Melissa D McCradden,Mjaye L Mazwi,Lauren Oakden-Rayner
Melissa D McCradden
Outcome-prediction models can harm patients even when they have good accuracy, as shown in a recent Patterns paper by Van Amsterdam et al. In this preview, we consider the ethical and empirical implications of this work by highlighting the ...
Yasuhiro Iba,Aya Kubota,Yusuke Takeda et al.
Yasuhiro Iba et al.
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 soli...
Insights into transportation CO2 emissions with big data and artificial intelligence [0.03%]
基于大数据和人工智能的交通运输二氧化碳排放研究
Zhenyu Luo,Tingkun He,Zhaofeng Lv et al.
Zhenyu Luo et al.
The ever-increasing stream of big data offers potential for deep decarbonization in the transportation sector but also presents challenges in extracting interpretable insights due to its complexity and volume. This overview discusses the ap...
When accurate prediction models yield harmful self-fulfilling prophecies [0.03%]
当精确的预测模型产生有害的自我实现预言时
Wouter A C van Amsterdam,Nan van Geloven,Jesse H Krijthe et al.
Wouter A C van Amsterdam et al.
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 perso...
RePower: An LLM-driven autonomous platform for power system data-guided research [0.03%]
基于LLM的自主平台促进电力系统数据指导研究：RePower
Yu-Xiao Liu,Mengshuo Jia,Yong-Xin Zhang et al.
Yu-Xiao Liu et al.
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...
Pouria Saidi,Gautam Dasarathy,Visar Berisha
Pouria Saidi
Machine learning (ML) is increasingly used across many disciplines with impressive reported results. However, recent studies suggest that the published performances of ML models are often overoptimistic. Validity concerns are underscored by...
Toward automated and explainable high-throughput perturbation analysis in single cells [0.03%]
迈向单细胞高通量扰动分析的自动化和可解释性
Jesus Gonzalez-Ferrer,Mohammed A Mostajo-Radji
Jesus Gonzalez-Ferrer
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 per...
Erratum: Data shadows: When data become tangible, material, and fragile [0.03%]
撤回：数据具象化：当数据成为有形的、物质的和脆弱的时候
Paul Trauttmansdorff,Kim M Hajek
Paul Trauttmansdorff
[This corrects the article DOI: 10.1016/j.patter.2025.101206.]. © 2025 The Author(s).
Published Erratum
Patterns (New York, N.Y.). 2025 Mar 27;6(4):101230. DOI:10.1016/j.patter.2025.101230 2025
Quantifying extreme failure scenarios in transportation systems with graph learning [0.03%]
基于图神经网络的交通系统极端故障场景量化研究
Mingxue Guo,Tingting Zhao,Jianxi Gao et al.
Mingxue Guo et al.
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 evaluatio...
Bi-level graph learning unveils prognosis-relevant tumor microenvironment patterns in breast multiplexed digital pathology [0.03%]
多层次图学习揭示乳腺多重数字化病理肿瘤微环境预后相关模式
Zhenzhen Wang,Cesar A Santa-Maria,Aleksander S Popel et al.
Zhenzhen Wang et al.
The tumor microenvironment (TME) is widely recognized for its central role in driving cancer progression and influencing prognostic outcomes. Increasing efforts have been dedicated to characterizing it, including its analysis with modern de...