There is increasing recognition of the role that artificial intelligence (AI) systems can play in managing health crises. One such approach, which allows for analysing the potential consequences of different policy interventions is agent-based social simulations (ABSS). Here, the actions and interactions of autonomous agents are modelled to generate virtual societies that can serve as a “testbed” for investigating and comparing different interventions and scenarios. This piece focuses on two key challenges of ABSS in collaborative policy interventions during the COVID-19 pandemic. These were defining valuable scenarios to simulate and the availability of appropriate data. This paper posits that drawing on the research on the “everyday” digital health perspective in designing ABSS before or during health crises, can overcome aspects of these challenges. The focus on digital health interventions reflects a rapid shift in the adoption of such technologies during and after the COVID-19 pandemic, and the new challenges this poses for policy makers. It is argued that by accounting for the everyday digital health in modelling, ABSS would be a more powerful tool in future health crisis management.

Ambulance travel time estimations play a pivotal role in ensuring timely and efficient emergency medical care by predicting the duration for an ambulance to reach a specific location. Overlooking factors such as local traffic situations, day of the week, hour of the day, or the weather may create a risk of inaccurately estimating the ambulance travel times, which might lead to delayed emergency response times, potentially impacting patient outcomes. In the current paper, we propose a novel framework for accurately estimating ambulance travel times using machine learning paradigms, employing real-world spatiotemporal ambulance data from the Skane region, Sweden. Our framework includes data preprocessing and feature engineering, with a focus on variables significantly correlated with travel time. First, through a comprehensive exploratory data analysis, we highlight the main characteristics, patterns, and underlying trends of the considered ambulance data set. Then, we present an extensive empirical analysis comparing the performance of different machine learning models across different ambulance travel trip scenarios and feature sets, revealing insights into the importance of each feature in improving the estimation accuracy. Our experiments indicate that the aforementioned factors play a significant role when estimating the travel time.

Mobile stroke units (MSUs), which are specialized ambulances equipped with a brain imaging device and staffed with trained healthcare personnel, have the potential to provide rapid on-site diagnosis and treatment for stroke patients. However, efficient access to prehospital stroke care requires optimizing the placement of MSUs. The MSU allocation problem has been previously solved using a traditional genetic algorithm that utilizes random starting solutions. The use of random starting solutions can, however, cause the algorithm to converge slowly. This can be especially problematic if the initial solutions are significantly far from the global optimum. To address this problem, we propose an enhanced genetic algorithm with clustering (EGAC), which is a time-efficient method to solve the MSU allocation problem by identifying the optimal locations of MSUs in a geographic region. By leveraging clustering, the EGAC provides diverse and comprehensive coverage, avoiding the pitfalls of starting with closely located and potentially less optimal solutions, thereby effectively steering and accelerating its convergence towards the optimal MSU placements. Our experimental results show that the EGAC significantly outperforms the traditional genetic algorithm, without cluster-based starting solutions, by achieving remarkably faster convergence toward the optimal solution for different number of MSUs to allocate. We validate the performance of the EGAC through qualitative and quantitative analyses.

Proper modeling of human behavior is crucial when developing agent-based models to investigate the effects of policies, such as the potential consequences of interventions during a pandemic. It is, however, unclear, how sophisticated behavior models need to be for being considered suitable to support policy making. The goal of this paper is to identify recommendations on how human behavior should be modeled in Agent-Based Social Simulation (ABSS) as well as to investigate to what extent these recommendations are actually followed by models explicitly developed for policy making. By analyzing the literature, we identify seven relevant aspects of human behavior for consideration in ABSS. Based on these aspects, we review how human behavior is modeled in ABSS of COVID-19 interventions, in order to investigate the capabilities and limitations of these models to provide policy advice. We focus on models that were published within six months of the start of the pandemic as this is when policy makers needed the support provided by ABSS the most. It was found that most models did not include the majority of the identified relevant aspects, in particular norm compliance, agent deliberation, and interventions’ affective effects on individuals. We argue that ABSS models need a higher level of descriptiveness than what is present in most of the studied early COVID-19 models to support policymaker decisions. 

Agent-based models have long been argued a useful toolto support policy analysis, variably targeting the assessment of policydesign, as well as establishing its performance. Challenging, however,remains appropriate empirical parameterization and validation of suchmodels. This paper contributes to the development of rigorous accountsof policy modelling primarily driven by policy documents in order to develop general conceptual model. Such models can then serve as a basis forearly validation by subject matter experts, but more importantly, informthe subsequent inquiry relevant for the parameterization of such models, while at the same time offering the opportunity to detect deviationsfrom regulated practice. Relying on the scenario of organ donation basedon the Swedish legislation, we explore the merits of such an approach,and sketch the individual steps from policy documents to conceptualmodel. Supporting the methodological process, this paper employs theInstitutional Grammar 2.0, which offers selected features supporting theproposed modelling approach.

Simulation has become, in many application areas, a sine qua non. Most recently, COVID-19 has underlined the importance of simulation studies and limitations in current practices and methods. We identify four goals of methodological work for addressing these limitations. The first is to provide better support for capturing, representing, and evaluating the context of simulation studies, including research questions, assumptions, requirements, and activities contributing to a simulation study. In addition, the composition of simulation models and other simulation studies' products must be supported beyond syntactical coherence, including aspects of semantics and purpose, enabling their effective reuse. A higher degree of automating simulation studies will contribute to more systematic, standardized simulation studies and their efficiency. Finally, it is essential to invest increased effort into effectively communicating results and the processes involved in simulation studies to enable their use in research and decision making. These goals are not pursued independently of each other, but they will benefit from and sometimes even rely on advances in other sub-fields. In this article, we explore the basis and interdependencies evident in current research and practice and delineate future research directions based on these considerations.

 The field of hybrid human-artificial intelligence (HHAI), although primarily driven by developments in AI, also requires fundamentally new approaches and solutions. Multidisciplinary in nature, it calls for collaboration across various research domains, such as AI, HCI, the cognitive and social sciences, philosophy and ethics, and complex systems, to name but a few. 

This book presents the proceedings of HHAI 2024, the 3rd International Conference on Hybrid Human-Artificial Intelligence, held from 10-14 June 2024 in Malmö, Sweden. The focus of HHAI 2024 was on artificially-intelligent systems that cooperate synergistically, proactively and purposefully with humans, amplifying rather than replacing human intelligence. A total of 62 submissions were received for the main track of the conference, of which 31 were accepted for presentation after a thorough double blind review process. These comprised 9 full papers, 5 blue sky papers, and 17 working papers, making the final acceptance rate for full papers 29%. Acceptance rate across all tracks of the main program was 50%. This book contains all submissions accepted for the main track, as well as the proposals for the Doctoral Consortium and extended abstracts from the Posters and Demos track. Topics covered include human-AI interaction and collaboration; learning, reasoning and planning with humans and machines in the loop; fair, ethical, responsible, and trustworthy AI; societal awareness of AI; and the role of design and compositionality of AI systems in interpretable/collaborative AI, among others. 

Providing a current overview of research and development, the book will be of interest to all those working in the field and facilitate the ongoing exchange and development of ideas across a range of disciplines.

This paper explores the topic of model credibility of Agent-based Models and how they should be evaluated prior to application in policy-making. Specifically, this involves analyzing bordering literature from different fields to: (1) establish a definition of model credibility -- a measure of confidence in the model's inferential capability -- and to (2) assess how model credibility can be strengthened through Verification, Validation, and Accreditation (VV&A) prior to application, as well as through post-application evaluation. Several studies have highlighted severe shortcomings in how V&V of Agent-based Models is performed and documented, and few public administrations have an established process for model accreditation. To address the first issue, we examine the literature on model V&V and, based on this review, introduce and outline the usage of a V&V plan. To address the second issue, we take inspiration from a practical use case of model accreditation applied by a government institution to propose a framework for the accreditation of ABMs for policy-making. The paper concludes with a discussion of the risks associated with improper assessments of model credibility. 

Understanding the potential impact of policy changes before implementation is vital, and can be achieved through modelling and simulation. To adequately model stakeholders and regulative constraints, we propose the use of Institutional Grammar to facilitate institutional modelling in Agent-based Social Simulations. We present an early-stage case study exploring the Swedish organ donation system.

Social phenomena emerge from agent-environment interactions, rendering many statistical models unsuit-able. Agent-based Models (ABMs) offer a viable alternative for exploring policy implications. While recentcrises like the COVID-19 pandemic may have increased ABM awareness, their use in policy-making hasa long history. To better understand the potential challenges and opportunities of using ABMs to informpolicy-making, we conducted a systematic literature review and identified 34 articles describing the use ofABMs involving policymakers. This review revealed that ABMs have been implemented to support pol-icymakers across a range of policy areas, but also identified low levels of model traceability and formalcommunication. Moreover, the review showed that the model’s purpose and type tend to influence howvalidation is performed. The review concludes that models that have undergone little validation and lackproper documentation, while being informally communicated, may hinder policymakers from effectivelymotivating their decision-making.