How to determine when data incompleteness compromises the correct training of data-enhanced mechanical models of haemodialysis? A data quality criterion [0.03%]
如何确定数据不完整影响血液透析数据增强机械模型正确训练的时机？一个数据质量标准
Lavinia Maria Pizzi,Carlo Balsamello,Andrea Ambrosini et al.
Lavinia Maria Pizzi et al.
Objective: Hemodialysis is essential for managing end-stage renal disease, with rising patient numbers increasing the need for individualized treatment. To support this, hybrid models-integrating mechanistic frameworks wi...
Heterogeneous domain adaptation survival analysis with partially observed outcomes via dictionary learning and distribution alignment [0.03%]
基于字典学习和分布对齐的异构领域适应生存分析算法
Dan Ni Lin,Dongping Du,Nandini Nair
Dan Ni Lin
Domain adaptation (DA) aligns learned representations so that predictive models generalize across domains with differing population characteristics, particularly when limited target-domain data prevents training domain-specific models. DA i...
Sparse autoencoders reveal interpretable cell-type programs in single-cell foundation model representations [0.03%]
稀疏自编码器揭示单细胞基础模型表示中的可解释细胞类型程序
Ihor Kendiukhov
Ihor Kendiukhov
Objective: Single-cell foundation models such as scGPT learn rich representations of cellular identity, yet the biological programs encoded in their internal activations remain opaque. We investigate whether sparse autoen...
DispFormer: A dual attention transformer with denoising for biomedical irregular time series classification [0.03%]
DispFormer：一种用于生物医学不规则时间序列分类的去噪双注意力变压器
Junjie Zhang,Xuan Zang,Hao Chen et al.
Junjie Zhang et al.
Electronic Health Records (EHRs) collected in intensive care units (ICUs) consist of irregular multivariate time series (IMTS), where measurements are recorded asynchronously and missingness is pervasive. These characteristics pose signific...
Mitigating hallucinations in synthesized clinical texts to improve multimodal deep learning for dermatology [0.03%]
通过改善合成临床文本中的幻觉以提高皮肤病学的多模态深度学习性能
Niccolo Marini,Zhaohui Liang,Sivaramakrishnan Rajaraman et al.
Niccolo Marini et al.
Objective: Despite recent advancements in the development of foundation models and multimodal (MM) architectures in dermatology, their translation to clinical practice remains limited by the scarcity of large-scale multim...
Optimising clinical information extraction: a comparative study of retrieval-augmented generation techniques in clinical notes [0.03%]
优化临床信息提取：临床笔记中检索增强生成技术的比较研究
Hengyi Zhang,Dinithi Vithanage,Chao Deng et al.
Hengyi Zhang et al.
Extracting clinically meaningful information from free-text notes in specific clinical settings, such as Australian aged care facilities, remains challenging due to the heterogeneity of text documents, which lack standardised structure and ...
CBFI: A multi-layer gene network key node identification algorithm integrating structural-biological features and dynamic regulatory weights [0.03%]
CBFI：一种融合结构生物属性和动态调控权重的多层基因网络关键节点识别算法
Yue Li,Junkai Kang,Xiaoyi Zhang
Yue Li
Objective: Identifying key nodes within multi-layer GRNs is crucial for uncovering potential biomarkers and therapeutic targets. Key nodes exhibit bothlocal structural advantages (e.g., bridging weak connections, disease ...
Automated identification of incidentalomas requiring follow-up: A multi-anatomy evaluation of LLM-based and supervised approaches [0.03%]
基于LLM和有监督方法的意外发现病变自动识别与随访评估研究
Namu Park,Farzad Ahmed,Zhaoyi Sun et al.
Namu Park et al.
Objective: To evaluate large language models (LLMs) against supervised baselines for fine-grained, lesion-level detection of incidentalomas requiring follow-up, addressing the limitations of current document-level classif...
Are LLM-generated plain language summaries truly understandable? A large-scale crowdsourced evaluation [0.03%]
LLM生成的通俗语言摘要真的易懂吗？一项大规模众包评估
Yue Guo,Jae Ho Sohn,Gondy Leroy et al.
Yue Guo et al.
Plain language summaries (PLSs) are essential for facilitating effective communication between clinicians and patients by making complex medical information easier for laypeople to understand and act upon. Large language models (LLMs) have ...
High-quality data selection-driven instruction tuning for biomedical large language models [0.03%]
基于高质量数据选择的指令微调用于生物医学大型语言模型
Jieqiong Zheng,Lu Sun,Xinyu He et al.
Jieqiong Zheng et al.
This study presents a novel data selection framework for enhancing the training efficiency of large language models (LLMs) in biomedical natural language processing (NLP) tasks. We focus on critical tasks sourced from the biomedical dataset...