检索结果-内蒙古大学图书馆

computational modeling Approaches to Characterize Risk and Achieve Safe, Effective, and Trusted Designs in the Development of Artificial Intelligence and Autonomous Closed Loop Medical Systems

Computational Modeling Approaches to Characterize Risk and A...

引用

Conference on Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications III

作者： Papadopoulos, Amy Salinas, Jose Crump, Cindy US Army Med Res & Dev Command Ft Detrick MD USA US Army Inst Surg Res Houston TX USA Express Networks LLC Washington DC 20002 USA

ISBN: (数字)9781510643307

ISBN: (纸本)9781510643307

While software using artificial intelligence and machine learning (AI/ML) is pervasive in many areas of society today, the use of these technologies to diagnose and treat medical conditions is limited due to a number of challenges associated with the trustworthiness of the results. This may include the inability to fully explain how an algorithm works inherent to the black-box nature of the system. Additionally, AI/ML may create a potential for bias and artifacts that cannot be validated due to the same limitations. In a medical application, the lack of transparency in how the system operates may lead to a loss of trust by users. Bayesian approaches that use computational modeling to quantify the level of uncertainty in a given result may provide a path towards improved confidence and use. In this paper, evidence from studies in a range of medical applications is presented and discussed, showing how Bayesian approaches can help to foster trust. A retrospective study using a publicly available dataset explored the feasibility of creating predictive models for early intervention in a Type 1 diabetes population. Creating the perfect model was not the goal of the exercise, rather the study aimed to demonstrate how Bayesian methods could be used to identify areas of uncertainty during model development. Feature selection was based on analytical assessment of various patterns found in the data. Models were trained, validated, and tested, generating uncertainty estimates. A two-feature Gaussian Naive Bayes (GNB) model, using the previous five minutes and ten minutes of blood glucose values, showed similar results for predictive accuracy as a three-feature model that included average change over the preceding 30 minutes. The two-feature model was selected because it allowed for a more easily understood visualization of uncertainty. The 2-feature GNB achieved an AUC = .94. The model showed good sensitivity for exceeding the > 180 mg/dl limit, obtaining threshold prediction =

关键词： computational modeling Regulatory Science Assured Autonomy Bayesian Models Artificial Intelligence Machine Learning Physiological Closed Loop Control

来源：评论

学校读者我要写书评

暂无评论

Characterization and computational modeling of continuous-fiber prepreg ply-ply interaction behavior

引用

COMPOSITES PART A-APPLIED SCIENCE AND MANUFACTURING 2024年 176卷

作者： Yang, Yunpei Colton, Jonathan Georgia Inst Technol Atlanta GA 30332 USA

Ply-ply interaction behavior critically affects wrinkle formation during composite forming. This paper presents a computational model of the ply-ply interaction behavior of woven thermoset prepreg fabrics. The computational model includes visco-elastic, pressure-sensitive adhesion behavior, as well as a yield behavior that allows the deformation to transition from adhesion to friction. The model is based on the analysis and observations of double-lap shear factor effect screening tests and of total slip test measurements. To validate the computational model, finite element simulations are compared to experimental response surface tests for various pressures and deformation rates. The comparison shows that the computational model closely captures the load-deformation response of the ply-ply interaction. This computational model can be used in a forming process simulation to predict wrinkle formations.

关键词： Prepreg computational modeling Defect Forming

来源：评论

学校读者我要写书评

暂无评论

Editorial: computational modeling and machine learning methods in neurodevelopment and neurodegeneration: from basic research to clinical applications

引用

FRONTIERS IN computational NEUROSCIENCE 2024年 18卷 1514220页

作者： Montobbio, Noemi Maffulli, Roberto Abrol, Anees Martinez-Canada, Pablo Univ Genoa Dept Hlth Sci DISSAL Genoa Italy EXUS AI Labs London England Georgia State Univ Ctr Translat Res Neuroimaging & Data Sci Atlanta GA USA Univ Granada Res Ctr Informat & Commun Technol CIT Granada Spain Univ Granada Dept Comp Engn Automat & Robot Granada Spain

The effective application of computational approaches still faces several challenges, including: the multiple spatial scales involved; the issue of interpretability of machine learning models, hampering transferability to clinical practice; and the lack of robust validation of non-invasive biomarkers of neural disorders. These challenges motivated us to edit the Research Topic "computational modeling and Machine Learning Methods in Neurodevelopment and Neurodegeneration: from Basic Research to Clinical Applications", culminating with the acceptance of 10 insightful papers that explore the subject from diverse perspectives using various innovative *** contributions covered a variety of themes, including disease diagnosis (Ruppert-Junk et al., Turrisi et al., Fernández-Ruiz et al.) Computer-aided diagnosis, as well as disease subtype or stage classification, are among the most frequently addressed tasks in machine learning studies in healthcare (Chan et al., 2020). In the present Research Topic, the study by Ruppert-Junk et al. investigated the use of [ 18 F]-FDG PET imaging to diagnose Parkinson's disease (PD) by focusing on midbrain metabolism, particularly in the substantia nigra. A machine learning model using random forest classification achieved high sensitivity and accuracy in distinguishing PD patients from healthy controls. Fernández-Ruiz et al. introduced a non-invasive method for identifying Smith-Magenis syndrome using machine learning techniques, focusing on cepstral peak prominence (CPP) from voice samples. The study significantly contributes to the theme of using computational methods for neurodevelopmental conditions by offering a potential clinical application for early diagnosis . Chen et al. explored the use of graph-based convolutional networks (GCNs) to classify multiple sclerosis (MS) clinical forms based on brain morphological connectivity from T1-weighted MRI data. The authors show how the approach outperforms stat

关键词： computational modeling machine learning neurodevelopmental disorders neurodegeneration clinical

来源：评论

学校读者我要写书评

暂无评论

Ring only repair of bileaflet mitral valve prolapse with mitral regurgitation: Insights from computational modeling

引用

JOURNAL OF BIOMECHANICS 2024年 176卷 112366-112366页

作者： Zeira, Adi White Weissmann, Jonathan Galili, Lee Ram, Eilon Raanani, Ehud Schwammenthal, Ehud Marom, Gil Tel Aviv Univ Sch Mech Engn Tel Aviv Israel Tel Aviv Univ Dept Biomed Engn Tel Aviv Israel Chaim Sheba Med Ctr Leviev Cardiothorac & Vasc Ctr Tel Hashomer Israel Tel Aviv Univ Sackler Sch Med Tel Aviv Israel

This study evaluates the efficacy of annuloplasty repair as a standalone procedure for treating bileaflet mitral valve prolapse with mitral regurgitation (MR). Various flexible ring bands for MR of different severities were compared to assess their biomechanical impact and treatment outcomes. computational beating heart models, based on the Living Heart Human Model, were utilized to simulate annuloplasty repairs. Repairs using bands of varying lengths were modeled on moderate and severe MR cases, considering bileaflet mitral valve prolapse. Key parameters, including regurgitant orifice area (ROA), prolapse severity, coaptation length, leaflet position, and deformation, were computed to compare conditions before and after implantation. Annuloplasty repairs effectively reduced the ROA in both moderate and severe MR cases, achieving complete sealing in selective instances. Additionally, annuloplasty repair corrected bileaflet prolapse, with prolapse severity decreasing as the annular size increased. Successful coaptation was indicated by the expansion of each leaflet's contact area distribution and percentage in contact with the opposing leaflet. The risk of systolic anterior motion, that may obstruct the left ventricular outflow tract, was minimized, as the anterior leaflet was directed towards the posterior position. In conclusion, annuloplasty repair alone can effectively treat MR when an appropriate band length is selected. It facilitates a significant reduction in ROA, correction of bileaflet prolapse, and improvement in leaflet coaptation. These findings have important clinical implications, potentially offering a less complex surgical treatment avenue and reducing complications in the management of MR.

关键词： Annuloplasty Mitral regurgitation Barlow disease Bileaflet prolapse Mitral valve repair Ring-only repair computational modeling

来源：评论

学校读者我要写书评

暂无评论

From experimental testing to computational modeling: A review of shape memory alloy fiber-reinforced concrete composites

引用

COMPOSITES PART B-ENGINEERING 2024年 281卷

作者： Tabrizikahou, Alireza Kuczma, Mieczyslaw Czaderski, Christoph Shahverdi, Moslem Poznan Univ Tech Inst Bldg Engn Piotrowo 5 PL-60965 Poznan Poland Empa Swiss Fed Labs Mat Sci & Technol CH-8600 Dubendorf Switzerland Univ Tehran Sch Civil Engn Tehran 456311155 Iran

Shape memory alloys (SMAs) have unique characteristics, such as the shape memory effect, which allows them to recover their initial shape after being deformed when stimulated, and pseudoelasticity, which enables them to accommodate large deformation without residual strains after being unloaded. SMAs may be used as short fibers in fiber -reinforced concrete (FRC) composites to pre -stress, heal fractures, and recenter themselves. As a result, SMA-FRC is a potential alternative to conventional construction materials in a wide range of applications. SMA-FRC composite application and modeling may present challenges, such as computational modeling complexities, practical constraints regarding fiber volume fraction, fiberto -concrete adhesion strength, and the complex temperature -based activation of SMA fibers embedded in concrete. Despite these challenges and difficulties, significant work toward resolution is being made, making SMA-FRC an innovative technology with many potential research and development alternatives. This article presents an overview of experimental testing, computational methods, limitations, and future research potential for SMA-FRC composite materials. The study also looks at practical applications of SMA fibers in concrete composites including beam-column junctions, pre -stressing, and self -healing, as well as major developments and implications. The advantages and limits of several computational strategies for studying SMA-FRCs are discussed. The research suggests multiscale modeling as an effective approach for analyzing SMA-FRC, and a unique example of SMA-FRC multiscale modeling is briefly demonstrated. In conclusion, this research emphasizes the significant potential of SMA-FRC composites as novel construction materials with prospective practical applications, as well as the importance of multiscale modeling in SMA-FRC computational modeling.

关键词： Fiber-reinforced concrete (FRC) Shape memory alloy (SMA) Experimental tests computational modeling Multiscale method

来源：评论

学校读者我要写书评

暂无评论

computational modeling of Embodied Visual Perspective Taking

引用

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 2020年第4期12卷 723-732页

作者： Fischer, Tobias Demiris, Yiannis Imperial Coll London Personal Robot Lab Dept Elect & Elect Engn London SW7 2BT England

Humans are inherently social beings that benefit from their perceptional capability to embody another point of view, typically referred to as perspective taking. Perspective taking is an essential feature in our daily interactions and is pivotal for human development. However, much remains unknown about the precise mechanisms that underlie perspective taking. Here, we show that formalizing perspective taking in a computational model can detail the embodied mechanisms employed by humans in perspective taking. The model's main building block is a set of action primitives that are passed through a forward model. The model employs a process that selects a subset of action primitives to be passed through the forward model to reduce the response time. The model demonstrates the results that mimic those captured by human data, including response times differences caused by the angular disparity between the perspective-taker and the other agent, the impact of task-irrelevant body posture variations in perspective taking, and differences in the perspective taking strategy between individuals. Our results provide support for the hypothesis that perspective taking is a mental simulation of the physical movements that are required to match another person's visual viewpoint. Furthermore, the model provides several testable predictions, including the prediction that forced early responses lead to an egocentric bias and that a selection process introduces dependencies between two consecutive trials. Our results indicate potential links between perspective taking and other essential perceptional and cognitive mechanisms, such as active vision and autobiographical memories.

关键词： computational modeling Time factors Robots Visualization Predictive models Task analysis Torso computational modeling forward models perspective taking social psychology visual perception

来源：评论

学校读者我要写书评

暂无评论

New mechanistic insights of nanoplastics synergistic cadmium induced overactivation of trypsin: Joint analysis from protein multi-level conformational changes and computational modeling

引用

JOURNAL OF HAZARDOUS MATERIALS 2024年 480卷 135817页

作者： Li, Xiangxiang Wang, Yanzhe Hu, Shaoyang Zong, Wansong Liu, Rutao Shandong Univ Sch Environm Sci & Engn China Amer CRC Environm & Hlth 72 Jimo Binhai Rd Qingdao 266237 Shandong Peoples R China Shandong Normal Univ Coll Geog & Environm 88 East Wenhua Rd Jinan 250014 Shandong Peoples R China

Nanoplastics (NPs) are emerging global contaminants that can exacerbate the animal toxicity and cytotoxicity of cadmium (Cd). However, the mechanisms by which NPs influence the toxic effects of Cd on key functional proteins within the body remain unknown. In this study, trypsin, a protein that is prone to coexist with NPs in the digestive tract, was selected as the target protein. The effects and mechanisms of NPs on Cd2+-induced structural damage at multiple levels and alterations in the biological function of trypsin were investigated using multi-spectroscopy techniques, enzyme activity assays, and computational modeling. Results indicated that the Cd2+-induced decrease and red shift of the trypsin backbone peak were exacerbated by the presence of NPs, leading to more serve backbone loosening. Furthermore, compared to Cd2+, NPs@Cd2+ caused a more pronounced reduction in the alpha-helix content of trypsin. These structural changes led to the opening of the trypsin pocket and the overactivation of the enzyme (NPs@Cd2+: 227.22%;Cd2+: 53.35%). Ultimately, the formation of a "protein corona" around NPs@Cd2+ and the metal contact of Cd2+ to the trypsin surface were identified as the mechanisms by which NPs enhanced the protein toxicity of Cd2+. This study elucidates, for the first time, the effects and underlying mechanisms of NPs on the toxicity of key functional proteins of Cd2+. These findings offer novel mechanistic insights and critical evidence essential for evaluating the risks associated with NPs.

关键词： Nanoplastics Cadmium Trypsin Amino acid microenvironment computational modeling

来源：评论

学校读者我要写书评

暂无评论

computational modeling of cardiac growth and remodeling in pressure overloaded hearts-Linking microstructure to organ phenotype

引用

ACTA BIOMATERIALIA 2020年 106卷 34-53页

作者： Niestrawska, Justyna A. Augustin, Christoph M. Plank, Gernot Med Univ Graz Gottfried Schatz Res Ctr Div Biophys A-8010 Graz Austria BioTechMed Graz Graz Austria

Cardiac growth and remodeling (G&R) refers to structural changes in myocardial tissue in response to chronic alterations in loading conditions. One such condition is pressure overload where elevated wall stresses stimulate the growth in cardiomyocyte thickness, associated with a phenotype of concentric hypertrophy at the organ scale, and promote fibrosis. The initial hypertrophic response can be considered adaptive and beneficial by favoring myocyte survival, but over time if pressure overload conditions persist, maladaptive mechanisms favoring cell death and fibrosis start to dominate, ultimately mediating the transition towards an overt heart failure phenotype. The underlying mechanisms linking biological factors at the myocyte level to biomechanical factors at the systemic and organ level remain poorly understood. computational models of G&R show high promise as a unique framework for providing a quantitative link between myocardial stresses and strains at the organ scale to biological regulatory processes at the cellular level which govern the hypertrophic response. However, microstructurally motivated, rigorously validated computational models of G&R are still in their infancy. This article provides an overview of the current state-of-the-art of computational models to study cardiac G&R. The microstructure and mechanosensing/mechanotransduction within cells of the myocardium is discussed and quantitative data from previous experimental and clinical studies is summarized. We conclude with a discussion of major challenges and possible directions of future research that can advance the current state of cardiac G&R computational modeling. Statement of Significance The mechanistic links between organ-scale biomechanics and biological factors at the cellular size scale remain poorly understood as these are largely elusive to investigations using experimental methodology alone. computational G&R models show high promise to establish quantitative links which allow more

关键词： Growth and remodeling Pressure overload Structural remodeling computational modeling Hypertrophy

来源：评论

学校读者我要写书评

暂无评论

computational modeling of media flow through perfusion-based bioreactors for bone tissue engineering

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART H-JOURNAL OF ENGINEERING IN MEDICINE 2020年第12期234卷 1397-1408页

作者： Nokhbatolfoghahaei, Hanieh Bohlouli, Mahboubeh Adavi, Kazem Paknejad, Zahrasadat Rad, Maryam Rezai Khani, Mohammad Mehdi Salehi-Nik, Nasim Khojasteh, Arash Shahid Beheshti Univ Med Sci Res Inst Dent Sci Dent Res Ctr Tehran Iran Shahid Beheshti Univ Med Sci Sch Adv Technol Med Dept Tissue Engn & Appl Cell Sci Daneshjou BlvdPO 19839 Tehran *** Iran Shahid Beheshti Univ Med Sci Med Nanotechnol & Tissue Engn Res Ctr Student Res Comm Tehran Iran Sharif Univ Technol Dept Chem & Petr Engn Tehran Iran Univ Twente Faulty Engn Technol Dept Biomech Engn Enschede Netherlands

Bioreactor system has been used in bone tissue engineering in order to simulate dynamic nature of bone tissue environments. Perfusion bioreactors have been reported as the most efficient types of shear-loading bioreactor. Also, combination of forces, such as rotation plus perfusion, has been reported to enhance cell growth and osteogenic differentiation. Mathematical modeling using sophisticated infrastructure processes could be helpful and streamline the development of functional grafts by estimating and defining an effective range of bioreactor settings for better augmentation of tissue engineering. This study is aimed to conduct computational modeling for newly designed bioreactors in order to alleviate the time and material consuming for evaluating bioreactor parameters and effect of fluid flow hydrodynamics (various amounts of shear stress) on osteogenesis. Also, biological assessments were performed in order to validate similar parameters under implementing the perfusion or rotating and perfusion fluid motions in bioreactors' prototype. Finite element method was used to investigate the effect of hydrodynamic of fluid flow inside the bioreactors. The equations used in the simulation to calculate the velocity values and consequently the shear stress values include Navier-Stokes and Brinkman equations. It has been shown that rotational fluid motion in rotating and perfusion bioreactor produces more velocity and shear stress compared with perfusion bioreactor. Moreover, implementing the perfusion together with rotational force in rotating and perfusion bioreactors has been shown to have more cell proliferation and higher activity of alkaline phosphatase enzyme as well as formation of extra cellular matrix sheet, as an indicator of bone-like tissue formation.

关键词： Flow modeling perfusion bioreactor rotating and perfusion bioreactor computational modeling bone tissue engineering

来源：评论

学校读者我要写书评

暂无评论

computational modeling of the immune response in multiple sclerosis using epimod framework

引用

BMC BIOINFORMATICS 2020年第17-Sup期21卷 550-550页

作者： Pernice, Simone Follia, Laura Maglione, Alessandro Pennisi, Marzio Pappalardo, Francesco Novelli, Francesco Clerico, Marinella Beccuti, Marco Cordero, Francesca Rolla, Simona Univ Turin Dept Comp Sci Turin Italy Univ Piemonte Orientale Comp Sci Inst DiSIT Alessandria Italy Univ Turin Dept Clin & Biol Sci Orbassano Italy Univ Catania Dept Drug Sci Catania Italy Univ Turin Dept Mol Biotechnol & Hlth Sci Turin Italy

BackgroundMultiple Sclerosis (MS) represents nowadays in Europe the leading cause of non-traumatic disabilities in young adults, with more than 700,000 EU cases. Although huge strides have been made over the years, MS etiology remains partially unknown. Furthermore, the presence of various endogenous and exogenous factors can greatly influence the immune response of different individuals, making it difficult to study and understand the disease. This becomes more evident in a personalized-fashion when medical doctors have to choose the best therapy for patient well-being. In this optics, the use of stochastic models, capable of taking into consideration all the fluctuations due to unknown factors and individual variability, is highly *** propose a new model to study the immune response in relapsing remitting MS (RRMS), the most common form of MS that is characterized by alternate episodes of symptom exacerbation (relapses) with periods of disease stability (remission). In this new model, both the peripheral lymph node/blood vessel and the central nervous system are explicitly represented. The model was created and analysed using Epimod, our recently developed general framework for modeling complex biological systems. Then the effectiveness of our model was shown by modeling the complex immunological mechanisms characterizing RRMS during its course and under the DAC *** results have proven the ability of the model to reproduce in silico the immune T cell balance characterizing RRMS course and the DAC effects. Furthermore, they confirmed the importance of a timely intervention on the disease course.

关键词： Multiple sclerosis Immune system computational modeling Stochastic modeling Petri net

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：