Artificial Intelligence (AI) has introduced significant innovations in healthcare, yet its adoption has been slower compared to other industries. A key barrier lies in concerns over trustworthiness, as healthcare stakeholders often express skepticism stemming from the opacity of AI systems, risks of privacy breaches, potential biases that exacerbate social inequities, and unresolved safety issues. Ensuring trustworthy AI is therefore essential for its safe, effective, and responsible integration into clinical practice. This integrative review examines four fundamental dimensions of trustworthy AI in healthcare: transparency and explainability, privacy and security, robustness and safety, and bias and fairness. Unlike prior surveys that either addressed trustworthiness in AI broadly or focused narrowly on traditional machine learning and deep learning (DL), this work extends the discussion to Large Language Models and Agentic AI, both of which are poised to play transformative roles in healthcare. We also explore the intersections among trustworthiness dimensions and highlight the often-overlooked roles of user trust and organizational accountability in shaping real-world adoption. Finally, we provide targeted recommendations, outlining practical tools, frameworks, and strategies tailored to different model classes to address concrete trustworthiness challenges in healthcare AI.

Foundation models are being broadly adopted for downstream tasks and then deployed in real-world systems due to their diverse and generalization capabilities. This versatility allows them to excel across various domains, providing a strong basis for building specialized models and solutions, thus, accelerating the process of artificial intelligence (AI) transition from research to real-world deployment. However, these foundation models and implemented AI systems driven by these models present many challenges, particularly in the area of trustworthiness. They might be vulnerable to adversarial attacks, output incorrect answers or decisions, biased against certain groups, prone to privacy leakage etc. This can cause severe outcomes, especially with the application of AI in high stake areas such as finance and healthcare. Thus, developing trustworthiness of foundation models-based AI systems has become important and necessary. Trustworthy AI systems ensure reliability, safety, and fairness, making them crucial for successful real-world implementation and user acceptance. The core questions under this survey topic are: How to define trustworthiness in foundation models? What trustworthy aspects should we take into consideration regarding foundation models? What approaches can enhance their trustworthiness? What are challenges and what future directions? In this survey, we present a comprehensive analysis of what constitute trustworthy foundation model. We summarized, analysed and discussed highly relevant trustworthy aspects for foundation models. To structure our analysis, we also formalized lifecycle of foundation model-based AI systems. This allowed us to specify the requirements and approaches for each stage of the lifecycle. Lastly, we outlined challenges and future directions towards trustworthy foundation models. The main contributions of this paper are four-fold: (1) Formalization of the lifecycle for foundation models and definition of each phase. (2) Summary of key trustworthy aspects of foundation models and define them. (3) Examination of approaches for each aspects across the lifecycle. (4) Identification of challenges, gaps, and future directions.

Purpose This study examines psychological strain in gig work by analyzing how algorithmic management (AM), framed through the Job Demands-Resources (JD-R) model and Self-Determination Theory (SDT), shapes strain outcomes. We compare gig and non-gig workers to isolate the influence of AM.Design/methodology/approach Using LIWC, we analyze 6,505 Glassdoor job reviews to compare psychological strain among drivers in gig versus non-gig roles.Findings Counterintuitively, compensation and work-life balance - typically strain-buffering resources - are associated with increased strain for gig workers, suggesting that algorithmic control alters how resources are experienced.Research limitations/implications The findings suggest that within the 'digital cage' of the gig economy, the traditional JD-R resource-to-strain pathway is reconfigured. This highlights the need for research that investigates how the delivery mechanism (AM) of a resource can neutralize its buffering potential.Practical implications Platform organizations must recognize that simply increasing pay or flexibility within need-thwarting structures may inadvertently worsen worker strain. Practitioners should prioritize autonomy-supportive algorithmic designs - moving away from gamified, opaque incentives toward transparent systems that restore operational control to the worker.Originality/value This research provides evidence that AM does not merely add demands but fundamentally reshapes the relationship between job resources and strain within the gig economy. It problematizes the "autonomy paradox" in gig work to explain why the JD-R resource pathway breaks down.

Since the advent of the digital age, the transformation of government operations, policy-making, citizen engagement, and public services has fundamentally reshaped the relationships between citizens and public institutions. Digital government, as a field of study, has evolved to address the complex challenges at the intersection of technology, governance, and society. Over the past decades, Government Information Quarterly (GIQ) has played a pivotal role in documenting and shaping this evolution from basic computerization to sophisticated digital transformation initiatives. The impact of digitalization extends across all aspects of public administration, from service delivery and policy-making to citizen engagement and democratic processes. This study brings together perspectives from leading digital government scholars to examine the nature of digital government research. Through the analysis of the journal's distinctive identity and characteristics, evolution, theoretical landscape, and methodological approaches, it offers insights into how GIQ has evolved to a transdisciplinary platform that bridges theoretical foundations with practical applications while consistently addressing emerging technological challenges, fundamental public sector values, and high-value public policy goals.

Artificial Intelligence (AI) is increasingly adopted by public sector organizations to provide better public services and to transform their internal processes. AI is now considered a key enabler for digital innovation and transformation in the public sector. However, AI is still relatively a new research area in the field of digital government. The term, AI, captures a wide range of technologies, techniques, and tools such as machine/deep learning, natural language processing, robotics, computer vision, and more recently Generative AI. While these AI technologies afford different applications and benefits in the government context, they also create social, ethical, and legal challenges. These challenges require solutions combining both technical (e.g., data and algorithmic solutions to minimize bias) and institutional (e.g., governance structures and processes) mechanisms. The special issue is a collection of articles that contribute to a better understanding of the issues associated with AI deployment in different areas of government operations. They cover AI applications in the areas of emergency response, policy analysis, public bids, and citizen participation. The contributions also address the challenge of realizing a legal transparency regime for AI in government and the effect of AI in bureaucratic decision-making.

Patient experience surveys have become a key source of evidence for supporting decision-making and continuous quality improvement within healthcare services. To harness free-text feedback collected as part of these surveys for additional insights, text analytics methods are increasingly employed when the data collected is not amenable to traditional qualitative analysis due to volume. However, while text analytics techniques offer good predictive capabilities, they have limited explanatory features often required in formal decision-making contexts, such as programme monitoring or evaluation. To overcome these limitations, this study integrates computational text and predictive modelling as part of a Computational Grounded Theory method to determine the effect of quality gaps in care dimensions and their prioritisation from free-text feedback. The feedback was collected as part of a national survey to support decisions on continuous improvement in Maternity Services in Ireland. Our approach enables (1) operationalising the service quality lexicon in the context of maternity care to explain the effect of quality gaps in care dimensions on overall satisfaction from free-text comments; and (2) extending the service quality lexicon with two organisational and political decision-making concepts: “Salience” and “Valence”, for prioritising perceived quality gaps. These methodological affordances enable the extension of service quality theory to explicitly support the prioritisation of improvement decisions which before now required additional decision frameworks. Results show that tangibles-, process-, and reliability-related care issues have the highest importance in our study context. We also find that hospital contexts partly determine the relative importance of gaps in care dimensions.

Many scholars argue that there is a deepening crisis of trust in healthcare systems. What is not contested is the centrality of public trust in building reputational value in healthcare organisations. However, there is a dearth of research focused on better understanding how trust in healthcare institutions, and the healthcare workforce, can be sustainably cultivated.To enable the exploration of care-related factors within hospitals and their potential impacts on trust in healthcare workers, this dataset was created based on the 2020 National Maternity Experience Survey data. The survey data include responses to 68 structured, tick-box questions and three open-ended questions prepared with the participation of over 250 healthcare practitioners and experts, patients, as well as policymakers and researchers. The survey covers the full pathway of maternity care from antenatal care, through labour and birth, to postnatal care in the community. A total of 19 maternity hospitals and units participated in the survey which ran from February to April 2020, resulting in a total of 3,204 women responses out of an eligible population of 6,357. The survey data was extended with contextual information from a monitoring report on the National Maternity Services Standard published in 2020. The additional data includes compliance levels of maternity hospitals with established standards in four key areas including effective care support, safe care support, leadership governance and management, and workforce. This curated dataset can support investigations into a) the factors that determine overall women's care experience, b) factors contributing to building confidence and trust in the maternity care workforce among different groups of women, and c) how hospital environment, processes and governance impact both women's trust in maternity hospitals and their overall satisfaction.

High-quality labelled datasets represent a cornerstone in the development of deep learning models for land use classification. The high cost of data collection, the inherent errors introduced during data mapping efforts, the lack of local knowledge, and the spatial variability of the data hinder the development of accurate and spatially-transferable deep learning models in the context of agriculture. In this paper, we investigate the use of Isolation Forest (IF), an anomaly detection algorithm, to reduce noise in a large-scale, low-resolution alternative ground truth dataset used to train land use deep learning models. We use a modest-size, high-resolution and high-fidelity manually collected ground-truth dataset to calibrate Isolation Forest parameters and evaluate our approach, highlighting the relatively low cost of the methodology. Our data-centric methodology demonstrates the efficacy of deep learning methods coupled with IF to create mid-resolution land-use models and map products for agriculture using an alternative ground-truth dataset. Moreover, we compare our deep learning approach with a traditional algorithm used in remote sensing and evaluate the spatial transferability of the created models. Finally, we reflect upon the lessons learnt and future work.

National surveys on care experiences are increasingly adopted as regulatory mechanisms for improving care quality and increasing public trust in healthcare services. Based on data collected as part of Ireland's 2020 National Maternity Experience Survey, this study investigates care-related factors that contribute most to confidence and trust in the professional workforce (or carers) within Irish maternity services. The survey covered the full spectrum of maternity care and received 3,206 responses which were analysed using structural equation modelling. Results show that trust in carers may be enhanced through greater attention to the quality of interpersonal aspects of maternity care in a few core areas. We found that factors related to dignity and respect (β=0.270), involvement in decision-making (β=0.186), pain management (β=0.172), and communication (β=0.151) are core determinants of confidence and trust in the professional workforce of maternity services. Perceived quality of care in these four aspects increased on average, with the women's age. Women under 29 rated their experiences in these areas as significantly lower than the average. Women with a disability also rated their experiences significantly lower than average in three core areas. Our results suggest that trustworthy, equitable, and high-quality maternity care requires ongoing development of interpersonal skills within the maternity services professional workforce particularly in caring for younger women (under 29 years) and those with a disability.

E-Governance primarily employs information and communication technologies (ICT) to facilitate the inclusion of citizens and non-state actors in government decision-making, particularly in co-producing and administering public policies, while delivering public services. Globally, e-governance is becoming more prevalent, especially in the context of the Sustainable Development Goals (SDGs). The achievement of the SDGs touches all spheres of society including both urban and rural areas. It is of high interest to develop tools for governments to measure how rurality affects the enabling function of e-governance though it is quite challenging. Among many measurements on e-government, the United Nations Department of Economic and Social Affairs (UNDESA) is quite concurrent. Its local service index (LOSI) is in the pilot stage, and it needs to gain momentum. The LOSI has the potential to be inclusive by assessing rural areas. The paper develops a framework to support LOSI in rural areas and a use case in the Indian context is presented to explain the relevance. It argues for a separate LOSI in rural areas.

In this study, we examine the relationship between anxiety and athletic performance, measuring pre-game anxiety in a corpus of 12,228 tweets of 81 National Basketball Association (NBA) players using an anxiety inference algorithm, and match this data with certified NBA individual player game performance data. We found a positive relationship between pre-game anxiety and athletic performance, which was moderated by both player experience and minutes played on the court. This paper serves to demonstrate the use case for using machine learning to label publicly available micro-blogs of players which can be used to form important discrete emotions, such as pre-game anxiety, which in turn can predict athletic performance in elite sports. Based on the results, we discuss these findings and outline recommendations for athletes, teams, team leaders, coaches, and managers.

Abstract Background Patient experience surveys are a key source of evidence for supporting decision-making and quality improvement in healthcare services. These surveys contain two main types of questions: closed and open-ended, asking about patients’ care experiences. Apart from the knowledge obtained from analysing closed-ended questions, invaluable insights can be gleaned from free-text data. Advanced analytics techniques are increasingly used to harness free-text data, yet existing approaches do not offer the rigour required to support formal decision-making through free-text. Methods This study addresses the challenge of effectively and rigorously analysing patients’ free-text feedback to improve maternity and acute hospital services in Ireland. Aspects of healthcare services (i.e. themes) that could be improved were determined using computational text analytics and predictive modelling. Themes extracted from comments were prioritised based on volume, the intensity of negative affect expressed in the texts, and the estimated influence of the themes on overall patient satisfaction. Results Results demonstrate the viability of producing rigorous evidence for prioritising interventions to improve healthcare services based on free-text feedback. Specifically, consistency in advice and support in breastfeeding were among the most important issues for maternity services. For acute hospital services, meals quality and access, A&E waiting time, ward hygiene and communication at discharge were among the most important issues. Women also wanted more emphasis on prior birth experience and complications in future maternity care surveys. Conclusions Advances in computational text modelling enable the extraction of concrete and actionable insights from the analysis of free-text data. This approach also allows decision-makers to prioritise emergent themes and inform actions that will positively impact overall patient satisfaction.

Recent research has shown that organizational leaders' tweets can influence employee anxiety. In this study, we turn the table and examine whether the same can be said about followers' tweets. Based on emotional contagion and a dataset of 108 leaders and 178 followers across 50 organizations, we infer and track state- and trait-anxiety scores of participants over 316 days, including pre- and post the onset of the SARS-CoV-2 pandemic and crisis. We show that although leaders traditionally possess greater authority and power than their followers, followers have the power to influence their leaders' state anxiety. In addition, this influence is particularly strong in the case of less trait anxious leaders.

Tax administrations worldwide have become highly digitised with a diverse and sophisticated array of e-services to enhance the taxpayer experience. Nevertheless, given the high rates of failure of e-government services, it is critical to understand the factors that are essential to the success of a digital tax system. Drawing on a systematic review of ninety-six publications across the digital taxation, taxation, and information systems (IS) literature, a comprehensive conceptual framework is developed to improve our success of digital services in tax administration. The conceptual framework identifies fifteen themes for consideration by policymakers when designing digital services in tax administrations clustered around four categories - Context, Stakeholders, Technology and Demonstrated Results. The framework should also serve as a reference point in successfully developing strategies and measures to embed digital services in tax administrations. Future research directions are also proposed based on the conceptual framework that will help advance our understanding of digital services in tax administration beyond technology acceptance models.

Introduction: The National Care Experience Programme (NCEP) conducts national surveys that ask people about their experiences of care in order to improve the quality of health and social care services in Ireland. Each survey contains open-ended questions, which allow respondents to comment on their experiences. While these comments provide important and valuable information about what matters most to service users, there is to date no unified approach to the analysis and integration of this detailed feedback. The objectives of this study are to analyse qualitative responses to NCEP surveys to determine the key care activities, resources and contextual factors related to positive and negative experiences; to identify key areas for improvement, policy development, healthcare regulation and monitoring; and to provide a tool to access the results of qualitative analyses on an ongoing basis to provide actionable insights and drive targeted improvements. Methods: Computational text analytics methods will be used to analyse 93,135 comments received in response to the National Inpatient Experience Survey and National Maternity Experience Survey. A comprehensive analytical framework grounded in both service management literature and the NCEP data will be employed as a coding framework to underpin automated analyses of the data using text analytics and deep learning techniques. Scenario-based designs will be adopted to determine effective ways of presenting insights to knowledge users to address their key information and decision-making needs. Conclusion: This study aims to use the qualitative data collected as part of routine care experience surveys to their full potential, making this information easier to access and use by those involved in developing quality improvement initiatives. The study will include the development of a tool to facilitate more efficient and standardised analysis of care experience data on an ongoing basis, enhancing and accelerating the translation of patient experience data into quality improvement initiatives.

Do organizational leaders' tweets influence their employees' anxiety? And if so, have employees become more susceptible to their leader's social media communications during the COVID-19 pandemic? Based on emotional contagion and using machine learning algorithms to track anxiety and personality traits of 197 leaders and 958 followers across 79 organizations over 316 days, we find that during the pandemic leaders' tweets do influence follower state anxiety. In addition, followers of trait anxious leaders seem somewhat protected by sudden spikes in leader state anxiety, while followers of less trait anxious leaders are most affected by increased leader state anxiety. Multi-day lagged regressions showcase that this effect is stronger post-onset of the COVID-19 pandemic compared to the pre-pandemic crisis context.

Since early 2020 the COVID-19 pandemic disrupted societies worldwide. As we moved from expecting the closure of society to be a short-term one to experiencing it as a longer-term phenomenon, we lacked understanding about how the pandemic has affected the working lives and wellbeing of employees in different life and career stages. Drawing from lifespan development approaches and Job Demands-Resources (JD-R), we considered the effect this profound disruption had on stress, burnout, and job satisfaction across career stages over time. We took a multi-level approach to the analysis of three waves of data. Disruptions were a predictor of stress and negatively affected disengagement and job satisfaction over time. We found differences in the ways in which people in different career stages reacted to these disruptions and adjusted over time. Job autonomy positively influenced wellbeing over time, however perceived organizational support contributed to growth in burnout disengagement and exhaustion and lower job satisfaction over time. We discuss the implications of our findings for workplaces managing in the aftermath of external shocks going forward.