首页 > 最新文献

Frontiers in Artificial Intelligence最新文献

英文 中文
Weighted Bayesian Belief Network for diabetics: a predictive model 糖尿病患者的加权贝叶斯信念网络:一种预测模型
Pub Date : 2024-04-11 DOI: 10.3389/frai.2024.1357121
S. Kharya, Sunita Soni, Abhilash Pati, Amrutanshu Panigrahi, Jayant Giri, Hong Qin, Saurav Mallik, Debasish Swapnesh Kumar Nayak, T. Swarnkar
Diabetes is an enduring metabolic condition identified by heightened blood sugar levels stemming from insufficient production of insulin or ineffective utilization of insulin within the body. India is commonly labeled as the “diabetes capital of the world” owing to the widespread prevalence of this condition. To the best of the authors' last knowledge updated on September 2021, approximately 77 million adults in India were reported to be affected by diabetes, reported by the International Diabetes Federation. Owing to the concealed early symptoms, numerous diabetic patients go undiagnosed, leading to delayed treatment. While Computational Intelligence approaches have been utilized to improve the prediction rate, a significant portion of these methods lacks interpretability, primarily due to their inherent black box nature. Rule extraction is frequently utilized to elucidate the opaque nature inherent in machine learning algorithms. Moreover, to resolve the black box nature, a method for extracting strong rules based on Weighted Bayesian Association Rule Mining is used so that the extracted rules to diagnose any disease such as diabetes can be very transparent and easily analyzed by the clinical experts, enhancing the interpretability. The WBBN model is constructed utilizing the UCI machine learning repository, demonstrating a performance accuracy of 95.8%.
糖尿病是一种持久的新陈代谢疾病,由于体内胰岛素分泌不足或不能有效利用胰岛素,导致血糖水平升高。由于糖尿病的广泛流行,印度通常被称为 "世界糖尿病之都"。根据作者在 2021 年 9 月的最新了解,据国际糖尿病联合会报告,印度约有 7700 万成年人患有糖尿病。由于早期症状被掩盖,许多糖尿病患者得不到诊断,导致治疗延误。虽然计算智能方法已被用于提高预测率,但这些方法中有很大一部分缺乏可解释性,这主要是由于其固有的黑箱性质。规则提取经常被用来阐明机器学习算法固有的不透明性。此外,为了解决黑箱性问题,我们采用了一种基于加权贝叶斯关联规则挖掘的强规则提取方法,这样提取出的糖尿病等疾病诊断规则就会非常透明,便于临床专家分析,从而提高了可解释性。WBBN 模型是利用 UCI 机器学习库构建的,准确率高达 95.8%。
{"title":"Weighted Bayesian Belief Network for diabetics: a predictive model","authors":"S. Kharya, Sunita Soni, Abhilash Pati, Amrutanshu Panigrahi, Jayant Giri, Hong Qin, Saurav Mallik, Debasish Swapnesh Kumar Nayak, T. Swarnkar","doi":"10.3389/frai.2024.1357121","DOIUrl":"https://doi.org/10.3389/frai.2024.1357121","url":null,"abstract":"Diabetes is an enduring metabolic condition identified by heightened blood sugar levels stemming from insufficient production of insulin or ineffective utilization of insulin within the body. India is commonly labeled as the “diabetes capital of the world” owing to the widespread prevalence of this condition. To the best of the authors' last knowledge updated on September 2021, approximately 77 million adults in India were reported to be affected by diabetes, reported by the International Diabetes Federation. Owing to the concealed early symptoms, numerous diabetic patients go undiagnosed, leading to delayed treatment. While Computational Intelligence approaches have been utilized to improve the prediction rate, a significant portion of these methods lacks interpretability, primarily due to their inherent black box nature. Rule extraction is frequently utilized to elucidate the opaque nature inherent in machine learning algorithms. Moreover, to resolve the black box nature, a method for extracting strong rules based on Weighted Bayesian Association Rule Mining is used so that the extracted rules to diagnose any disease such as diabetes can be very transparent and easily analyzed by the clinical experts, enhancing the interpretability. The WBBN model is constructed utilizing the UCI machine learning repository, demonstrating a performance accuracy of 95.8%.","PeriodicalId":508738,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"9 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140713988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
“Better than my professor?” How to develop artificial intelligence tools for higher education "比我的教授更好?如何为高等教育开发人工智能工具
Pub Date : 2024-04-10 DOI: 10.3389/frai.2024.1329605
Stefano Triberti, Raffaele Di Fuccio, Chiara Scuotto, Emanuele Marsico, P. Limone
Artificial Intelligence (AI) tools are currently designed and tested in many fields to improve humans’ ability to make decisions. One of these fields is higher education. For example, AI-based chatbots (“conversational pedagogical agents”) could engage in conversations with students in order to provide timely feedback and responses to questions while the learning process is taking place and to collect data to personalize the delivery of course materials. However, many existent tools are able to perform tasks that human professionals (educators, tutors, professors) could perform, just in a timelier manner. While discussing the possible implementation of AI-based tools in our university’s educational programs, we reviewed the current literature and identified a number of capabilities that future AI solutions may feature, in order to improve higher education processes, with a focus on distance higher education. Specifically, we suggest that innovative tools could influence the methodologies by which students approach learning; facilitate connections and information attainment beyond course materials; support the communication with the professor; and, draw from motivation theories to foster learning engagement, in a personalized manner. Future research should explore high-level opportunities represented by AI for higher education, including their effects on learning outcomes and the quality of the learning experience as a whole.
目前,许多领域都在设计和测试人工智能(AI)工具,以提高人类的决策能力。高等教育就是其中之一。例如,基于人工智能的聊天机器人("对话式教学代理")可以与学生进行对话,以便在学习过程中及时反馈和回答问题,并收集数据以个性化地提供课程材料。然而,现有的许多工具都能完成人类专业人员(教育工作者、辅导员、教授)所能完成的任务,只是更及时而已。在讨论在我校教育项目中实施基于人工智能的工具的可能性时,我们回顾了当前的文献,并确定了未来人工智能解决方案可能具备的一些功能,以改善高等教育过程,重点是远程高等教育。具体来说,我们认为创新工具可以影响学生的学习方法;促进课程材料之外的联系和信息获取;支持与教授的交流;以及借鉴激励理论,以个性化的方式促进学习参与。未来的研究应探索人工智能为高等教育带来的高层次机遇,包括其对学习成果和整个学习体验质量的影响。
{"title":"“Better than my professor?” How to develop artificial intelligence tools for higher education","authors":"Stefano Triberti, Raffaele Di Fuccio, Chiara Scuotto, Emanuele Marsico, P. Limone","doi":"10.3389/frai.2024.1329605","DOIUrl":"https://doi.org/10.3389/frai.2024.1329605","url":null,"abstract":"Artificial Intelligence (AI) tools are currently designed and tested in many fields to improve humans’ ability to make decisions. One of these fields is higher education. For example, AI-based chatbots (“conversational pedagogical agents”) could engage in conversations with students in order to provide timely feedback and responses to questions while the learning process is taking place and to collect data to personalize the delivery of course materials. However, many existent tools are able to perform tasks that human professionals (educators, tutors, professors) could perform, just in a timelier manner. While discussing the possible implementation of AI-based tools in our university’s educational programs, we reviewed the current literature and identified a number of capabilities that future AI solutions may feature, in order to improve higher education processes, with a focus on distance higher education. Specifically, we suggest that innovative tools could influence the methodologies by which students approach learning; facilitate connections and information attainment beyond course materials; support the communication with the professor; and, draw from motivation theories to foster learning engagement, in a personalized manner. Future research should explore high-level opportunities represented by AI for higher education, including their effects on learning outcomes and the quality of the learning experience as a whole.","PeriodicalId":508738,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"50 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140717656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Hyperdimensional computing with holographic and adaptive encoder 利用全息和自适应编码器进行超维计算
Pub Date : 2024-04-09 DOI: 10.3389/frai.2024.1371988
Alejandro Hernández-Cano, Yang Ni, Zhuowen Zou, Ali Zakeri, Mohsen Imani
Introduction Brain-inspired computing has become an emerging field, where a growing number of works focus on developing algorithms that bring machine learning closer to human brains at the functional level. As one of the promising directions, Hyperdimensional Computing (HDC) is centered around the idea of having holographic and high-dimensional representation as the neural activities in our brains. Such representation is the fundamental enabler for the efficiency and robustness of HDC. However, existing HDC-based algorithms suffer from limitations within the encoder. To some extent, they all rely on manually selected encoders, meaning that the resulting representation is never adapted to the tasks at hand. Methods In this paper, we propose FLASH, a novel hyperdimensional learning method that incorporates an adaptive and learnable encoder design, aiming at better overall learning performance while maintaining good properties of HDC representation. Current HDC encoders leverage Random Fourier Features (RFF) for kernel correspondence and enable locality-preserving encoding. We propose to learn the encoder matrix distribution via gradient descent and effectively adapt the kernel for a more suitable HDC encoding. Results Our experiments on various regression datasets show that tuning the HDC encoder can significantly boost the accuracy, surpassing the current HDC-based algorithm and providing faster inference than other baselines, including RFF-based kernel ridge regression. Discussion The results indicate the importance of an adaptive encoder and customized high-dimensional representation in HDC.
引言 脑启发计算已成为一个新兴领域,越来越多的研究工作侧重于开发在功能层面使机器学习更接近人类大脑的算法。超维计算(Hyperdimensional Computing,HDC)是其中一个前景广阔的方向,其核心思想是将我们大脑中的神经活动进行全息和高维表示。这种表征是提高 HDC 效率和鲁棒性的基础。然而,现有的基于 HDC 的算法受到编码器内部的限制。在某种程度上,它们都依赖于人工选择的编码器,这意味着生成的表示从未适应过手头的任务。方法 在本文中,我们提出了一种新颖的超维度学习方法 FLASH,它结合了自适应和可学习的编码器设计,旨在提高整体学习性能,同时保持 HDC 表示法的良好特性。当前的 HDC 编码器利用随机傅里叶特征(RFF)进行内核对应,并实现了位置保护编码。我们建议通过梯度下降来学习编码器矩阵分布,并有效地调整内核以获得更合适的 HDC 编码。结果 我们在各种回归数据集上的实验表明,调整 HDC 编码器可以显著提高准确率,超越当前基于 HDC 的算法,并提供比其他基线(包括基于 RFF 的核脊回归)更快的推理速度。讨论 结果表明了自适应编码器和定制高维表示在 HDC 中的重要性。
{"title":"Hyperdimensional computing with holographic and adaptive encoder","authors":"Alejandro Hernández-Cano, Yang Ni, Zhuowen Zou, Ali Zakeri, Mohsen Imani","doi":"10.3389/frai.2024.1371988","DOIUrl":"https://doi.org/10.3389/frai.2024.1371988","url":null,"abstract":"Introduction Brain-inspired computing has become an emerging field, where a growing number of works focus on developing algorithms that bring machine learning closer to human brains at the functional level. As one of the promising directions, Hyperdimensional Computing (HDC) is centered around the idea of having holographic and high-dimensional representation as the neural activities in our brains. Such representation is the fundamental enabler for the efficiency and robustness of HDC. However, existing HDC-based algorithms suffer from limitations within the encoder. To some extent, they all rely on manually selected encoders, meaning that the resulting representation is never adapted to the tasks at hand. Methods In this paper, we propose FLASH, a novel hyperdimensional learning method that incorporates an adaptive and learnable encoder design, aiming at better overall learning performance while maintaining good properties of HDC representation. Current HDC encoders leverage Random Fourier Features (RFF) for kernel correspondence and enable locality-preserving encoding. We propose to learn the encoder matrix distribution via gradient descent and effectively adapt the kernel for a more suitable HDC encoding. Results Our experiments on various regression datasets show that tuning the HDC encoder can significantly boost the accuracy, surpassing the current HDC-based algorithm and providing faster inference than other baselines, including RFF-based kernel ridge regression. Discussion The results indicate the importance of an adaptive encoder and customized high-dimensional representation in HDC.","PeriodicalId":508738,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"55 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140725103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
ALL classification using neural ensemble and memetic deep feature optimization 利用神经集合和记忆深度特征优化进行 ALL 分类
Pub Date : 2024-04-09 DOI: 10.3389/frai.2024.1351942
Muhammad Awais, Riaz Ahmad, Nabeela Kausar, A. Alzahrani, Nasser Alalwan, Anum Masood
Acute lymphoblastic leukemia (ALL) is a fatal blood disorder characterized by the excessive proliferation of immature white blood cells, originating in the bone marrow. An effective prognosis and treatment of ALL calls for its accurate and timely detection. Deep convolutional neural networks (CNNs) have shown promising results in digital pathology. However, they face challenges in classifying different subtypes of leukemia due to their subtle morphological differences. This study proposes an improved pipeline for binary detection and sub-type classification of ALL from blood smear images. At first, a customized, 88 layers deep CNN is proposed and trained using transfer learning along with GoogleNet CNN to create an ensemble of features. Furthermore, this study models the feature selection problem as a combinatorial optimization problem and proposes a memetic version of binary whale optimization algorithm, incorporating Differential Evolution-based local search method to enhance the exploration and exploitation of feature search space. The proposed approach is validated using publicly available standard datasets containing peripheral blood smear images of various classes of ALL. An overall best average accuracy of 99.15% is achieved for binary classification of ALL with an 85% decrease in the feature vector, together with 99% precision and 98.8% sensitivity. For B-ALL sub-type classification, the best accuracy of 98.69% is attained with 98.7% precision and 99.57% specificity. The proposed methodology shows better performance metrics as compared with several existing studies.
急性淋巴细胞白血病(ALL)是一种致命的血液疾病,其特征是起源于骨髓的未成熟白细胞过度增殖。要对急性淋巴细胞白血病进行有效的预后和治疗,就必须对其进行准确及时的检测。深度卷积神经网络(CNN)在数字病理学领域取得了可喜的成果。然而,由于不同亚型白血病在形态上存在细微差别,因此它们在对不同亚型白血病进行分类时面临挑战。本研究提出了一种改进的管道,用于从血液涂片图像中对 ALL 进行二元检测和亚型分类。首先,提出了一种定制的 88 层深度 CNN,并利用迁移学习与 GoogleNet CNN 一起进行训练,以创建特征集合。此外,本研究还将特征选择问题建模为组合优化问题,并提出了二元鲸优化算法的记忆版本,结合基于差分进化的局部搜索方法,以增强对特征搜索空间的探索和利用。所提出的方法利用公开的标准数据集进行了验证,这些数据集包含各种类型 ALL 的外周血涂片图像。在特征向量减少 85% 的情况下,ALL 二元分类的总体最佳平均准确率达到 99.15%,精确度为 99%,灵敏度为 98.8%。对于 B-ALL 亚型分类,最佳准确率为 98.69%,精确度为 98.7%,特异度为 99.57%。与现有的几项研究相比,所提出的方法显示出更好的性能指标。
{"title":"ALL classification using neural ensemble and memetic deep feature optimization","authors":"Muhammad Awais, Riaz Ahmad, Nabeela Kausar, A. Alzahrani, Nasser Alalwan, Anum Masood","doi":"10.3389/frai.2024.1351942","DOIUrl":"https://doi.org/10.3389/frai.2024.1351942","url":null,"abstract":"Acute lymphoblastic leukemia (ALL) is a fatal blood disorder characterized by the excessive proliferation of immature white blood cells, originating in the bone marrow. An effective prognosis and treatment of ALL calls for its accurate and timely detection. Deep convolutional neural networks (CNNs) have shown promising results in digital pathology. However, they face challenges in classifying different subtypes of leukemia due to their subtle morphological differences. This study proposes an improved pipeline for binary detection and sub-type classification of ALL from blood smear images. At first, a customized, 88 layers deep CNN is proposed and trained using transfer learning along with GoogleNet CNN to create an ensemble of features. Furthermore, this study models the feature selection problem as a combinatorial optimization problem and proposes a memetic version of binary whale optimization algorithm, incorporating Differential Evolution-based local search method to enhance the exploration and exploitation of feature search space. The proposed approach is validated using publicly available standard datasets containing peripheral blood smear images of various classes of ALL. An overall best average accuracy of 99.15% is achieved for binary classification of ALL with an 85% decrease in the feature vector, together with 99% precision and 98.8% sensitivity. For B-ALL sub-type classification, the best accuracy of 98.69% is attained with 98.7% precision and 99.57% specificity. The proposed methodology shows better performance metrics as compared with several existing studies.","PeriodicalId":508738,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"26 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140727801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Analysis of social metrics on scientific production in the field of emotion-aware education through artificial intelligence 通过人工智能分析情绪感知教育领域科学生产的社会指标
Pub Date : 2024-04-08 DOI: 10.3389/frai.2024.1401162
Jacobo Roda-Segarra, Santiago Mengual-Andrés, Andrés Payà Rico
Research in the field of Artificial Intelligence applied to emotions in the educational context has experienced significant growth in recent years. However, despite the field’s profound implications for the educational community, the social impact of this scientific production on digital social media remains unclear. To address this question, the present research has been proposed, aiming to analyze the social impact of scientific production on the use of Artificial Intelligence for emotions in the educational context. For this purpose, a sample of 243 scientific publications indexed in Scopus and Web of Science has been selected, from which a second sample of 6,094 social impact records has been extracted from Altmetric, Crossref, and PlumX databases. A dual analysis has been conducted using specially designed software: on one hand, the scientific sample has been analyzed from a bibliometric perspective, and on the other hand, the social impact records have been studied. Comparative analysis based on the two dimensions, scientific and social, has focused on the evolution of scientific production with its corresponding social impact, sources, impact, and content analysis. The results indicate that scientific publications have had a high social impact (with an average of 25.08 social impact records per publication), with a significant increase in research interest starting from 2019, likely driven by the emotional implications of measures taken to curb the COVID-19 pandemic. Furthermore, a lack of alignment has been identified between articles with the highest scientific impact and those with the highest social impact, as well as a lack of alignment in the most commonly used terms from both scientific and social perspectives, a significant variability in the lag in months for scientific research to make an impact on social media, and the fact that the social impact of the research did not emerge from the interest of Twitter users unaffiliated with the research, but rather from the authors, publishers, or scientific institutions. The proposed comparative methodology can be applied to any field of study, making it a useful tool given that current trends in accreditation agencies propose the analysis of the repercussion of scientific research in social media.
近年来,将人工智能应用于情感教育领域的研究取得了长足的发展。然而,尽管这一领域对教育界有着深远的影响,但这一科学成果对数字社交媒体的社会影响仍不明确。为了解决这个问题,我们提出了本研究,旨在分析在教育领域使用人工智能情感的科学成果的社会影响。为此,我们选取了 Scopus 和 Web of Science 中索引的 243 篇科学出版物作为样本,并从 Altmetric、Crossref 和 PlumX 数据库中提取了 6094 条社会影响记录作为第二样本。我们使用专门设计的软件进行了双重分析:一方面从文献计量学的角度分析了科学样本,另一方面研究了社会影响记录。基于科学和社会两个维度的比较分析侧重于科学成果的演变及其相应的社会影响、来源、影响和内容分析。结果表明,科学出版物具有较高的社会影响(平均每份出版物的社会影响记录为 25.08),从 2019 年开始,研究兴趣显著增加,这可能是由于为遏制 COVID-19 大流行而采取的措施所产生的情感影响。此外,还发现科学影响最大的文章与社会影响最大的文章之间缺乏一致性,从科学和社会角度来看,最常用的术语也缺乏一致性,科学研究在社交媒体上产生影响的滞后月数存在显著差异,而且研究的社会影响并非来自与研究无关的推特用户的兴趣,而是来自作者、出版商或科研机构。所提出的比较方法可应用于任何研究领域,鉴于当前认证机构的趋势是建议分析科学研究在社交媒体上的反响,因此该方法是一个有用的工具。
{"title":"Analysis of social metrics on scientific production in the field of emotion-aware education through artificial intelligence","authors":"Jacobo Roda-Segarra, Santiago Mengual-Andrés, Andrés Payà Rico","doi":"10.3389/frai.2024.1401162","DOIUrl":"https://doi.org/10.3389/frai.2024.1401162","url":null,"abstract":"Research in the field of Artificial Intelligence applied to emotions in the educational context has experienced significant growth in recent years. However, despite the field’s profound implications for the educational community, the social impact of this scientific production on digital social media remains unclear. To address this question, the present research has been proposed, aiming to analyze the social impact of scientific production on the use of Artificial Intelligence for emotions in the educational context. For this purpose, a sample of 243 scientific publications indexed in Scopus and Web of Science has been selected, from which a second sample of 6,094 social impact records has been extracted from Altmetric, Crossref, and PlumX databases. A dual analysis has been conducted using specially designed software: on one hand, the scientific sample has been analyzed from a bibliometric perspective, and on the other hand, the social impact records have been studied. Comparative analysis based on the two dimensions, scientific and social, has focused on the evolution of scientific production with its corresponding social impact, sources, impact, and content analysis. The results indicate that scientific publications have had a high social impact (with an average of 25.08 social impact records per publication), with a significant increase in research interest starting from 2019, likely driven by the emotional implications of measures taken to curb the COVID-19 pandemic. Furthermore, a lack of alignment has been identified between articles with the highest scientific impact and those with the highest social impact, as well as a lack of alignment in the most commonly used terms from both scientific and social perspectives, a significant variability in the lag in months for scientific research to make an impact on social media, and the fact that the social impact of the research did not emerge from the interest of Twitter users unaffiliated with the research, but rather from the authors, publishers, or scientific institutions. The proposed comparative methodology can be applied to any field of study, making it a useful tool given that current trends in accreditation agencies propose the analysis of the repercussion of scientific research in social media.","PeriodicalId":508738,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"63 S14","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140731810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Enhancing portfolio management using artificial intelligence: literature review 利用人工智能加强投资组合管理:文献综述
Pub Date : 2024-04-08 DOI: 10.3389/frai.2024.1371502
Kristina Sutiene, Peter Schwendner, Ciprian Sipos, Luis Lorenzo, Miroslav Mirchev, Petre Lameski, Audrius Kabašinskas, Chemseddine Tidjani, Belma Ozturkkal, Jurgita Černevičienė
Building an investment portfolio is a problem that numerous researchers have addressed for many years. The key goal has always been to balance risk and reward by optimally allocating assets such as stocks, bonds, and cash. In general, the portfolio management process is based on three steps: planning, execution, and feedback, each of which has its objectives and methods to be employed. Starting from Markowitz's mean-variance portfolio theory, different frameworks have been widely accepted, which considerably renewed how asset allocation is being solved. Recent advances in artificial intelligence provide methodological and technological capabilities to solve highly complex problems, and investment portfolio is no exception. For this reason, the paper reviews the current state-of-the-art approaches by answering the core question of how artificial intelligence is transforming portfolio management steps. Moreover, as the use of artificial intelligence in finance is challenged by transparency, fairness and explainability requirements, the case study of post-hoc explanations for asset allocation is demonstrated. Finally, we discuss recent regulatory developments in the European investment business and highlight specific aspects of this business where explainable artificial intelligence could advance transparency of the investment process.
建立投资组合是众多研究人员多年来一直在探讨的问题。其主要目标一直是通过优化配置股票、债券和现金等资产来平衡风险和回报。一般来说,投资组合管理过程分为三个步骤:计划、执行和反馈,每个步骤都有其目标和方法。从马科维茨的均值方差投资组合理论开始,不同的框架已被广泛接受,这大大更新了资产配置的解决方式。人工智能的最新进展为解决高度复杂的问题提供了方法和技术能力,投资组合也不例外。因此,本文通过回答人工智能如何改变投资组合管理步骤这一核心问题,回顾了当前最先进的方法。此外,由于人工智能在金融领域的应用受到透明度、公平性和可解释性等要求的挑战,本文对资产配置的事后解释进行了案例研究。最后,我们讨论了欧洲投资业务近期的监管发展,并强调了可解释人工智能可提高投资过程透明度的具体业务方面。
{"title":"Enhancing portfolio management using artificial intelligence: literature review","authors":"Kristina Sutiene, Peter Schwendner, Ciprian Sipos, Luis Lorenzo, Miroslav Mirchev, Petre Lameski, Audrius Kabašinskas, Chemseddine Tidjani, Belma Ozturkkal, Jurgita Černevičienė","doi":"10.3389/frai.2024.1371502","DOIUrl":"https://doi.org/10.3389/frai.2024.1371502","url":null,"abstract":"Building an investment portfolio is a problem that numerous researchers have addressed for many years. The key goal has always been to balance risk and reward by optimally allocating assets such as stocks, bonds, and cash. In general, the portfolio management process is based on three steps: planning, execution, and feedback, each of which has its objectives and methods to be employed. Starting from Markowitz's mean-variance portfolio theory, different frameworks have been widely accepted, which considerably renewed how asset allocation is being solved. Recent advances in artificial intelligence provide methodological and technological capabilities to solve highly complex problems, and investment portfolio is no exception. For this reason, the paper reviews the current state-of-the-art approaches by answering the core question of how artificial intelligence is transforming portfolio management steps. Moreover, as the use of artificial intelligence in finance is challenged by transparency, fairness and explainability requirements, the case study of post-hoc explanations for asset allocation is demonstrated. Finally, we discuss recent regulatory developments in the European investment business and highlight specific aspects of this business where explainable artificial intelligence could advance transparency of the investment process.","PeriodicalId":508738,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"37 23","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140728349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An empirical assessment of the use of an algorithm factory for video delivery operations 对使用算法工厂进行视频传输操作的实证评估
Pub Date : 2024-04-08 DOI: 10.3389/frai.2024.1281110
Gabor Molnar, Luís Ferreira Pires, Oscar de Boer, Vera Kovaleva
Introduction Video service providers are moving from focusing on Quality of Service (QoS) to Quality of Experience (QoE) in their video networks since the users’ demand for high-quality video content is continually growing. By focusing on QoE, video service providers can provide their subscribers with a more personalized and engaging experience, which can help increase viewer satisfaction and retention. This focus shift requires not only a more sophisticated approach to network management and new tools and technologies to measure and optimize QoE in their networks but also a novel approach to video delivery operations. Methods This paper describes the components, interactions, and relationships of an algorithm factory for video delivery operation that assures high QoE for video streaming services. The paper also showcases the results of gradually implementing an algorithm factory in the video industry. Using a dataset from 2016 to 2022, we present the case of a European PayTV service provider that achieved improved performance measured by both objective and subjective metrics. Results The use of an algorithm factory significantly improved the PayTV service provider’s performance. The study found a fivefold increase in the speed of critical incident resolution and a 59% reduction in the number of critical incidents, all while expanding the customer base and maintaining the same level of labor resources. The case also demonstrates a strong positive relation between the productivity measures of the PayTV operator and their survey-based quality ratings. These results underscore the importance of flawless QoS and operational excellence in delivering QoE to meet the evolving demands of viewers. Discussion The paper adds to the existing literature on relationships between operational efficiency, innovation, and subjective quality. The paper further offers empirical evidence from the PayTV industry. The insights provided are expected to benefit both traditional and over-the-top (OTT) video service providers in their quest to stay ahead in the rapidly evolving video industry. It may also translate to other service providers in similar industries committed to supporting high-quality service delivery.
导言:由于用户对高质量视频内容的需求不断增长,视频服务提供商正在将视频网络的重点从服务质量(QoS)转向体验质量(QoE)。通过关注 QoE,视频服务提供商可以为用户提供更加个性化和更具吸引力的体验,从而有助于提高观众的满意度和保留率。这种重点转移不仅需要更先进的网络管理方法和新工具与技术来测量和优化网络中的 QoE,还需要一种新颖的视频传输操作方法。方法 本文介绍了确保视频流服务高 QoE 的视频交付运营算法工厂的组成、互动和关系。本文还展示了在视频行业逐步实施算法工厂的成果。通过使用 2016 年至 2022 年的数据集,我们介绍了一家欧洲付费电视服务提供商的案例,该服务提供商通过客观和主观指标衡量,实现了性能的提升。结果 算法工厂的使用大大提高了付费电视服务提供商的性能。研究发现,关键事件的解决速度提高了五倍,关键事件的数量减少了 59%,所有这些都是在扩大客户群和保持相同劳动力资源水平的情况下实现的。该案例还表明,付费电视运营商的生产率措施与其基于调查的质量评级之间存在很强的正相关关系。这些结果凸显了完美的服务质量和卓越运营在提供 QoE 以满足观众不断变化的需求方面的重要性。讨论 本文补充了有关运营效率、创新和主观质量之间关系的现有文献。本文进一步提供了付费电视行业的经验证据。所提供的见解有望使传统和 OTT 视频服务提供商受益,帮助他们在快速发展的视频行业中保持领先地位。它还可转化为致力于支持提供高质量服务的类似行业的其他服务提供商。
{"title":"An empirical assessment of the use of an algorithm factory for video delivery operations","authors":"Gabor Molnar, Luís Ferreira Pires, Oscar de Boer, Vera Kovaleva","doi":"10.3389/frai.2024.1281110","DOIUrl":"https://doi.org/10.3389/frai.2024.1281110","url":null,"abstract":"Introduction Video service providers are moving from focusing on Quality of Service (QoS) to Quality of Experience (QoE) in their video networks since the users’ demand for high-quality video content is continually growing. By focusing on QoE, video service providers can provide their subscribers with a more personalized and engaging experience, which can help increase viewer satisfaction and retention. This focus shift requires not only a more sophisticated approach to network management and new tools and technologies to measure and optimize QoE in their networks but also a novel approach to video delivery operations. Methods This paper describes the components, interactions, and relationships of an algorithm factory for video delivery operation that assures high QoE for video streaming services. The paper also showcases the results of gradually implementing an algorithm factory in the video industry. Using a dataset from 2016 to 2022, we present the case of a European PayTV service provider that achieved improved performance measured by both objective and subjective metrics. Results The use of an algorithm factory significantly improved the PayTV service provider’s performance. The study found a fivefold increase in the speed of critical incident resolution and a 59% reduction in the number of critical incidents, all while expanding the customer base and maintaining the same level of labor resources. The case also demonstrates a strong positive relation between the productivity measures of the PayTV operator and their survey-based quality ratings. These results underscore the importance of flawless QoS and operational excellence in delivering QoE to meet the evolving demands of viewers. Discussion The paper adds to the existing literature on relationships between operational efficiency, innovation, and subjective quality. The paper further offers empirical evidence from the PayTV industry. The insights provided are expected to benefit both traditional and over-the-top (OTT) video service providers in their quest to stay ahead in the rapidly evolving video industry. It may also translate to other service providers in similar industries committed to supporting high-quality service delivery.","PeriodicalId":508738,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"19 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140728706","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Application of machine learning for lung cancer survival prognostication—A systematic review and meta-analysis 机器学习在肺癌生存预后中的应用--系统综述与荟萃分析
Pub Date : 2024-04-05 DOI: 10.3389/frai.2024.1365777
Alexander J. Didier, Anthony Nigro, Zaid Noori, Mohamed A. Omballi, Scott M. Pappada, Danae Hamouda
Introduction Machine learning (ML) techniques have gained increasing attention in the field of healthcare, including predicting outcomes in patients with lung cancer. ML has the potential to enhance prognostication in lung cancer patients and improve clinical decision-making. In this systematic review and meta-analysis, we aimed to evaluate the performance of ML models compared to logistic regression (LR) models in predicting overall survival in patients with lung cancer. Methods We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement. A comprehensive search was conducted in Medline, Embase, and Cochrane databases using a predefined search query. Two independent reviewers screened abstracts and conflicts were resolved by a third reviewer. Inclusion and exclusion criteria were applied to select eligible studies. Risk of bias assessment was performed using predefined criteria. Data extraction was conducted using the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies (CHARMS) checklist. Meta-analytic analysis was performed to compare the discriminative ability of ML and LR models. Results The literature search resulted in 3,635 studies, and 12 studies with a total of 211,068 patients were included in the analysis. Six studies reported confidence intervals and were included in the meta-analysis. The performance of ML models varied across studies, with C-statistics ranging from 0.60 to 0.85. The pooled analysis showed that ML models had higher discriminative ability compared to LR models, with a weighted average C-statistic of 0.78 for ML models compared to 0.70 for LR models. Conclusion Machine learning models show promise in predicting overall survival in patients with lung cancer, with superior discriminative ability compared to logistic regression models. However, further validation and standardization of ML models are needed before their widespread implementation in clinical practice. Future research should focus on addressing the limitations of the current literature, such as potential bias and heterogeneity among studies, to improve the accuracy and generalizability of ML models for predicting outcomes in patients with lung cancer. Further research and development of ML models in this field may lead to improved patient outcomes and personalized treatment strategies.
导言 机器学习(ML)技术在医疗保健领域受到越来越多的关注,其中包括肺癌患者的预后预测。机器学习有可能提高肺癌患者的预后并改善临床决策。在这项系统综述和荟萃分析中,我们旨在评估 ML 模型与逻辑回归(LR)模型相比在预测肺癌患者总生存期方面的性能。方法 我们遵循了系统综述和荟萃分析首选报告项目(PRISMA)声明。使用预定义的检索查询在 Medline、Embase 和 Cochrane 数据库中进行了全面检索。两位独立审稿人对摘要进行筛选,并由第三位审稿人解决冲突。纳入和排除标准用于筛选符合条件的研究。采用预定义标准对偏倚风险进行评估。数据提取采用预测建模研究系统性综述的批判性评估和数据提取(CHARMS)核对表进行。进行了元分析,以比较 ML 和 LR 模型的判别能力。结果 文献检索结果为 3,635 项研究,其中 12 项研究纳入了分析,共计 211,068 名患者。六项研究报告了置信区间,并被纳入荟萃分析。不同研究的 ML 模型性能各不相同,C 统计量从 0.60 到 0.85 不等。汇总分析表明,与 LR 模型相比,ML 模型具有更高的分辨能力,ML 模型的加权平均 C 统计量为 0.78,而 LR 模型为 0.70。结论 机器学习模型有望预测肺癌患者的总生存期,其判别能力优于逻辑回归模型。然而,在广泛应用于临床实践之前,还需要对机器学习模型进行进一步的验证和标准化。未来的研究应侧重于解决当前文献的局限性,如潜在的偏倚和研究间的异质性,以提高 ML 模型预测肺癌患者预后的准确性和可推广性。在这一领域进一步研究和开发 ML 模型可能会改善患者的预后和个性化治疗策略。
{"title":"Application of machine learning for lung cancer survival prognostication—A systematic review and meta-analysis","authors":"Alexander J. Didier, Anthony Nigro, Zaid Noori, Mohamed A. Omballi, Scott M. Pappada, Danae Hamouda","doi":"10.3389/frai.2024.1365777","DOIUrl":"https://doi.org/10.3389/frai.2024.1365777","url":null,"abstract":"Introduction Machine learning (ML) techniques have gained increasing attention in the field of healthcare, including predicting outcomes in patients with lung cancer. ML has the potential to enhance prognostication in lung cancer patients and improve clinical decision-making. In this systematic review and meta-analysis, we aimed to evaluate the performance of ML models compared to logistic regression (LR) models in predicting overall survival in patients with lung cancer. Methods We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement. A comprehensive search was conducted in Medline, Embase, and Cochrane databases using a predefined search query. Two independent reviewers screened abstracts and conflicts were resolved by a third reviewer. Inclusion and exclusion criteria were applied to select eligible studies. Risk of bias assessment was performed using predefined criteria. Data extraction was conducted using the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies (CHARMS) checklist. Meta-analytic analysis was performed to compare the discriminative ability of ML and LR models. Results The literature search resulted in 3,635 studies, and 12 studies with a total of 211,068 patients were included in the analysis. Six studies reported confidence intervals and were included in the meta-analysis. The performance of ML models varied across studies, with C-statistics ranging from 0.60 to 0.85. The pooled analysis showed that ML models had higher discriminative ability compared to LR models, with a weighted average C-statistic of 0.78 for ML models compared to 0.70 for LR models. Conclusion Machine learning models show promise in predicting overall survival in patients with lung cancer, with superior discriminative ability compared to logistic regression models. However, further validation and standardization of ML models are needed before their widespread implementation in clinical practice. Future research should focus on addressing the limitations of the current literature, such as potential bias and heterogeneity among studies, to improve the accuracy and generalizability of ML models for predicting outcomes in patients with lung cancer. Further research and development of ML models in this field may lead to improved patient outcomes and personalized treatment strategies.","PeriodicalId":508738,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"23 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140738607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Artificial neural network-assisted prediction of radiobiological indices in head and neck cancer 人工神经网络辅助预测头颈癌的放射生物学指标
Pub Date : 2024-04-05 DOI: 10.3389/frai.2024.1329737
Saad Bin Saeed Ahmed, Shahzaib Naeem, Agha Muhammad Hammad Khan, Bilal Mazhar Qureshi, Amjad Hussain, Bulent Aydogan, Wazir Muhammad
Background and purpose We proposed an artificial neural network model to predict radiobiological parameters for the head and neck squamous cell carcinoma patients treated with radiation therapy. The model uses the tumor specification, demographics, and radiation dose distribution to predict the tumor control probability and the normal tissue complications probability. These indices are crucial for the assessment and clinical management of cancer patients during treatment planning. Methods Two publicly available datasets of 31 and 215 head and neck squamous cell carcinoma patients treated with conformal radiation therapy were selected. The demographics, tumor specifications, and radiation therapy treatment parameters were extracted from the datasets used as inputs for the training of perceptron. Radiobiological indices are calculated by open-source software using dosevolume histograms from radiation therapy treatment plans. Those indices were used as output in the training of a single-layer neural network. The distribution of data used for training, validation, and testing purposes was 70, 15, and 15%, respectively. Results The best performance of the neural network was noted at epoch number 32 with the mean squared error of 0.0465. The accuracy of the prediction of radiobiological indices by the artificial neural network in training, validation, and test phases were determined to be 0.89, 0.87, and 0.82, respectively. We also found that the percentage volume of parotid inside the planning target volume is the significant parameter for the prediction of normal tissue complications probability. Conclusion We believe that the model has significant potential to predict radiobiological indices and help clinicians in treatment plan evaluation and treatment management of head and neck squamous cell carcinoma patients.
背景和目的 我们提出了一种人工神经网络模型,用于预测接受放射治疗的头颈部鳞状细胞癌患者的放射生物学参数。该模型利用肿瘤规格、人口统计学和辐射剂量分布来预测肿瘤控制概率和正常组织并发症概率。这些指标对癌症患者治疗计划的评估和临床管理至关重要。方法 选取了两个公开的数据集,分别包含 31 名和 215 名接受适形放射治疗的头颈部鳞状细胞癌患者。从数据集中提取人口统计学、肿瘤规格和放疗治疗参数,作为感知器训练的输入。放射生物学指数由开源软件利用放射治疗计划中的剂量体积直方图计算得出。这些指数被用作单层神经网络训练的输出。用于训练、验证和测试的数据分布分别为 70%、15% 和 15%。结果 神经网络在第 32 个历元时表现最佳,平均平方误差为 0.0465。人工神经网络在训练、验证和测试阶段预测放射生物学指标的准确率分别为 0.89、0.87 和 0.82。我们还发现,计划目标体积内腮腺体积百分比是预测正常组织并发症概率的重要参数。结论 我们认为该模型在预测放射生物学指标方面具有巨大潜力,有助于临床医生对头颈部鳞状细胞癌患者的治疗方案进行评估和治疗管理。
{"title":"Artificial neural network-assisted prediction of radiobiological indices in head and neck cancer","authors":"Saad Bin Saeed Ahmed, Shahzaib Naeem, Agha Muhammad Hammad Khan, Bilal Mazhar Qureshi, Amjad Hussain, Bulent Aydogan, Wazir Muhammad","doi":"10.3389/frai.2024.1329737","DOIUrl":"https://doi.org/10.3389/frai.2024.1329737","url":null,"abstract":"Background and purpose We proposed an artificial neural network model to predict radiobiological parameters for the head and neck squamous cell carcinoma patients treated with radiation therapy. The model uses the tumor specification, demographics, and radiation dose distribution to predict the tumor control probability and the normal tissue complications probability. These indices are crucial for the assessment and clinical management of cancer patients during treatment planning. Methods Two publicly available datasets of 31 and 215 head and neck squamous cell carcinoma patients treated with conformal radiation therapy were selected. The demographics, tumor specifications, and radiation therapy treatment parameters were extracted from the datasets used as inputs for the training of perceptron. Radiobiological indices are calculated by open-source software using dosevolume histograms from radiation therapy treatment plans. Those indices were used as output in the training of a single-layer neural network. The distribution of data used for training, validation, and testing purposes was 70, 15, and 15%, respectively. Results The best performance of the neural network was noted at epoch number 32 with the mean squared error of 0.0465. The accuracy of the prediction of radiobiological indices by the artificial neural network in training, validation, and test phases were determined to be 0.89, 0.87, and 0.82, respectively. We also found that the percentage volume of parotid inside the planning target volume is the significant parameter for the prediction of normal tissue complications probability. Conclusion We believe that the model has significant potential to predict radiobiological indices and help clinicians in treatment plan evaluation and treatment management of head and neck squamous cell carcinoma patients.","PeriodicalId":508738,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"10 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140739910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Interactive network visualization of opioid crisis research: a tool for reinforcing data linkage skills for public health policy researchers 阿片类药物危机研究的交互式网络可视化:加强公共卫生政策研究人员数据链接技能的工具
Pub Date : 2024-04-05 DOI: 10.3389/frai.2024.1208874
O. Scrivner, Thuy Nguyen, Michael Ginda, Kosali Simon, Katy Börner
Background Public health policy researchers face a persistent challenge in identifying and integrating relevant data, particularly in the context of the U.S. opioid crisis, where a comprehensive approach is crucial. Purpose To meet this new workforce demand health policy and health economics programs are increasingly introducing data analysis and data visualization skills. Such skills facilitate data integration and discovery by linking multiple resources. Common linking strategies include individual or aggregate level linking (e.g., patient identifiers) in primary clinical data and conceptual linking (e.g., healthcare workforce, state funding, burnout rates) in secondary data. Often, the combination of primary and secondary datasets is sought, requiring additional skills, for example, understanding metadata and constructing interlinkages. Methods To help improve those skills, we developed a 2-step process using a scoping method to discover data and network visualization to interlink metadata. Results: We show how these new skills enable the discovery of relationships among data sources pertinent to public policy research related to the opioid overdose crisis and facilitate inquiry across heterogeneous data resources. In addition, our interactive network visualization introduces (1) a conceptual approach, drawing from recent systematic review studies and linked by the publications, and (2) an aggregate approach, constructed using publicly available datasets and linked through crosswalks. Conclusions These novel metadata visualization techniques can be used as a teaching tool or a discovery method and can also be extended to other public policy domains.
背景 公共卫生政策研究人员在识别和整合相关数据方面一直面临着挑战,尤其是在美国阿片类药物危机的背景下,采用综合方法至关重要。目的 为满足这一新的劳动力需求,卫生政策和卫生经济学课程正越来越多地引入数据分析和数据可视化技能。这些技能通过连接多种资源来促进数据整合和发现。常见的链接策略包括初级临床数据中的个体或总体级别链接(如患者标识符)和次级数据中的概念链接(如医疗保健劳动力、国家资金、职业倦怠率)。通常情况下,需要将主要数据集和次要数据集结合起来,这就需要额外的技能,例如理解元数据和构建相互链接。方法:为了帮助提高这些技能,我们开发了一个两步流程,使用范围界定法来发现数据,并使用网络可视化来将元数据相互连接起来。结果我们展示了这些新技能如何发现与阿片类药物过量危机相关的公共政策研究数据源之间的关系,以及如何促进跨异构数据资源的查询。此外,我们的交互式网络可视化还引入了(1)一种概念方法,该方法借鉴了近期的系统性综述研究,并通过出版物进行链接;(2)一种汇总方法,该方法利用公开可用的数据集构建,并通过横向联系进行链接。结论 这些新颖的元数据可视化技术可用作教学工具或发现方法,也可扩展到其他公共政策领域。
{"title":"Interactive network visualization of opioid crisis research: a tool for reinforcing data linkage skills for public health policy researchers","authors":"O. Scrivner, Thuy Nguyen, Michael Ginda, Kosali Simon, Katy Börner","doi":"10.3389/frai.2024.1208874","DOIUrl":"https://doi.org/10.3389/frai.2024.1208874","url":null,"abstract":"Background Public health policy researchers face a persistent challenge in identifying and integrating relevant data, particularly in the context of the U.S. opioid crisis, where a comprehensive approach is crucial. Purpose To meet this new workforce demand health policy and health economics programs are increasingly introducing data analysis and data visualization skills. Such skills facilitate data integration and discovery by linking multiple resources. Common linking strategies include individual or aggregate level linking (e.g., patient identifiers) in primary clinical data and conceptual linking (e.g., healthcare workforce, state funding, burnout rates) in secondary data. Often, the combination of primary and secondary datasets is sought, requiring additional skills, for example, understanding metadata and constructing interlinkages. Methods To help improve those skills, we developed a 2-step process using a scoping method to discover data and network visualization to interlink metadata. Results: We show how these new skills enable the discovery of relationships among data sources pertinent to public policy research related to the opioid overdose crisis and facilitate inquiry across heterogeneous data resources. In addition, our interactive network visualization introduces (1) a conceptual approach, drawing from recent systematic review studies and linked by the publications, and (2) an aggregate approach, constructed using publicly available datasets and linked through crosswalks. Conclusions These novel metadata visualization techniques can be used as a teaching tool or a discovery method and can also be extended to other public policy domains.","PeriodicalId":508738,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"4 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140736959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Frontiers in Artificial Intelligence
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
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
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1