (ASMs) are frequently co-prescribed and are associated with a high risk of clinically significant drug-drug interactions (DDIs). Large language models (LLMs) are increasingly used for clinical queries, yet their performance in detecting ASM-related DDIs compared with established drug interaction databases remains uncertain. METHODS: A cross-sectional comparative study evaluated 186 ASM-comedication pairs (126 classified as major/moderate by Lexicomp) using ChatGPT-4, DeepSeek-V3, and Drugs.com, with Lexicomp as the reference standard. Interactions were assessed for presence, severity, mechanism, and management recommendations. Major and moderate interactions were classified as clinically relevant for performance analysis. A post hoc iterative prompting analysis was conducted exclusively on false positive cases to assess improvements in specificity. Performance metrics included sensitivity, specificity, predictive values, and overall accuracy. Two clinical pharmacists independently assessed outputs for accuracy, clarity, and completeness, with adjudication by a third pharmacist. RESULTS: Drugs.com demonstrated the best overall performance, with sensitivity 0.870, specificity 0.629, and accuracy 0.709. ChatGPT showed high sensitivity (0.842) but low specificity (0.358), reflecting frequent over prediction of interactions. Low specificity reflected frequent overclassification of non-interacting or minor pairs as clinically relevant, potentially leading to alert fatigue, unnecessary monitoring or therapeutic modification. DeepSeek achieved the highest sensitivity (0.877) but the lowest specificity (0.200) and the greatest number of false positives. Iterative prompting substantially improved specificity for ChatGPT (0.77) and DeepSeek (0.42), correcting many false positive classifications. CONCLUSION: ChatGPT and DeepSeek provided broad interaction overviews but demonstrated limited specificity under single-prompt conditions. Structured, evidence-constrained prompting improved specificity in false positive cases within this dataset. Drugs.com showed the most balanced performance compared with zero-shot LLM outputs. At present, LLMs may serve as supplementary explanatory tools, whereas structured drug interaction databases remain more reliable for primary DDI screening.",
          "authors": [
            "Maazuddin Mohammed",
            "Mohammed Amer Khan",
            "Vaibhav Chaudhary",
            "Hamzeh Alsaleh",
            "Syeda Bushra Fatima",
            "Biplab Pal"
          ],
          "categories": [
            "Journal Article"
          ],
          "paper_id": "pubmed:41994367",
          "abstract_url": "https://pubmed.ncbi.nlm.nih.gov/41994367/",
          "pdf_url": null,
          "published_at": "2026-04-17T05:31:00+00:00",
          "updated_at": "2026-04-17T05:31:00+00:00",
          "source": "pubmed",
          "date_label": "Entered",
          "analysis": null,
          "tags": [
            "评测",
            "数据",
            "方法"
          ],
          "topics": [
            "Language Model",
            "Clinical"
          ],
          "doi": "10.1016/j.rcsop.2026.100733",
          "arxiv_id": null,
          "source_variants": [
            "pubmed"
          ],
          "source_urls": {
            "pubmed": "https://pubmed.ncbi.nlm.nih.gov/41994367/",
            "doi": "https://doi.org/10.1016/j.rcsop.2026.100733"
          },
          "relevance_score": 82,
          "match_reasons": [
            "title matched \"language model\"",
            "summary matched \"clinical\"",
            "has DOI",
            "has rich summary",
            "has complete metadata"
          ],
          "feedback_status": null,
          "feedback_note": null,
          "feedback_next_action": null,
          "feedback_due_date": null,
          "feedback_snoozed_until": null,
          "feedback_review_interval_days": null,
          "canonical_id": "doi:10.1016/j.rcsop.2026.100733"
        },
        {
          "title": "Weakly Supervised Composed Object Re-Identification With Large Models.",
          "summary": "Existing object re-identification (re-ID) and composed image retrieval (CIR) methods capture different aspects of real-world retrieval requirements; re-ID preserves identity but cannot specify desired appearance changes, whereas CIR supports attribute-guided retrieval but does not enforce identity consistency. To bridge this gap, we introduce composed object re-identification (CORI), a new task that requires the retrieved target to simultaneously satisfy identity preservation and text-guided attribute modification. This problem is fundamentally different from existing re-ID and CIR settings and has not been explicitly studied before. To make CORI feasible without costly manual annotation, we propose a weakly supervised framework that leverages large language models (LLMs) and visual question answering (VQA) models to automatically generate reference-to-target descriptions using ID labels alone. We further develop the first baseline model tailored for CORI, which jointly learns multimodal composition and identity-aware matching through shared-weight image encoders, a text encoder, and a compositor module optimized by contrastive, ID, and triplet losses. We also establish four CORI benchmark datasets covering person and vehicle retrieval. Experiments show that the proposed method consistently outperforms representative baselines adapted from existing CIR and re-ID methods for the newly introduced CORI setting, improving Rank@1 by 2.1% and 0.8% on RAP and Celeb-reID-light, and by 9.9% and 9.5% on VeRi-776 and VRIC, respectively.",
          "authors": [
            "Yan Huang",
            "Jie Lu",
            "Qiang Wu",
            "Guangquan Zhang"
          ],
          "categories": [
            "Journal Article"
          ],
          "paper_id": "pubmed:41996440",
          "abstract_url": "https://pubmed.ncbi.nlm.nih.gov/41996440/",
          "pdf_url": null,
          "published_at": "2026-04-17T13:53:00+00:00",
          "updated_at": "2026-04-17T13:53:00+00:00",
          "source": "pubmed",
          "date_label": "Entered",
          "analysis": null,
          "tags": [
            "评测",
            "数据",
            "方法"
          ],
          "topics": [
            "Benchmark",
            "Language Model"
          ],
          "doi": "10.1109/tcyb.2026.3681841",
          "arxiv_id": null,
          "source_variants": [
            "pubmed"
          ],
          "source_urls": {
            "pubmed": "https://pubmed.ncbi.nlm.nih.gov/41996440/",
            "doi": "https://doi.org/10.1109/TCYB.2026.3681841"
          },
          "relevance_score": 68,
          "match_reasons": [
            "summary matched \"language model\"",
            "summary matched \"benchmark\"",
            "has DOI",
            "has rich summary",
            "has complete metadata"
          ],
          "feedback_status": null,
          "feedback_note": null,
          "feedback_next_action": null,
          "feedback_due_date": null,
          "feedback_snoozed_until": null,
          "feedback_review_interval_days": null,
          "canonical_id": "doi:10.1109/tcyb.2026.3681841"
        },
        {
          "title": "An explainable multi-head attention network for healthcare IoT threat detection based on the MedDefender-MHAN framework.",
          "summary": "The rapid proliferation of Internet of Medical Things (IoMT) devices in healthcare environments has created critical cybersecurity vulnerabilities that demand both accurate and interpretable intrusion detection solutions. Existing deep learning-based intrusion detection systems (IDS) achieve high detection accuracy but lack inherent explainability, limiting their clinical adoption under regulatory frameworks such as GDPR and FDA guidelines. This paper presents MedDefender-MHAN, an explainable multi-head attention network specifically designed for healthcare IoT threat detection. The proposed framework introduces a novel dual-stream architecture that combines convolutional neural networks for local spatial feature extraction with transformer-based encoders for long-range temporal dependency modeling. Unlike existing approaches that apply explainability as a post-hoc process, MedDefender-MHAN embeds interpretability directly into the multi-head attention mechanism, enabling real-time gradient-weighted explanation generation without external XAI pipelines. Evaluated on CICIDS2017 and TON_IoT benchmark datasets, MedDefender-MHAN achieves detection accuracies of 99.47% and 98.92% respectively, with sub-3ms inference latency and a throughput of 435 samples per second. Explainability evaluation demonstrates 94.6% alignment with expert-annotated attack signatures and 91.9% temporal accuracy, outperforming post-hoc methods such as SHAP and Integrated Gradients. These results confirm that MedDefender-MHAN provides a clinically viable, regulatory-compliant security solution for real-world healthcare IoT infrastructure. The proposed framework addresses the dual imperatives of methodological transparency and clinical impact, directly responding to the growing need for trustworthy AI-driven security solutions in regulated healthcare IoMT environments.",
          "authors": [
            "Ali Alqazzaz"
          ],
          "categories": [
            "Journal Article"
          ],
          "paper_id": "pubmed:41996403",
          "abstract_url": "https://pubmed.ncbi.nlm.nih.gov/41996403/",
          "pdf_url": null,
          "published_at": "2026-04-17T13:45:00+00:00",
          "updated_at": "2026-04-17T13:45:00+00:00",
          "source": "pubmed",
          "date_label": "Entered",
          "analysis": null,
          "tags": [
            "评测",
            "数据",
            "应用",
            "方法"
          ],
          "topics": [
            "Benchmark",
            "Clinical"
          ],
          "doi": "10.1371/journal.pone.0346677",
          "arxiv_id": null,
          "source_variants": [
            "pubmed"
          ],
          "source_urls": {
            "pubmed": "https://pubmed.ncbi.nlm.nih.gov/41996403/",
            "doi": "https://doi.org/10.1371/journal.pone.0346677"
          },
          "relevance_score": 68,
          "match_reasons": [
            "summary matched \"benchmark\"",
            "summary matched \"clinical\"",
            "has DOI",
            "has rich summary",
            "has complete metadata"
          ],
          "feedback_status": null,
          "feedback_note": null,
          "feedback_next_action": null,
          "feedback_due_date": null,
          "feedback_snoozed_until": null,
          "feedback_review_interval_days": null,
          "canonical_id": "doi:10.1371/journal.pone.0346677"
        }
      ]
    },
    {
      "name": "OpenAlex AI",
      "key_points": [],
      "sort_by": "hybrid",
      "papers": []
    }
  ]
}