❌

Normal view

Received — 20 January 2026 ⏭ Favourites

UroFusion-X: a unified multimodal deep learning framework for robust diagnosis, subtyping, and prognosis of urological cancers

✇npj Digital Medicine
By: Yingming Xiao · Shengke Yang · Mingjing He · Li Chen · Yi Wu · Lei Zhong
19 January 2026 at 08:00

npj Digital Medicine, Published online: 19 January 2026; doi:10.1038/s41746-025-02295-6

UroFusion-X: a unified multimodal deep learning framework for robust diagnosis, subtyping, and prognosis of urological cancers
Received — 4 December 2025 ⏭ Favourites

AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys

✇cs.AI, q-bio.NC updates on arXiv.org
By: Siyi Wu · Chiaxin Liang · Ziqian Bi · Leyi Zhao · Tianyang Wang · Junhao Song · Yichao Zhang · Keyu Chen · Benji Peng · Xinyuan Song
3 December 2025 at 13:00
arXiv:2510.26012v3 Announce Type: replace Abstract: The rapid growth of research literature, particularly in large language models (LLMs), has made producing comprehensive and current survey papers increasingly difficult. This paper introduces autosurvey2, a multi-stage pipeline that automates survey generation through retrieval-augmented synthesis and structured evaluation. The system integrates parallel section generation, iterative refinement, and real-time retrieval of recent publications to ensure both topical completeness and factual accuracy. Quality is assessed using a multi-LLM evaluation framework that measures coverage, structure, and relevance in alignment with expert review standards. Experimental results demonstrate that autosurvey2 consistently outperforms existing retrieval-based and automated baselines, achieving higher scores in structural coherence and topical relevance while maintaining strong citation fidelity. By combining retrieval, reasoning, and automated evaluation into a unified framework, autosurvey2 provides a scalable and reproducible solution for generating long-form academic surveys and contributes a solid foundation for future research on automated scholarly writing. All code and resources are available at https://github.com/annihi1ation/auto_research.
Received — 19 November 2025 ⏭ Favourites

Synthetic Clinical Notes for Rare ICD Codes: A Data-Centric Framework for Long-Tail Medical Coding

✇cs.AI, q-bio.NC updates on arXiv.org
By: Truong Vo · Weiyi Wu · Kaize Ding
19 November 2025 at 13:00
arXiv:2511.14112v1 Announce Type: cross Abstract: Automatic ICD coding from clinical text is a critical task in medical NLP but remains hindered by the extreme long-tail distribution of diagnostic codes. Thousands of rare and zero-shot ICD codes are severely underrepresented in datasets like MIMIC-III, leading to low macro-F1 scores. In this work, we propose a data-centric framework that generates high-quality synthetic discharge summaries to mitigate this imbalance. Our method constructs realistic multi-label code sets anchored on rare codes by leveraging real-world co-occurrence patterns, ICD descriptions, synonyms, taxonomy, and similar clinical notes. Using these structured prompts, we generate 90,000 synthetic notes covering 7,902 ICD codes, significantly expanding the training distribution. We fine-tune two state-of-the-art transformer-based models, PLM-ICD and GKI-ICD, on both the original and extended datasets. Experiments show that our approach modestly improves macro-F1 while maintaining strong micro-F1, outperforming prior SOTA. While the gain may seem marginal relative to the computational cost, our results demonstrate that carefully crafted synthetic data can enhance equity in long-tail ICD code prediction.
Received — 3 September 2025 ⏭ Favourites

Protein lipoylation in cancer: metabolic reprogramming and therapeutic potential

✇Cell Death Discovery nature.com science feeds
By: Sainan Li · Yingchao Liu · Wanye Hu · Aoli Deng · Xueying Ren · Lulu Chen · Yajuan Lu · Yunyi Wu · Hangqi Huang · Jinghao Cao · Jing Du · Jun Xia · Yanchun Li
2 September 2025 at 08:00

Cell Death Discovery, Published online: 02 September 2025; doi:10.1038/s41420-025-02718-z

Protein lipoylation in cancer: metabolic reprogramming and therapeutic potential
Received — 16 June 2025 ⏭ Favourites

Advances in molecular pathology and therapy of non-small cell lung cancer

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Qing Huang · Yuanxiang Li · Yingdan Huang · Jingyi Wu · Wendai Bao · Chang Xue · Xiaoyu Li · Shuang Dong · Zhiqiang Dong · Sheng Hu
14 June 2025 at 18:00

Signal Transduct Target Ther. 2025 Jun 15;10(1):186. doi: 10.1038/s41392-025-02243-6.

ABSTRACT

Over the past two decades, non-small cell lung cancer (NSCLC) has witnessed encouraging advancements in basic and clinical research. However, substantial unmet needs remain for patients worldwide, as drug resistance persists as an inevitable reality. Meanwhile, the journey towards amplifying the breadth and depth of the therapeutic effect requires comprehending and integrating diverse and profound progress. In this review, therefore, we aim to comprehensively present such progress that spans the various aspects of molecular pathology, encompassing elucidations of metastatic mechanisms, identification of therapeutic targets, and dissection of spatial omics. Additionally, we also highlight the numerous small molecule and antibody drugs, encompassing their application alone or in combination, across later-line, frontline, neoadjuvant or adjuvant settings. Then, we elaborate on drug resistance mechanisms, mainly involving targeted therapies and immunotherapies, revealed by our proposed theoretical models to clarify interactions between cancer cells and a variety of non-malignant cells, as well as almost all the biological regulatory pathways. Finally, we outline mechanistic perspectives to pursue innovative treatments of NSCLC, through leveraging artificial intelligence to incorporate the latest insights into the design of finely-tuned, biomarker-driven combination strategies. This review not only provides an overview of the various strategies of how to reshape available armamentarium, but also illustrates an example of clinical translation of how to develop novel targeted drugs, to revolutionize therapeutic landscape for NSCLC.

PMID:40517166 | PMC:PMC12167388 | DOI:10.1038/s41392-025-02243-6

There are no more articles
❌