Patterns最新文献_第10页

UltraLight VM-UNet: Parallel Vision Mamba significantly reduces parameters for skin lesion segmentation. UltraLight VM-UNet：平行视觉曼巴显着减少了皮肤病变分割的参数。

IF 7.4

Patterns Pub Date : 2025-06-26 eCollection Date: 2025-11-14 DOI: 10.1016/j.patter.2025.101298

Renkai Wu, Yinghao Liu, Guochen Ning, Pengchen Liang, Qing Chang

{"title":"UltraLight VM-UNet: Parallel Vision Mamba significantly reduces parameters for skin lesion segmentation.","authors":"Renkai Wu, Yinghao Liu, Guochen Ning, Pengchen Liang, Qing Chang","doi":"10.1016/j.patter.2025.101298","DOIUrl":"10.1016/j.patter.2025.101298","url":null,"abstract":"Traditionally, to improve the segmentation performance of models, most approaches prefer to use more complex modules. This is not suitable for the medical field, especially for mobile medical devices, where computationally loaded models are not suitable for real clinical environments due to computational resource constraints. Recently, state-space models, represented by Mamba, have become a strong competitor to traditional convolutional neural networks and transformers. In this paper, we deeply explore the key elements of parameter influence in Mamba and propose an UltraLight Vision Mamba UNet (UltraLight VM-UNet) based on this. Specifically, we propose a method for processing features in parallel Vision Mamba, named the PVM Layer, which achieves competitive performance with the lowest computational complexity while keeping the overall number of processing channels constant. We conducted segmentation experiments on three public datasets of skin lesions and showed that UltraLight VM-UNet exhibits competitive performance with only 0.049M parameters and 0.060 GFLOPs.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 11","pages":"101298"},"PeriodicalIF":7.4,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12664954/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145655714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Data-driven discovery of medication effects on blood glucose from electronic health records. 从电子健康记录中发现药物对血糖的影响。

IF 7.4

Patterns Pub Date : 2025-06-26 eCollection Date: 2025-11-14 DOI: 10.1016/j.patter.2025.101312

Amanda Momenzadeh, Caleb Cranney, So Yung Choi, Catherine Bresee, Mourad Tighiouart, Roma Gianchandani, Joshua Pevnick, Jason H Moore, Jesse G Meyer

{"title":"Data-driven discovery of medication effects on blood glucose from electronic health records.","authors":"Amanda Momenzadeh, Caleb Cranney, So Yung Choi, Catherine Bresee, Mourad Tighiouart, Roma Gianchandani, Joshua Pevnick, Jason H Moore, Jesse G Meyer","doi":"10.1016/j.patter.2025.101312","DOIUrl":"10.1016/j.patter.2025.101312","url":null,"abstract":"Blood glucose (BG) in hospitalized patients is influenced by numerous clinical factors, including medications not traditionally associated with glycemic control. To better characterize these effects, we analyzed electronic health record data from 97,281 inpatient encounters (2014-2022), capturing 3,009,686 point-of-care BG measurements. We extracted over 300 variables-medications, labs, and socio-demographics-and used Lasso, ridge, and elastic net regression for predictive modeling, alongside propensity score matching (PSM) for causal inference. While Lasso reduced multicollinearity, it often assigned implausible coefficient directions. In contrast, PSM yielded clinically consistent and interpretable estimates, identifying 55 variables significantly associated with BG changes, without shrinking coefficients to zero of known BG-modulating drugs. Findings were validated in a 2022-2024 test set of 27,847 encounters. This work highlights the value of causal inference in observational EHR analysis and identifies both established and under-recognized (e.g., cholecalciferol) medication effects on BG, offering insights that inform safer inpatient glycemic management.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 11","pages":"101312"},"PeriodicalIF":7.4,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12664950/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145655434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A view of the sustainable computing landscape. 对可持续计算前景的看法。

IF 7.4

Patterns Pub Date : 2025-06-25 eCollection Date: 2025-07-11 DOI: 10.1016/j.patter.2025.101296

Benjamin C Lee, David Brooks, Arthur van Benthem, Mariam Elgamal, Udit Gupta, Gage Hills, Vincent Liu, Linh Thi Xuan Phan, Benjamin Pierce, Christopher Stewart, Emma Strubell, Gu-Yeon Wei, Adam Wierman, Yuan Yao, Minlan Yu

{"title":"A view of the sustainable computing landscape.","authors":"Benjamin C Lee, David Brooks, Arthur van Benthem, Mariam Elgamal, Udit Gupta, Gage Hills, Vincent Liu, Linh Thi Xuan Phan, Benjamin Pierce, Christopher Stewart, Emma Strubell, Gu-Yeon Wei, Adam Wierman, Yuan Yao, Minlan Yu","doi":"10.1016/j.patter.2025.101296","DOIUrl":"10.1016/j.patter.2025.101296","url":null,"abstract":"This article presents a holistic research agenda to address the significant environmental impact of information and communication technology (ICT), which accounts for 2.1%-3.9% of global greenhouse gas emissions. It proposes several research thrusts to achieve sustainable computing: accurate carbon accounting models, life cycle design strategies for hardware, efficient use of renewable energy, and integrated design and management strategies for next-generation hardware and software systems. If successful, the research would flatten and reverse growth trajectories for computing power and carbon, especially for rapidly growing applications like artificial intelligence. The research takes a holistic approach because strategies that reduce operational carbon may increase embodied carbon, and vice versa. Achieving these goals will require interdisciplinary collaboration between computer scientists, electrical engineers, environmental scientists, and economists.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 7","pages":"101296"},"PeriodicalIF":7.4,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12416076/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145030916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

cytoGPNet: Enhancing clinical outcome prediction accuracy using longitudinal cytometry data in small cohort studies. cytoGPNet：在小队列研究中使用纵向细胞术数据提高临床预后预测的准确性。

IF 7.4

Patterns Pub Date : 2025-06-25 eCollection Date: 2025-09-12 DOI: 10.1016/j.patter.2025.101297

Jingxuan Zhang, Liwen Sun, Neal E Ready, Wenbo Guo, Lin Lin

{"title":"cytoGPNet: Enhancing clinical outcome prediction accuracy using longitudinal cytometry data in small cohort studies.","authors":"Jingxuan Zhang, Liwen Sun, Neal E Ready, Wenbo Guo, Lin Lin","doi":"10.1016/j.patter.2025.101297","DOIUrl":"10.1016/j.patter.2025.101297","url":null,"abstract":"Cytometry data, including flow and mass cytometry, are widely used in immunological studies such as cancer immunotherapy and vaccine trials. These data provide rich insights into immune cell dynamics and their relationship to clinical outcomes. However, traditional analyses based on summary statistics may overlook critical single-cell information. To address this, we introduce cytoGPNet, a novel method for predicting individual-level outcomes from cytometry data. cytoGPNet addresses four key challenges: (1) accommodating varying numbers of cells per sample, (2) analyzing longitudinal cytometry data to capture temporal patterns, (3) maintaining robustness despite limited sample sizes, and (4) ensuring interpretability for biomarker discovery. We apply cytoGPNet across multiple immunological studies with diverse designs and show that it consistently outperforms existing methods in predictive accuracy. Importantly, cytoGPNet also offers interpretable insights at multiple levels, enhancing our understanding of immune responses. These results highlight cytoGPNet's potential to advance cytometry-based analysis in immunological research.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 9","pages":"101297"},"PeriodicalIF":7.4,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12485536/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145214030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

S2S: A deep learning method for the radiological diagnosis of fine-grained diseases spanning screening to subtyping. S2S：一种跨越筛查到分型的细粒度疾病放射诊断的深度学习方法。

IF 7.4

Patterns Pub Date : 2025-06-17 eCollection Date: 2025-10-10 DOI: 10.1016/j.patter.2025.101294

Ruijie Tang, Yuchen Guo, Hengrui Liang, Jianxing He, Yuerong Lizhu, Yaou Liu, Feng Xu

{"title":"S2S: A deep learning method for the radiological diagnosis of fine-grained diseases spanning screening to subtyping.","authors":"Ruijie Tang, Yuchen Guo, Hengrui Liang, Jianxing He, Yuerong Lizhu, Yaou Liu, Feng Xu","doi":"10.1016/j.patter.2025.101294","DOIUrl":"10.1016/j.patter.2025.101294","url":null,"abstract":"Radiographic images play a critical role in disease diagnosis, but accurately interpreting them requires considerable expertise and workload. Recent research has advanced artificial intelligence-based medical image analysis, but such advancements remain limited in real clinical practice where multistage diagnosis is required for fine-grained diseases. This study proposes a screening-to-subtyping (S2S) AI paradigm specifically designed for accurate radiological diagnosis of fine-grained diseases, encompassing the entire diagnostic process from initial screening to final subtyping. The S2S framework integrates information from multiple diagnostic phases, radiological viewpoints, lesion dimensions, and imaging modalities to address complex diagnostic challenges. Evaluation using a large-scale, multi-center radiography dataset of fine-grained thoracic cancer subtypes demonstrates the system's robust performance. Furthermore, this investigation offers novel insights into human-AI collaboration for diagnosing intricate fine-grained pathologies. Our results highlight the substantial clinical potential of S2S AI across varied healthcare environments and disease entities, facilitating deeper integration of artificial intelligence in radiological diagnostics.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 10","pages":"101294"},"PeriodicalIF":7.4,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12546454/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145372850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Coordination of network heterogeneity and individual preferences promotes collective fairness. 网络异质性与个体偏好的协调促进了集体公平。

IF 7.4

Patterns Pub Date : 2025-06-16 eCollection Date: 2025-11-14 DOI: 10.1016/j.patter.2025.101293

Xiao Han, Shangmei Ma, Wen-Xu Wang, Angel Sánchez, H Eugene Stanley, Shinan Cao, Boyu Zhang

引用次数: 0

⁠Advancing ethical AI in healthcare through interpretability. 通过可解释性推进医疗保健领域的伦理AI。

IF 6.7

Patterns Pub Date : 2025-06-13 DOI: 10.1016/j.patter.2025.101290

Yilin Ning, Mingxuan Liu, Nan Liu

引用次数: 0

Tokenized and continuous embedding compressions of protein sequence and structure. 蛋白质序列和结构的标记化和连续嵌入压缩。

IF 6.7

Patterns Pub Date : 2025-06-13 DOI: 10.1016/j.patter.2025.101289

Amy X Lu, Wilson Yan, Kevin K Yang, Vladimir Gligorijevic, Kyunghyun Cho, Pieter Abbeel, Richard Bonneau, Nathan C Frey

{"title":"Tokenized and continuous embedding compressions of protein sequence and structure.","authors":"Amy X Lu, Wilson Yan, Kevin K Yang, Vladimir Gligorijevic, Kyunghyun Cho, Pieter Abbeel, Richard Bonneau, Nathan C Frey","doi":"10.1016/j.patter.2025.101289","DOIUrl":"10.1016/j.patter.2025.101289","url":null,"abstract":"Existing protein machine learning representations typically model either the sequence or structure distribution, with the other modality implicit. Here, we characterize an embedding of the joint distribution of protein sequence and structure by compressing the latent space of the protein folding model ESMFold. This provides mechanistic interpretability insights, as well as a flexible compressed representation. We term these CHEAP (compressed hourglass embedding adaptations of proteins) embeddings. In continuous compression schemes, the ESMFold latent space can be reduced by factors of 128 <math><mrow><mo>×</mo></mrow> </math> along the channel and 8 <math><mrow><mo>×</mo></mrow> </math> along the length while retaining structure information at <2 Å scale accuracy and performing competitively on protein function and localization benchmarks. In discrete compression schemes, we construct a tokenized all-atom structure vocabulary that retains high reconstruction accuracy, thus introducing a tokenized representation of an all-atom structure that can be obtained from the sequence alone. CHEAP democratizes representations captured by large models and can enable flexible downstream applications such as generation, search, and prediction.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 6","pages":"101289"},"PeriodicalIF":6.7,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12191763/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144508675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Highlighting the achievements and impact of women in data science. 突出女性在数据科学领域的成就和影响。

IF 7.4

Patterns Pub Date : 2025-06-13 DOI: 10.1016/j.patter.2025.101263

Lauren Higa, Youping Deng

引用次数: 0

DiffuSETS: 12-Lead ECG generation conditioned on clinical text reports and patient-specific information. DiffuSETS: 12导联心电图生成条件下的临床文本报告和患者的具体信息。

IF 7.4

Patterns Pub Date : 2025-06-11 eCollection Date: 2025-10-10 DOI: 10.1016/j.patter.2025.101291

Yongfan Lai, Jiabo Chen, Qinghao Zhao, Deyun Zhang, Yue Wang, Shijia Geng, Hongyan Li, Shenda Hong

{"title":"DiffuSETS: 12-Lead ECG generation conditioned on clinical text reports and patient-specific information.","authors":"Yongfan Lai, Jiabo Chen, Qinghao Zhao, Deyun Zhang, Yue Wang, Shijia Geng, Hongyan Li, Shenda Hong","doi":"10.1016/j.patter.2025.101291","DOIUrl":"10.1016/j.patter.2025.101291","url":null,"abstract":"The scarcity of high-quality electrocardiogram (ECG) data, driven by privacy concerns and limited medical resources, creates a pressing need for effective ECG signal generation. Existing approaches for generating ECG signals typically rely on small training datasets, lack comprehensive evaluation frameworks, and overlook potential applications beyond data augmentation. To address these challenges, we propose DiffuSETS, a framework capable of generating ECG signals with high semantic alignment and fidelity. DiffuSETS accepts various modalities of clinical text reports and patient-specific information as inputs, enabling the creation of clinically meaningful ECG signals. Additionally, we introduce a comprehensive benchmarking methodology to assess the effectiveness of ECG generative models. Our model achieves excellent results in tests, proving its superiority in the task of ECG generation. Furthermore, we showcase its potential to mitigate data scarcity while exploring applications in cardiology education and medical knowledge discovery.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 10","pages":"101291"},"PeriodicalIF":7.4,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12546759/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145379116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0