检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wu, Da Wang, Zhanliang Nguyen, Quan Wang, Kai Raymond G. Perelman Center for Cellular and Molecular Therapeutics Children's Hospital of Philadelphia PhiladelphiaPA19104 United States Applied Mathematics and Computational Science Graduate Program University of Pennsylvania PhiladelphiaPA19104 United States Bioengineering Graduate Program University of Pennsylvania PhiladelphiaPA19104 United States Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania PhiladelphiaPA19104 United States

Background: Several studies show that large language models (LLMs) struggle with phenotype-driven gene prioritization for rare diseases. These studies typically use Human Phenotype Ontology (HPO) terms to prompt foundation models like GPT and LLaMA to predict candidate genes. However, in real-world settings, foundation models are not optimized for domain-specific tasks like clinical diagnosis, yet inputs are unstructured clinical notes rather than standardized terms. How LLMs can be instructed to predict candidate genes or disease diagnosis from unstructured clinical notes remains a major challenge. Methods: We introduce RAG-driven CoT and CoT-driven RAG, two methods that combine Chain-of-Thought (CoT) and Retrieval Augmented Generation (RAG) to analyze clinical notes. A five-question CoT protocol mimics expert reasoning, while RAG retrieves data from sources like HPO and OMIM (Online Mendelian Inheritance in Man). We evaluated these approaches on rare disease datasets, including 5,980 Phenopacket-derived notes, 255 literature-based narratives, and 220 in-house clinical notes from Children’s Hospital of Philadelphia. Results: We found that recent foundations models, including Llama 3.3-70B-Instruct and DeepSeek-R1-Distill-Llama-70B, outperformed earlier versions such as Llama 2 and GPT-3.5. We also showed that RAG-driven CoT and CoT-driven RAG both outperform foundation models in candidate gene prioritization from clinical notes;in particular, both methods with DeepSeek backbone resulted in a top-10 gene accuracy of over 40% on Phenopacket-derived clinical notes. RAG-driven CoT works better for high-quality notes, where early retrieval can anchor the subsequent reasoning steps in domain-specific evidence, while CoT-driven RAG has advantage when processing lengthy and noisy notes. Conclusions: Integrating CoT and RAG enhances LLMs’ understanding of clinical notes in the context of rare disease diagnosis, and can facilitate various downstream medical tasks. © 2025, CC

关键词： Chains

来源：评论

学校读者我要写书评

暂无评论

A dive into spectral inference networks: improved algorithms for self-supervised learning of continuous spectral representations

引用

applied mathematics and Mechanics(English Edition) 2023年第7期44卷 1199-1224页

作者： J.WU S.F.WANG P.PERDIKARIS Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania PhiladelphiaPA 19104U.S.A. Department of Mechanical Engineering and Applied Mechanics University of Pennsylvania PhiladelphiaPA 19104U.S.A.

We propose a self-supervising learning framework for finding the dominant eigenfunction-eigenvalue pairs of linear and self-adjoint *** represent target eigenfunctions with coordinate-based neural networks and employ the Fourier positional encodings to enable the approximation of high-frequency *** formulate a self-supervised training objective for spectral learning and propose a novel regularization mechanism to ensure that the network finds the exact eigenfunctions instead of a space spanned by the ***,we investigate the effect of weight normalization as a mechanism to alleviate the risk of recovering linear dependent modes,allowing us to accurately recover a large number of *** effectiveness of our methods is demonstrated across a collection of representative benchmarks including both local and non-local diffusion operators,as well as high-dimensional time-series data from a video *** results indicate that the present algorithm can outperform competing approaches in terms of both approximation accuracy and computational cost.

关键词： spectral learning partial differential equation(PDE) neural network slow features analysis

来源：评论

学校读者我要写书评

暂无评论

Single-scattering optical tomography: Simultaneous reconstruction of scattering and absorption

引用

Physical Review E 2010年第1期81卷 016602-016602页

作者： Lucia Florescu Vadim A. Markel John C. Schotland Department of Bioengineering and Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania Philadelphia Pennsylvania 19104 USA

We report theory and numerical simulations that demonstrate the feasibility of simultaneous reconstruction of the three-dimensional scattering and absorption coefficients of a mesoscopic system using angularly resolved measurements of scattered light. Image reconstruction is based on the inversion of a generalized (broken ray) Radon transform relating the scattering and absorption coefficients of the medium to angularly resolved intensity measurements. Although the single-scattering approximation to the radiative transport equation (RTE) is used to devise the image reconstruction method, there is no assumption that only singly scattered light is measured. That is, no physical mechanism for separating single-scattered photons from the rest of the multiply-scattered light (e.g., time gating) is employed in the proposed experiments. Numerical examples of image reconstruction are obtained using samples of optical depth of up to 3.2. The forward data are obtained from numerical solution of the RTE, accounting for all orders of scattering.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Leveraging undecided cases in chart-reviewed phenotypes to enhance EHR-based association studies

引用

Journal of Biomedical Informatics 2025年 166卷 104839页

作者： Jian, Xinyao Zhang, Dazheng Yu, Zehao Xu, Hua Bian, Jiang Wu, Yonghui Tong, Jiayi Chen, Yong University of Pennsylvania Perelman School of Medicine PhiladelphiaPA United States Department of Biostatistics Epidemiology and Informatics Perelman School of Medicine The University of Pennsylvania PhiladelphiaPA United States Department of Health Outcomes and Biomedical Informatics College of Medicine University of Florida GainesvilleFL United States Department of Biomedical Informatics and Data Science School of Medicine Yale University New HavenCT United States Department of Biostatistics and Health Data Science School of Medicine Indiana University IndianapolisIN United States Regenstreif Institute Indianapolis IndianaIN United States Cancer Informatics Shared Resource University of Florida Health Cancer Center GainesvilleFL United States Department of Biostatistics Johns Hopkins Bloomberg School of Public Health BaltimoreMD United States The Graduate Group in Applied Mathematics and Computational Science School of Arts and Sciences University of Pennsylvania PhiladelphiaPA United States Leonard Davis Institute of Health Economics PhiladelphiaPA United States PhiladelphiaPA United States PhiladelphiaPA United States

Objectives: In electronic health record (EHR)-based association studies, phenotyping algorithms efficiently classify patient clinical outcomes into binary categories but are susceptible to misclassification errors. The gold standard, manual chart review, involves clinicians determining the true disease status based on their assessment of health records. These clinicians-labeled phenotypes are labor-intensive and typically limited to a small subset of patients, potentially introducing a third "undecided" category when phenotypes are indeterminate. We aim to effectively integrate the algorithm-derived and chart-reviewed outcomes when both are available in EHR-based association studies. Material and Methods: We propose an augmented estimation method that combines the binary algorithm-derived phenotypes for the entire cohort with the trinary chart-reviewed phenotypes for a small, selected subset. Additionally, a cost-effective outcome-dependent sampling strategy is used to address the rare disease scenarios. The proposed trinary chart-reviewed phenotype integrated cost-effective augmented estimation (TriCA) was evaluated across a wide range of simulation settings and real-world applications, including using EHR data on Alzheimer's disease and related dementias (ADRD) from the OneFlorida + Clinical Research Network, and using cohort data on second breast cancer events (SBCE) from the Kaiser Permanente Washington. Results: Compared to estimation based on random sampling, our augmented method improved mean square error by up to 28.3% in simulation studies;compared to estimation using only trinary chart-reviewed phenotypes, our method improved efficiency by up to 33.3% in ADRD data and 50.8% in SBCE data. Discussion: Our simulation studies and real-world applications demonstrate that, compared to existing methods, the proposed method provides unbiased estimates with higher statistical efficiency. Conclusion: The proposed method effectively combined binary algorithm-derived

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

Deep learning with Gaussian differential privacy

arXiv

引用

arXiv 2019年

作者： Bu, Zhiqi Dong, Jinshuo Long, Qi Su, Weijie J. Graduate Group in Applied Mathematics and Computational Science Graduate Group in Applied Mathematics and Computational Science Department of Biostatistics Epidemiology and Informatics Department of Statistics

Deep learning models are often trained on datasets that contain sensitive information such as individuals' shopping transactions, personal contacts, and medical records. An increasingly important line of work therefore has sought to train neural networks subject to privacy constraints that are specified by differential privacy or its divergence-based relaxations. These privacy definitions, however, have weaknesses in handling certain important primitives (composition and subsampling), thereby giving loose or complicated privacy analyses of training neural networks. In this paper, we consider a recently proposed privacy definition termed f-differential privacy [17] for a refined privacy analysis of training neural networks. Leveraging the appealing properties of f-differential privacy in handling composition and subsampling, this paper derives analytically tractable expressions for the privacy guarantees of both stochastic gradient descent and Adam used in training deep neural networks, without the need of developing sophisticated techniques as [3] did. Our results demonstrate that the f-differential privacy framework allows for a new privacy analysis that improves on the prior analysis [3], which in turn suggests tuning certain parameters of neural networks for a better prediction accuracy without violating the privacy budget. These theoretically derived improvements are confirmed by our experiments in a range of tasks in image classification, text classification, and recommender systems. Copyright © 2019, The Authors. All rights reserved.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

One-shot distributed ridge regression in high dimensions 37

One-shot distributed ridge regression in high dimensions

引用

37th International Conference on Machine Learning, ICML 2020

作者： Dobriban, Edgar Sheng, Yue Wharton Statistics Department University of Pennsylvania PhiladelphiaPA United States Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania PhiladelphiaPA United States

ISBN: (纸本)9781713821120

To scale up data analysis, distributed and parallel computing approaches are increasingly needed. Here we study a fundamental problem in this area: How to do ridge regression in a distributed computing environment? We study one-shot methods constructing weighted combinations of ridge regression estimators computed on each machine. By analyzing the mean squared error in a high dimensional model where each predictor has a small effect, we discover several new phenomena including that the efficiency depends strongly on the signal strength, but does not degrade with many workers, the risk decouples over machines, and the unexpected consequence that the optimal weights do not sum to unity. We also propose a new optimally weighted one-shot ridge regression algorithm. Our results are supported by simulations and real data analysis. © 2020 37th International Conference on Machine Learning, ICML 2020. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Theoretical and numerical investigation of the size-dependent optical effects in metal nanoparticles

引用

Physical Review B 2011年第15期84卷 155461-155461页

作者： Alexander A. Govyadinov George Y. Panasyuk John C. Schotland Vadim A. Markel Departments of Radiology and Bioengineering and the Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania Philadelphia Pennsylvania 19104 USA

We further develop the theory of quantum finite-size effects in metallic nanoparticles, which was originally formulated by F. Hache, D. Ricard, and C. Flytzanis [J. Opt. Soc. Am. B 3, 1647 (1986)] and (in a somewhat corrected form) by S. G. Rautian [Sov. Phys. JETP 85, 451 (1997)]. These references consider a metal nanoparticle as a degenerate Fermi gas of conduction electrons in an infinitely high spherical potential well. This model (referred to as the HRFR model below) yields mathematical expressions for the linear and the third-order nonlinear polarizabilities of a nanoparticle in terms of infinite nested series. These series have not been evaluated numerically so far and, in the case of nonlinear polarizability, they cannot be evaluated with the use of conventional computers due to the high computational complexity involved. Rautian has derived a set of remarkable analytical approximations to the series but direct numerical verification of Rautian’s approximate formulas remained a formidable challenge. In this work, we derive an expression for the third-order nonlinear polarizability, which is exact within the HRFR model but amenable to numerical implementation. We then evaluate the expressions obtained by us numerically for both linear and nonlinear polarizabilities. We investigate the limits of applicability of Rautian’s approximations and find that they are surprisingly accurate in a wide range of physical parameters. We also discuss the limits of small frequencies (comparable to or below the Drude relaxation constant) and of large particle sizes (the bulk limit) and show that these limits are problematic for the HRFR model, irrespective of any additional approximations used. Finally, we compare the HRFR model to the purely classical theory of nonlinear polarization of metal nanoparticles developed by us earlier [G. Y. Panasyuk, J. C. Schotland, and V. A. Markel, Phys. Rev. Lett. 100, 47402 (2008)].

关键词： NANOPARTICLES ELECTRON gas QUANTUM theory QUANTUM wells APPROXIMATION theory

来源：评论

学校读者我要写书评

暂无评论

Surface plasmon polaritons in curved chains of metal nanoparticles

引用

Physical Review B 2014年第7期90卷 075405-075405页

作者： Ilia L. Rasskazov Sergei V. Karpov Vadim A. Markel Departments of Radiology and Bioengineering and the Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania Philadelphia Pennsylvania 19104 USA

We investigate numerically the propagation of steady-state monochromatic surface plasmon polaritons (SPPs) in curved chains of metal nanoparticles of various spheroidal shapes. We discuss the SPP propagation (decay of the amplitude), the polarization conversion due to coupling of orthogonally polarized SPPs, and the electromagnetic field localization in the near-field vicinity of a chain.

关键词： POLARITONS SURFACE plasmons METAL nanoparticles OPTICAL polarization ELECTROMAGNETIC fields GEOMETRIC modeling

来源：评论

学校读者我要写书评

暂无评论

Quantum theory of the electromagnetic response of metal nanofilms

引用

Physical Review B 2011年第15期84卷 155460-155460页

作者： George Y. Panasyuk John C. Schotland Vadim A. Markel Departments of Radiology Bioengineering and Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania Philadelphia Pennsylvania 19104 USA

We develop a quantum theory of electron confinement in metal nanofilms. The theory is used to compute the nonlinear response of the film to a static or low-frequency external electric field and to investigate the role of boundary conditions imposed on the metal surface. We find that the sign and magnitude of the nonlinear polarizability depends dramatically on the type of boundary condition used.

关键词： QUANTUM theory FIELD theory (Physics) BOUNDARY value problems ELECTRIC fields NONLINEAR models (Statistics)

来源：评论

学校读者我要写书评

暂无评论

Homogenization of Maxwell's equations in periodic composites: Boundary effects and dispersion relations

引用

Physical Review E 2012年第6期85卷 066603-066603页

作者： Vadim A. Markel John C. Schotland []Department of Radiology and Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania Philadelphia Pennsylvania 19104 USA

We consider the problem of homogenizing the Maxwell equations for periodic composites. The analysis is based on Bloch-Floquet theory. We calculate explicitly the reflection coefficient for a half space and derive and implement a computationally efficient continued-fraction expansion for the effective permittivity. Our results are illustrated by numerical computations for the case of two-dimensional systems. The homogenization theory of this paper is designed to predict various physically measurable quantities rather than to simply approximate certain coefficients in a partial differential equation.

关键词： HOMOGENIZATION (Differential equations) MAXWELL equations DISPERSION relations BOUNDARY value problems PERMITTIVITY NUMERICAL analysis PARTIAL differential equations

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：