发布求助
文献互助 智能选刊 最新文献

Patterns最新文献

筛选
英文 中文
When accurate prediction models yield harmful self-fulfilling prophecies. 当准确的预测模型产生有害的自我实现预言时。
IF 6.7
Patterns Pub Date : 2025-04-11 DOI: 10.1016/j.patter.2025.101229
Wouter A C van Amsterdam, Nan van Geloven, Jesse H Krijthe, Rajesh Ranganath, Giovanni Cinà
{"title":"When accurate prediction models yield harmful self-fulfilling prophecies.","authors":"Wouter A C van Amsterdam, Nan van Geloven, Jesse H Krijthe, Rajesh Ranganath, Giovanni Cinà","doi":"10.1016/j.patter.2025.101229","DOIUrl":"https://doi.org/10.1016/j.patter.2025.101229","url":null,"abstract":"<p><p>Prediction models are popular in medical research and practice. Many expect that by predicting patient-specific outcomes, these models have the potential to inform treatment decisions, and they are frequently lauded as instruments for personalized, data-driven healthcare. We show, however, that using prediction models for decision-making can lead to harm, even when the predictions exhibit good discrimination after deployment. These models are harmful self-fulfilling prophecies: their deployment harms a group of patients, but the worse outcome of these patients does not diminish the discrimination of the model. Our main result is a formal characterization of a set of such prediction models. Next, we show that models that are well calibrated before and after deployment are useless for decision-making, as they make no change in the data distribution. These results call for a reconsideration of standard practices for validation and deployment of prediction models that are used in medical decisions.</p>","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 4","pages":"101229"},"PeriodicalIF":6.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12010445/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144051728","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
Can an accurate model be bad? 一个准确的模型会是坏的吗？
IF 6.7
Patterns Pub Date : 2025-04-11 DOI: 10.1016/j.patter.2025.101205
Melissa D McCradden, Mjaye L Mazwi, Lauren Oakden-Rayner
{"title":"Can an accurate model be bad?","authors":"Melissa D McCradden, Mjaye L Mazwi, Lauren Oakden-Rayner","doi":"10.1016/j.patter.2025.101205","DOIUrl":"https://doi.org/10.1016/j.patter.2025.101205","url":null,"abstract":"<p><p>Outcome-prediction models can harm patients even when they have good accuracy, as shown in a recent <i>Patterns</i> paper by Van Amsterdam et al. In this preview, we consider the ethical and empirical implications of this work by highlighting the impact of reifying self-fulfilling prophecies and propose a reorientation toward actions over accuracy as a priority for AI integration.</p>","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 4","pages":"101205"},"PeriodicalIF":6.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12010442/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144062726","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
Toward automated and explainable high-throughput perturbation analysis in single cells. 迈向自动化和可解释的单细胞高通量扰动分析。
IF 6.7
Patterns Pub Date : 2025-04-11 DOI: 10.1016/j.patter.2025.101228
Jesus Gonzalez-Ferrer, Mohammed A Mostajo-Radji
{"title":"Toward automated and explainable high-throughput perturbation analysis in single cells.","authors":"Jesus Gonzalez-Ferrer, Mohammed A Mostajo-Radji","doi":"10.1016/j.patter.2025.101228","DOIUrl":"https://doi.org/10.1016/j.patter.2025.101228","url":null,"abstract":"<p><p>Perturbation analysis in single-cell RNA sequencing (scRNA-seq) data is challenging due to the complexity of cellular responses. To address this, Xu and Fleming et al. developed CellCap, a generative deep-learning model that decodes the perturbation effect on a particular cell state. CellCap extracts interpretable latent representations of perturbation response modules, identifying key cellular pathways activated under various conditions. This allows for a deeper understanding of cell-state-specific responses to genetic, chemical, or biological perturbations.</p>","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 4","pages":"101228"},"PeriodicalIF":6.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12010446/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144062727","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
Nature visible only digitally. 只有数字才能看到自然。
IF 6.7
Patterns Pub Date : 2025-04-11 DOI: 10.1016/j.patter.2025.101210
Yasuhiro Iba, Aya Kubota, Yusuke Takeda, Mehmet Oguz Derin, Shin Ikegami, Jörg Mutterlose, Takahiro Harada, Tomonori Takeuchi, Kazuki Tainaka
{"title":"Nature visible only digitally.","authors":"Yasuhiro Iba, Aya Kubota, Yusuke Takeda, Mehmet Oguz Derin, Shin Ikegami, Jörg Mutterlose, Takahiro Harada, Tomonori Takeuchi, Kazuki Tainaka","doi":"10.1016/j.patter.2025.101210","DOIUrl":"https://doi.org/10.1016/j.patter.2025.101210","url":null,"abstract":"<p><p>Recent progress in imaging technology has enabled paleontologists to visualize all fossils inside solid rocks. Consequently, we can now imagine the natural worlds hidden not only inside our research materials but also within the opaque solids of everyday life. Here, we introduce the unique visual-spatial worlds that emerge from inside rocks and the creativity this discovery fosters.</p>","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 4","pages":"101210"},"PeriodicalIF":6.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12010443/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144044393","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
RePower: An LLM-driven autonomous platform for power system data-guided research. RePower：一个llm驱动的电力系统数据导向研究自主平台。
IF 6.7
Patterns Pub Date : 2025-03-31 eCollection Date: 2025-04-11 DOI: 10.1016/j.patter.2025.101211
Yu-Xiao Liu, Mengshuo Jia, Yong-Xin Zhang, Jianxiao Wang, Guannan He, Shao-Long Zhong, Zhi-Min Dang
{"title":"RePower: An LLM-driven autonomous platform for power system data-guided research.","authors":"Yu-Xiao Liu, Mengshuo Jia, Yong-Xin Zhang, Jianxiao Wang, Guannan He, Shao-Long Zhong, Zhi-Min Dang","doi":"10.1016/j.patter.2025.101211","DOIUrl":"https://doi.org/10.1016/j.patter.2025.101211","url":null,"abstract":"<p><p>Large language models (LLMs) have shown strong capabilities across disciplines such as chemistry, mathematics, and medicine, yet their application in power system research remains limited, and most studies still focus on supporting specific tasks under human supervision. Here, we introduce Revive Power Systems (RePower), an autonomous LLM-driven research platform that uses a reflection-evolution strategy to independently conduct complex research in power systems. RePower assists researchers by controlling devices, acquiring data, designing methods, and evolving algorithms to address problems that are difficult to solve but easy to evaluate. Validated on three critical data-driven tasks in power systems-parameter prediction, power optimization, and state estimation-RePower outperformed traditional methods. Consistent performance improvements were observed across multiple tasks, with an average error reduction of 29.07%. For example, in the power optimization task, the error decreased from 0.00137 to 0.000825, a reduction of 39.78%. This framework facilitates autonomous discoveries, promoting innovation in power systems research.</p>","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 4","pages":"101211"},"PeriodicalIF":6.7,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12010440/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144051820","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
Erratum: Data shadows: When data become tangible, material, and fragile. 勘误：数据阴影：当数据变得有形、物质和脆弱时。
IF 6.7
Patterns Pub Date : 2025-03-27 eCollection Date: 2025-04-11 DOI: 10.1016/j.patter.2025.101230
Paul Trauttmansdorff, Kim M Hajek
{"title":"Erratum: Data shadows: When data become tangible, material, and fragile.","authors":"Paul Trauttmansdorff, Kim M Hajek","doi":"10.1016/j.patter.2025.101230","DOIUrl":"https://doi.org/10.1016/j.patter.2025.101230","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.1016/j.patter.2025.101206.].</p>","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 4","pages":"101230"},"PeriodicalIF":6.7,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12010441/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144046948","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
Navigating COP16's digital sequence information outcomes: What researchers need to do in practice. 导航COP16的数字序列信息结果：研究人员在实践中需要做什么。
IF 6.7
Patterns Pub Date : 2025-03-14 DOI: 10.1016/j.patter.2025.101208
Melania Muñoz-García, Amber Hartman Scholz
{"title":"Navigating COP16's digital sequence information outcomes: What researchers need to do in practice.","authors":"Melania Muñoz-García, Amber Hartman Scholz","doi":"10.1016/j.patter.2025.101208","DOIUrl":"10.1016/j.patter.2025.101208","url":null,"abstract":"<p><p>The UN Convention on Biological Diversity adopted new rules for sharing benefits from publicly available genetic sequence data, also known as digital sequence information (DSI). In this Opinion, the authors describe the key elements researchers need to be aware of, address real-life questions, and explain the practical implications of these rules for research and development.</p>","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 3","pages":"101208"},"PeriodicalIF":6.7,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11963070/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143781263","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
Quantifying extreme failure scenarios in transportation systems with graph learning. 用图学习量化交通系统的极端故障情况。
IF 6.7
Patterns Pub Date : 2025-03-14 eCollection Date: 2025-04-11 DOI: 10.1016/j.patter.2025.101209
Mingxue Guo, Tingting Zhao, Jianxi Gao, Xin Meng, Ziyou Gao
{"title":"Quantifying extreme failure scenarios in transportation systems with graph learning.","authors":"Mingxue Guo, Tingting Zhao, Jianxi Gao, Xin Meng, Ziyou Gao","doi":"10.1016/j.patter.2025.101209","DOIUrl":"https://doi.org/10.1016/j.patter.2025.101209","url":null,"abstract":"<p><p>Statistical analysis of extreme events in complex engineering systems is essential for system design and reliability and resilience assessment. Due to the rarity of extreme events and the computational burden of system performance evaluation, estimating the probability of extreme failures is prohibitively expensive. Traditional methods, such as importance sampling, struggle with the high cost of deriving importance sampling densities for numerous components in large-scale systems. Here, we propose a graph learning approach, called importance sampling based on graph autoencoder (GAE-IS), to integrate a modified graph autoencoder model, termed a criticality assessor, with the cross-entropy-based importance sampling method. GAE-IS effectively decouples the criticality of components from their vulnerability to disastrous events in the workflow, demonstrating notable transferability and leading to significantly reduced computational costs of importance sampling in large-scale networks. The proposed methodology improves sampling efficiency by one to two orders of magnitude across several road networks and provides more accurate probability estimations.</p>","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 4","pages":"101209"},"PeriodicalIF":6.7,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12010444/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143989254","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
Strategies to include prior knowledge in omics analysis with deep neural networks. 在深度神经网络组学分析中包含先验知识的策略。
IF 6.7
Patterns Pub Date : 2025-03-14 DOI: 10.1016/j.patter.2025.101203
Kisan Thapa, Meric Kinali, Shichao Pei, Augustin Luna, Özgün Babur
{"title":"Strategies to include prior knowledge in omics analysis with deep neural networks.","authors":"Kisan Thapa, Meric Kinali, Shichao Pei, Augustin Luna, Özgün Babur","doi":"10.1016/j.patter.2025.101203","DOIUrl":"10.1016/j.patter.2025.101203","url":null,"abstract":"<p><p>High-throughput molecular profiling technologies have revolutionized molecular biology research in the past decades. One important use of molecular data is to make predictions of phenotypes and other features of the organisms using machine learning algorithms. Deep learning models have become increasingly popular for this task due to their ability to learn complex non-linear patterns. Applying deep learning to molecular profiles, however, is challenging due to the very high dimensionality of the data and relatively small sample sizes, causing models to overfit. A solution is to incorporate biological prior knowledge to guide the learning algorithm for processing the functionally related input together. This helps regularize the models and improve their generalizability and interpretability. Here, we describe three major strategies proposed to use prior knowledge in deep learning models to make predictions based on molecular profiles. We review the related deep learning architectures, including the major ideas in relatively new graph neural networks.</p>","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 3","pages":"101203"},"PeriodicalIF":6.7,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11963003/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143781268","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 shadows: When data become tangible, material, and fragile. 数据阴影：当数据变得有形、物质化和脆弱时。
IF 6.7
Patterns Pub Date : 2025-03-14 DOI: 10.1016/j.patter.2025.101206
Paul Trauttmansdorff, Kim M Hajek
{"title":"Data shadows: When data become tangible, material, and fragile.","authors":"Paul Trauttmansdorff, Kim M Hajek","doi":"10.1016/j.patter.2025.101206","DOIUrl":"10.1016/j.patter.2025.101206","url":null,"abstract":"","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"6 3","pages":"101206"},"PeriodicalIF":6.7,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11963112/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143781251","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
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信