Pub Date : 2024-08-07DOI: 10.1007/s10796-024-10524-8
Avijit Sengupta, Anik Mukherjee, Debra VanderMeer
Digitizing healthcare is a major aim of healthcare policy, with efforts aimed at increasing adoption of electronic health records (EHRs). We study the capability use for EHRs through the lens of normalisation process theory to assess whether these barriers to adoption also remain barriers to sustained use. We focus on health information exchange (HIE), which is one of the most challenging capabilities identified in the literature. We analyse the National Electronic Health Records Survey data, in which physicians were asked whether known HIE adoption barriers remain in place, and how frequently they use HIE capabilities. Though we expect that adoption barriers reported to be less problematic will be associated with greater capability use, we found that adoption barriers perceived to be more (less) problematic were not necessarily those that predicted less (greater) capability use. This study contributes through a critical examination of the process of normalization of EHR capabilities.
医疗保健数字化是医疗保健政策的一个主要目标,旨在提高电子健康记录(EHR)的采用率。我们从规范化过程理论的角度研究了电子健康记录的能力使用,以评估这些采用障碍是否仍然是持续使用的障碍。我们将重点放在健康信息交换(HIE)上,这是文献中指出的最具挑战性的能力之一。我们分析了全国电子健康记录调查的数据,其中医生被问及已知的 HIE 采用障碍是否仍然存在,以及他们使用 HIE 功能的频率。虽然我们预计问题较少的采用障碍会与更多的功能使用相关联,但我们发现,被认为问题较多(较少)的采用障碍并不一定会导致功能使用较少(较多)。本研究通过对电子病历功能正常化过程的批判性研究做出了贡献。
{"title":"Impact of Perceived Barriers of Electronic Health Information Exchange on Physician’s Use of EHR: A Normalisation Process Theory Approach","authors":"Avijit Sengupta, Anik Mukherjee, Debra VanderMeer","doi":"10.1007/s10796-024-10524-8","DOIUrl":"https://doi.org/10.1007/s10796-024-10524-8","url":null,"abstract":"<p>Digitizing healthcare is a major aim of healthcare policy, with efforts aimed at increasing adoption of electronic health records (EHRs). We study the capability use for EHRs through the lens of normalisation process theory to assess whether these barriers to adoption also remain barriers to sustained use. We focus on health information exchange (HIE), which is one of the most challenging capabilities identified in the literature. We analyse the National Electronic Health Records Survey data, in which physicians were asked whether known HIE adoption barriers remain in place, and how frequently they use HIE capabilities. Though we expect that adoption barriers reported to be less problematic will be associated with greater capability use, we found that adoption barriers perceived to be more (less) problematic were not necessarily those that predicted less (greater) capability use. This study contributes through a critical examination of the process of normalization of EHR capabilities.</p>","PeriodicalId":13610,"journal":{"name":"Information Systems Frontiers","volume":"45 1","pages":""},"PeriodicalIF":5.9,"publicationDate":"2024-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141899783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-07DOI: 10.1007/s10796-024-10522-w
Prasanta Kumar Pattanaik, Shivam Gupta, Ashis K. Pani, Urmii Himanshu, Ilias O. Pappas
Digitalization of the healthcare industry is a major trend and focus worldwide. It has the capability to improve the quality of care, reduce costs, and increase accessibility. India’s Healthcare Vision 2030 serves as a driving force compelling healthcare organization in India to embrace digitalization in their operations and services. We surveyed Indian healthcare employees to provide a comprehensive understanding of how external factors impact an organization's internal resources towards successful adoption of healthcare digitalization. The integration of three theoretical perspectives Institutional Theory (IP), Resource-Based View (RBV), and Absorptive Capacity Theory (ACT)) enables a more holistic and intricacies view. Our results emphasize that healthcare digital transformation requires more than just investment and time. Neglecting to respond to external pressures can lead to limited outcomes in digitalization efforts. It necessitates the presence of an appropriate organizational culture, accompanied by strong belief and support from top management.
{"title":"Impact of Inter and Intra Organizational Factors in Healthcare Digitalization: a Conditional Mediation Analysis","authors":"Prasanta Kumar Pattanaik, Shivam Gupta, Ashis K. Pani, Urmii Himanshu, Ilias O. Pappas","doi":"10.1007/s10796-024-10522-w","DOIUrl":"https://doi.org/10.1007/s10796-024-10522-w","url":null,"abstract":"<p>Digitalization of the healthcare industry is a major trend and focus worldwide. It has the capability to improve the quality of care, reduce costs, and increase accessibility. India’s Healthcare Vision 2030 serves as a driving force compelling healthcare organization in India to embrace digitalization in their operations and services. We surveyed Indian healthcare employees to provide a comprehensive understanding of how external factors impact an organization's internal resources towards successful adoption of healthcare digitalization. The integration of three theoretical perspectives Institutional Theory (IP), Resource-Based View (RBV), and Absorptive Capacity Theory (ACT)) enables a more holistic and intricacies view. Our results emphasize that healthcare digital transformation requires more than just investment and time. Neglecting to respond to external pressures can lead to limited outcomes in digitalization efforts. It necessitates the presence of an appropriate organizational culture, accompanied by strong belief and support from top management.</p>","PeriodicalId":13610,"journal":{"name":"Information Systems Frontiers","volume":"21 1","pages":""},"PeriodicalIF":5.9,"publicationDate":"2024-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141899784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-06DOI: 10.1007/s10796-024-10523-9
Nan Zhang, Chenhan Ruan, Xiwen Wang
Short video represents a novel form of social media with rich vividness and sociability, facilitating social media influencers’ (SMIs) self-presentations and endorsements. While SMIs become primary information sources through short videos, they also face challenges such as high return rates and consumer distrust. This research investigates how SMIs can effectively achieve authenticity through the design of self-presentation strategies, specifically focusing on credibility and attractiveness from a source-effect perspective. Across three studies, this research demonstrates that: (1) both credibility and attractiveness positively increase SMIs’ authenticity perception, mediated by para-social interaction; (2) credibility and attractiveness exhibit a negative interactive relationship; (3) the substitutability of credibility and attractiveness varies depending on the type of SMIs (informative vs. entertainment). This research contributes to the literature on short-video information processing and consumer attitudes toward SMIs based on authenticity building.
{"title":"You recommend, I trust: the interactive self-presentation strategies for social media influencers to build authenticity perception in short video scenes","authors":"Nan Zhang, Chenhan Ruan, Xiwen Wang","doi":"10.1007/s10796-024-10523-9","DOIUrl":"https://doi.org/10.1007/s10796-024-10523-9","url":null,"abstract":"<p>Short video represents a novel form of social media with rich vividness and sociability, facilitating social media influencers’ (SMIs) self-presentations and endorsements. While SMIs become primary information sources through short videos, they also face challenges such as high return rates and consumer distrust. This research investigates how SMIs can effectively achieve authenticity through the design of self-presentation strategies, specifically focusing on credibility and attractiveness from a source-effect perspective. Across three studies, this research demonstrates that: (1) both credibility and attractiveness positively increase SMIs’ authenticity perception, mediated by para-social interaction; (2) credibility and attractiveness exhibit a negative interactive relationship; (3) the substitutability of credibility and attractiveness varies depending on the type of SMIs (informative vs. entertainment). This research contributes to the literature on short-video information processing and consumer attitudes toward SMIs based on authenticity building.</p>","PeriodicalId":13610,"journal":{"name":"Information Systems Frontiers","volume":"125 1","pages":""},"PeriodicalIF":5.9,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141895462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-30DOI: 10.1007/s10796-024-10514-w
Zakaria El Hathat, V. G. Venkatesh, V. Raja Sreedharan, Tarik Zouadi, Arunmozhi Manimuthu, Yangyan Shi, S. Srivatsa Srinivas
As emphasized in multiple United Nations (UN) reports, sustainable agriculture, a key goal in the UN Sustainable Development Goals (SDGs), calls for dedicated efforts and innovative solutions. In this study, greenhouse gas (GHG) emissions in the groundnut supply chain from the region of Diourbel & Niakhar, Senegal, to the port of Dakar are investigated. The groundnut supply chain is divided into three steps: cultivation, harvesting, and processing/shipping. This work adheres to UN guidelines, addressing the imperative for sustainable agriculture by applying machine learning-based predictive modeling (MLPMs) utilizing the FAOSTAT and EDGAR databases. Additionally, it provides a novel approach using blockchain-enabled off-chain machine learning through smart contracts built on Hyperledger Fabric to secure GHG emissions storage and machine learning’s predictive analytics from fraud and enhance transparency and data security. This study also develops a decision-making dashboard to provide actionable insights for GHG emissions reduction strategies across the groundnut supply chain.
{"title":"Leveraging Greenhouse Gas Emissions Traceability in the Groundnut Supply Chain: Blockchain-Enabled Off-Chain Machine Learning as a Driver of Sustainability","authors":"Zakaria El Hathat, V. G. Venkatesh, V. Raja Sreedharan, Tarik Zouadi, Arunmozhi Manimuthu, Yangyan Shi, S. Srivatsa Srinivas","doi":"10.1007/s10796-024-10514-w","DOIUrl":"https://doi.org/10.1007/s10796-024-10514-w","url":null,"abstract":"<p>As emphasized in multiple United Nations (UN) reports, sustainable agriculture, a key goal in the UN Sustainable Development Goals (SDGs), calls for dedicated efforts and innovative solutions. In this study, greenhouse gas (GHG) emissions in the groundnut supply chain from the region of Diourbel & Niakhar, Senegal, to the port of Dakar are investigated. The groundnut supply chain is divided into three steps: cultivation, harvesting, and processing/shipping. This work adheres to UN guidelines, addressing the imperative for sustainable agriculture by applying machine learning-based predictive modeling (MLPMs) utilizing the FAOSTAT and EDGAR databases. Additionally, it provides a novel approach using blockchain-enabled off-chain machine learning through smart contracts built on Hyperledger Fabric to secure GHG emissions storage and machine learning’s predictive analytics from fraud and enhance transparency and data security. This study also develops a decision-making dashboard to provide actionable insights for GHG emissions reduction strategies across the groundnut supply chain.</p>","PeriodicalId":13610,"journal":{"name":"Information Systems Frontiers","volume":"18 1","pages":""},"PeriodicalIF":5.9,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141857870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-29DOI: 10.1007/s10796-024-10515-9
Gokce Baysal Turkolmez, Zakaria El Hathat, Nachiappan Subramanian, Saravanan Kuppusamy, V. Raja Sreedharan
Due to the growing volume of e-waste in the world and its environmental impact, it is important to understand how to extend the useful life of electronic items. In this paper, we examine the remanufacturing process of end-of-life laptops for third-party remanufacturers and consider their pricing problem, which involves issues like a lack of reliable datasets, fluctuating costs of new components, and difficulties in benchmarking laptop prices, to name a few. We develop a unique approach that uses machine learning algorithms to help price remanufactured laptops. Our methodology involves a variety of techniques, which include an additive model, CART analysis, Random Forest, and Polynomial Regression. We consider depreciation and discount factors to account for the varying ages and conditions of laptops when estimating remanufactured laptop prices. Finally, we also compare our estimated prices to traditional prices. In summary, we leverage data-driven decision-making and develop a robust methodology for pricing remanufactured laptops to extend their lifespan.
{"title":"Machine Learning Algorithms for Pricing End-of-Life Remanufactured Laptops","authors":"Gokce Baysal Turkolmez, Zakaria El Hathat, Nachiappan Subramanian, Saravanan Kuppusamy, V. Raja Sreedharan","doi":"10.1007/s10796-024-10515-9","DOIUrl":"https://doi.org/10.1007/s10796-024-10515-9","url":null,"abstract":"<p>Due to the growing volume of e-waste in the world and its environmental impact, it is important to understand how to extend the useful life of electronic items. In this paper, we examine the remanufacturing process of end-of-life laptops for third-party remanufacturers and consider their pricing problem, which involves issues like a lack of reliable datasets, fluctuating costs of new components, and difficulties in benchmarking laptop prices, to name a few. We develop a unique approach that uses machine learning algorithms to help price remanufactured laptops. Our methodology involves a variety of techniques, which include an additive model, CART analysis, Random Forest, and Polynomial Regression. We consider depreciation and discount factors to account for the varying ages and conditions of laptops when estimating remanufactured laptop prices. Finally, we also compare our estimated prices to traditional prices. In summary, we leverage data-driven decision-making and develop a robust methodology for pricing remanufactured laptops to extend their lifespan.</p>","PeriodicalId":13610,"journal":{"name":"Information Systems Frontiers","volume":"62 1","pages":""},"PeriodicalIF":5.9,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141790983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-23DOI: 10.1007/s10796-024-10516-8
Christos K. Filelis-Papadopoulos, Samuel N. Kirshner, Philip O’Reilly
Unforeseen events (e.g., COVID-19, the Russia-Ukraine conflict) create significant challenges for accurately predicting CO2 emissions in the airline industry. These events severely disrupt air travel by grounding planes and creating unpredictable, ad hoc flight schedules. This leads to many missing data points and data quality issues in the emission datasets, hampering accurate prediction. To address this issue, we develop a predictive analytics method to forecast CO2 emissions using a unique dataset of monthly emissions from 29,707 aircraft. Our approach outperforms prominent machine learning techniques in both accuracy and computational time. This paper contributes to theoretical knowledge in three ways: 1) advancing predictive analytics theory, 2) illustrating the organisational benefits of using analytics for decision-making, and 3) contributing to the growing focus on aviation in information systems literature. From a practical standpoint, our industry partner adopted our forecasting approach under an evaluation licence into their client-facing CO2 emissions platform.
{"title":"Sustainability with Limited Data: A Novel Predictive Analytics Approach for Forecasting CO2 Emissions","authors":"Christos K. Filelis-Papadopoulos, Samuel N. Kirshner, Philip O’Reilly","doi":"10.1007/s10796-024-10516-8","DOIUrl":"https://doi.org/10.1007/s10796-024-10516-8","url":null,"abstract":"<p>Unforeseen events (e.g., COVID-19, the Russia-Ukraine conflict) create significant challenges for accurately predicting CO2 emissions in the airline industry. These events severely disrupt air travel by grounding planes and creating unpredictable, ad hoc flight schedules. This leads to many missing data points and data quality issues in the emission datasets, hampering accurate prediction. To address this issue, we develop a predictive analytics method to forecast CO2 emissions using a unique dataset of monthly emissions from 29,707 aircraft. Our approach outperforms prominent machine learning techniques in both accuracy and computational time. This paper contributes to theoretical knowledge in three ways: 1) advancing predictive analytics theory, 2) illustrating the organisational benefits of using analytics for decision-making, and 3) contributing to the growing focus on aviation in information systems literature. From a practical standpoint, our industry partner adopted our forecasting approach under an evaluation licence into their client-facing CO2 emissions platform.</p>","PeriodicalId":13610,"journal":{"name":"Information Systems Frontiers","volume":"52 1","pages":""},"PeriodicalIF":5.9,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141755259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-19DOI: 10.1007/s10796-024-10517-7
Ali Dag, Abdullah Asilkalkan, Osman T. Aydas, Musa Caglar, Serhat Simsek, Dursun Delen
Effective management of colorectal cancer (CRC) necessitates precise prognostication and informed decision-making, yet existing literature often lacks emphasis on parsimonious variable selection and conveying complex interdependencies among factors to medical practitioners. To address this gap, we propose a decision support system integrating Elastic Net (EN) and Simulated Annealing (SA) algorithms for variable selection, followed by Tree Augmented Naive Bayes (TAN) modeling to elucidate conditional relationships. Through k-fold cross-validation, we identify optimal TAN models with varying variable sets and explore interdependency structures. Our approach acknowledges the challenge of conveying intricate relationships among numerous variables to medical practitioners and aims to enhance patient-physician communication. The stage of cancer emerges as a robust predictor, with its significance amplified by the number of metastatic lymph nodes. Moreover, the impact of metastatic lymph nodes on survival prediction varies with the age of diagnosis, with diminished relevance observed in older patients. Age itself emerges as a crucial determinant of survival, yet its effect is modulated by marital status. Leveraging these insights, we develop a web-based tool to facilitate physician–patient communication, mitigate clinical inertia, and enhance decision-making in CRC treatment. This research contributes to a parsimonious model with superior predictive capabilities while uncovering hidden conditional relationships, fostering more meaningful discussions between physicians and patients without compromising patient satisfaction with healthcare provision.
结直肠癌(CRC)的有效治疗需要精确的预后和明智的决策,但现有文献往往缺乏对变量选择的重视,也没有向医疗从业人员传达各因素之间复杂的相互依存关系。为了弥补这一不足,我们提出了一种决策支持系统,该系统集成了弹性网(EN)和模拟退火(SA)算法来选择变量,然后用树增强奈何贝叶(TAN)建模来阐明条件关系。通过 k 倍交叉验证,我们确定了具有不同变量集的最佳 TAN 模型,并探索了相互依存结构。我们的方法认识到了向医疗从业人员传达众多变量之间错综复杂的关系所面临的挑战,旨在加强患者与医生之间的沟通。癌症分期是一个强有力的预测因素,其重要性因转移淋巴结的数量而放大。此外,转移性淋巴结对生存预测的影响随确诊年龄的不同而变化,老年患者的相关性更小。年龄本身是生存率的重要决定因素,但其影响受婚姻状况的调节。利用这些见解,我们开发了一种基于网络的工具,以促进医生与患者之间的交流,缓解临床惰性,并加强对 CRC 治疗的决策。这项研究有助于建立一个具有卓越预测能力的简约模型,同时揭示隐藏的条件关系,促进医生和患者之间进行更有意义的讨论,而不会影响患者对医疗服务的满意度。
{"title":"A Parsimonious Tree Augmented Naive Bayes Model for Exploring Colorectal Cancer Survival Factors and Their Conditional Interrelations","authors":"Ali Dag, Abdullah Asilkalkan, Osman T. Aydas, Musa Caglar, Serhat Simsek, Dursun Delen","doi":"10.1007/s10796-024-10517-7","DOIUrl":"https://doi.org/10.1007/s10796-024-10517-7","url":null,"abstract":"<p>Effective management of colorectal cancer (CRC) necessitates precise prognostication and informed decision-making, yet existing literature often lacks emphasis on parsimonious variable selection and conveying complex interdependencies among factors to medical practitioners. To address this gap, we propose a decision support system integrating Elastic Net (EN) and Simulated Annealing (SA) algorithms for variable selection, followed by Tree Augmented Naive Bayes (TAN) modeling to elucidate conditional relationships. Through k-fold cross-validation, we identify optimal TAN models with varying variable sets and explore interdependency structures. Our approach acknowledges the challenge of conveying intricate relationships among numerous variables to medical practitioners and aims to enhance patient-physician communication. The stage of cancer emerges as a robust predictor, with its significance amplified by the number of metastatic lymph nodes. Moreover, the impact of metastatic lymph nodes on survival prediction varies with the age of diagnosis, with diminished relevance observed in older patients. Age itself emerges as a crucial determinant of survival, yet its effect is modulated by marital status. Leveraging these insights, we develop a web-based tool to facilitate physician–patient communication, mitigate clinical inertia, and enhance decision-making in CRC treatment. This research contributes to a parsimonious model with superior predictive capabilities while uncovering hidden conditional relationships, fostering more meaningful discussions between physicians and patients without compromising patient satisfaction with healthcare provision.</p>","PeriodicalId":13610,"journal":{"name":"Information Systems Frontiers","volume":"69 1","pages":""},"PeriodicalIF":5.9,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141726304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The COVID-19 pandemic has highlighted the critical need for advanced technology in healthcare. Clinical Decision Support Systems (CDSS) utilizing Artificial Intelligence (AI) have emerged as one of the most promising technologies for improving patient outcomes. This study’s focus on developing a deep state-space model (DSSM) is of utmost importance, as it addresses the current limitations of AI predictive models in handling high-dimensional and longitudinal electronic health records (EHRs). The DSSM’s ability to capture time-varying information from unstructured medical notes, combined with label-dependent attention for interpretability, will allow for more accurate risk prediction for patients. As we move into a post-COVID-19 era, the importance of CDSS in precision medicine cannot be ignored. This study’s contribution to the development of DSSM for unstructured medical notes has the potential to greatly improve patient care and outcomes in the future.
{"title":"Modelling Patient Longitudinal Data for Clinical Decision Support: A Case Study on Emerging AI Healthcare Technologies","authors":"Shuai Niu, Jing Ma, Qing Yin, Zhihua Wang, Liang Bai, Xian Yang","doi":"10.1007/s10796-024-10513-x","DOIUrl":"https://doi.org/10.1007/s10796-024-10513-x","url":null,"abstract":"<p>The COVID-19 pandemic has highlighted the critical need for advanced technology in healthcare. Clinical Decision Support Systems (CDSS) utilizing Artificial Intelligence (AI) have emerged as one of the most promising technologies for improving patient outcomes. This study’s focus on developing a deep state-space model (DSSM) is of utmost importance, as it addresses the current limitations of AI predictive models in handling high-dimensional and longitudinal electronic health records (EHRs). The DSSM’s ability to capture time-varying information from unstructured medical notes, combined with label-dependent attention for interpretability, will allow for more accurate risk prediction for patients. As we move into a post-COVID-19 era, the importance of CDSS in precision medicine cannot be ignored. This study’s contribution to the development of DSSM for unstructured medical notes has the potential to greatly improve patient care and outcomes in the future.</p>","PeriodicalId":13610,"journal":{"name":"Information Systems Frontiers","volume":"40 1","pages":""},"PeriodicalIF":5.9,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141726300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-18DOI: 10.1007/s10796-024-10512-y
Sara Migliorini, Anna Dalla Vecchia, Alberto Belussi, Elisa Quintarelli
Recommendation systems are becoming an invaluable assistant not only for users, who may be disoriented in the presence of a huge number of different alternatives, but also for service providers or sellers, who would like to be able to guide the choice of customers toward particular items with specific characteristics. This influence capability can be particularly useful in the tourism domain, where the need to manage the industry in a more sustainable way and the ability to predict and control the level of crowding of PoIs (Points of Interest) have become more pressing in recent years. In this paper, we study the role of contextual information in determining both PoI occupations and user preferences, and we explore how machine learning and deep learning techniques can help produce good recommendations for users by enriching historical information with its contextual counterpart. As a result, we propose the architecture of ARTEMIS, a context-Aware Recommender sysTEM wIth crowding forecaSting, able to learn and forecast user preferences and occupation levels based on historical contextual features. Throughout the paper, we refer to a real-world application scenario regarding the tourist visits performed in Verona, a municipality in Northern Italy, between 2014 and 2019.
推荐系统正在成为一种无价的助手,它不仅可以帮助用户在面对大量不同选择时迷失方向,还可以帮助服务提供商或销售商引导客户选择具有特定特征的商品。这种影响能力在旅游领域尤为有用,近年来,以更可持续的方式管理旅游业的需求以及预测和控制兴趣点(PoIs)拥挤程度的能力变得更加迫切。在本文中,我们研究了上下文信息在决定 PoI 职业和用户偏好方面的作用,并探讨了机器学习和深度学习技术如何通过丰富历史信息与上下文信息的对应关系来帮助为用户提供良好的推荐。因此,我们提出了 ARTEMIS 的架构,这是一个具有拥挤预测功能的情境感知推荐系统,能够根据历史情境特征学习和预测用户偏好和职业水平。在整篇论文中,我们引用了一个真实世界的应用场景,涉及 2014 年至 2019 年期间在意大利北部维罗纳市进行的游客访问。
{"title":"ARTEMIS: a Context-Aware Recommendation System with Crowding Forecaster for the Touristic Domain","authors":"Sara Migliorini, Anna Dalla Vecchia, Alberto Belussi, Elisa Quintarelli","doi":"10.1007/s10796-024-10512-y","DOIUrl":"https://doi.org/10.1007/s10796-024-10512-y","url":null,"abstract":"<p>Recommendation systems are becoming an invaluable assistant not only for users, who may be disoriented in the presence of a huge number of different alternatives, but also for service providers or sellers, who would like to be able to guide the choice of customers toward particular items with specific characteristics. This influence capability can be particularly useful in the tourism domain, where the need to manage the industry in a more sustainable way and the ability to predict and control the level of crowding of PoIs (Points of Interest) have become more pressing in recent years. In this paper, we study the role of contextual information in determining both PoI occupations and user preferences, and we explore how machine learning and deep learning techniques can help produce good recommendations for users by enriching historical information with its contextual counterpart. As a result, we propose the architecture of ARTEMIS, a context-Aware Recommender sysTEM wIth crowding forecaSting, able to learn and forecast user preferences and occupation levels based on historical contextual features. Throughout the paper, we refer to a real-world application scenario regarding the tourist visits performed in Verona, a municipality in Northern Italy, between 2014 and 2019.</p>","PeriodicalId":13610,"journal":{"name":"Information Systems Frontiers","volume":"66 1","pages":""},"PeriodicalIF":5.9,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141726330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recently, 5G/B5G/6G networks (5G for short) have been gloriously developed to give us colorful lives and make our daily activities more convenient than before. On the other hand, online meetings, like video conferences and online educations, have been popularly held everywhere in the world. Nevertheless, in such a meeting on 5G networks, a packet P transmitted from a User Plane Function (UPF), e.g., UPF1 of a 5G, e.g., 5G1, to P’s destinations, e.g., the set {UPF2, UPF3, …UPFn}, respectively, in {5G2, 5G3, …5Gn}, is not secure, even not encrypted, particularly when P goes through the Internet. Hackers may duplicate P, i.e., data leakage on the connections among these UPFs. The situation needs to be avoided when data of the meetings ought not to be leaked, e.g., for an important military conference. Therefore, in this study, we propose a security architecture, named Group Key using IKA (GKIKA), which encrypts/decrypt packets before sending them, e.g., EC1 in 5G1 encrypts P and then sends P’s ciphertext which will be decrypted by edge computers {EC2, EC3, …ECn} where ECj is in 5Gj, (2le jle n). Our security scenarios include data transmission among n-parties, n(ge) 2. When n(=) 2, symmetric or asymmetric cryptography is adopted depending on the security level and time constraints required. As n(>) 2, the Initial Key Agreement (IKA) is utilized to establish a secret key for all participating ECs. Other security mechanisms, like message authentication code and time stamp, are also utilized to enhance the security level of data transmission. Our analyses show that the GKIKA can effectively avoid some types of attacks.
近来,5G/B5G/6G 网络(简称 5G)光彩夺目,为我们带来了丰富多彩的生活,使我们的日常活动比以前更加便捷。另一方面,视频会议和在线教育等在线会议已在世界各地普及。然而,在 5G 网络上举行这样的会议时,从用户平面功能(UPF)(如 5G1 的 UPF1)向 P 的目的地(如 {UPF2、UPF3、...UPFn} 中的集合 {UPF2、UPF3、...UPFn})传输的数据包 P 并不安全,甚至没有加密,尤其是当 P 通过互联网时。黑客可能会复制 P,即在这些 UPF 之间的连接上泄漏数据。当会议数据不应泄漏时,如重要的军事会议,就需要避免这种情况。因此,在本研究中,我们提出了一种安全架构,命名为使用IKA的组密钥(GKIKA),它在发送数据包之前对其进行加密/解密,例如,5G1中的EC1对P进行加密,然后发送P的密文,密文将由边缘计算机{EC2,EC3,...ECn}解密,其中ECj在5Gj中,(2le jle n)。我们的安全场景包括n方之间的数据传输,n()2。 当n()2时,根据所需的安全级别和时间限制,采用对称或非对称加密技术。当 n (=)2 时,使用初始密钥协议(IKA)为所有参与的 EC 建立密钥。其他安全机制,如信息验证码和时间戳,也被用来提高数据传输的安全级别。我们的分析表明,GKIKA 可以有效避免某些类型的攻击。
{"title":"Security among UPFs belonging to Different 5G/B5G/6G Networks","authors":"Liang-Sheng Hsiao, Kun-Lin Tsai, Jung-Chun Liu, Fang-Yie Leu, Yu-Syuan Lu, I-Long Lin","doi":"10.1007/s10796-024-10510-0","DOIUrl":"https://doi.org/10.1007/s10796-024-10510-0","url":null,"abstract":"<p>Recently, 5G/B5G/6G networks (5G for short) have been gloriously developed to give us colorful lives and make our daily activities more convenient than before. On the other hand, online meetings, like video conferences and online educations, have been popularly held everywhere in the world. Nevertheless, in such a meeting on 5G networks, a packet P transmitted from a User Plane Function (UPF), e.g., UPF<sub>1</sub> of a 5G, e.g., 5G<sub>1</sub>, to P’s destinations, e.g., the set {UPF<sub>2</sub>, UPF<sub>3</sub>, …UPF<sub><i>n</i></sub>}, respectively, in {5G<sub>2</sub>, 5G<sub>3</sub>, …5G<sub><i>n</i></sub>}, is not secure, even not encrypted, particularly when P goes through the Internet. Hackers may duplicate P, i.e., data leakage on the connections among these UPFs. The situation needs to be avoided when data of the meetings ought not to be leaked, e.g., for an important military conference. Therefore, in this study, we propose a security architecture, named Group Key using IKA (GKIKA), which encrypts/decrypt packets before sending them, e.g., EC<sub>1</sub> in 5G<sub>1</sub> encrypts P and then sends P’s ciphertext which will be decrypted by edge computers {EC<sub>2</sub>, EC<sub>3</sub>, …EC<sub><i>n</i></sub>} where EC<sub><i>j</i></sub> is in 5G<sub><i>j</i></sub>, <span>(2le jle n)</span>. Our security scenarios include data transmission among <i>n</i>-parties, <i>n</i> <span>(ge)</span> 2. When<i> n</i> <span>(=)</span> 2, symmetric or asymmetric cryptography is adopted depending on the security level and time constraints required. As <i>n</i> <span>(>)</span> 2, the Initial Key Agreement (IKA) is utilized to establish a secret key for all participating ECs. Other security mechanisms, like message authentication code and time stamp, are also utilized to enhance the security level of data transmission. Our analyses show that the GKIKA can effectively avoid some types of attacks.</p>","PeriodicalId":13610,"journal":{"name":"Information Systems Frontiers","volume":"7 1","pages":""},"PeriodicalIF":5.9,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141625034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}