Information Technology in Healthcare Track

As healthcare systems grow increasingly complex, there is a critical need to leverage AI and systems engineering principles together to optimize healthcare delivery across various settings. This minitrack focuses on innovative approaches that combine AI-driven methods with healthcare systems to enhance patient care, clinician decision-making, and resource utilization. We seek papers that address the integration of AI with healthcare delivery, particularly in areas such as:

• Novel frameworks for AI-enhanced healthcare optimization in clinical setting
• Impact of Large Language Models (LLMs) on clinical workflow and documentation burden
• Data-driven approaches for personalized treatment planning and optimization
• Machine learning applications to improve emergency and acute care
• AI-enhanced healthcare resource allocation and scheduling
• Natural language processing to improve clinical documentation and triage accuracy
• Wearable biosensing and remote monitoring technologies for healthcare optimization
• Preventing bias in healthcare datasets and treatment algorithms 
• Methods to improve diversity in healthcare datasets and research 
• Systems engineering approaches to precision medicine and nutrition
• Systems engineering approaches to validating and monitoring Generative AI at scale 
• Implementation case studies of AI-driven solutions in healthcare settings 
• Integration of expert knowledge with AI systems in healthcare delivery
• The economics of AI adoption: ROI analysis for hospital systems

The minitrack particularly welcomes papers that demonstrate practical applications and real-world impact while advancing theoretical foundations. We encourage submissions that bridge the gap between AI capabilities and healthcare challenges, with emphasis on maintaining personalization, equity, and quality at scale.

Minitrack Co-Chairs:

Farzin Ahmadi (Primary Contact)
Towson University
fahmadi@towson.edu

Guruprasad Jambaulikar
Brigham and Women’s Hospital
gjambaulikar@bwh.harvard.edu

Clint Vaz
St Francis Medical Center
clint.vaz@fmlohs.org

Behavior change is an important component of improving health and well-being. Following medical guidelines for diet, exercise, medications, cessation of unhealthy habits, are examples of behavior change that can lead to better health. Persuasive systems design plays a critical role in driving meaningful behavior change at the individual, population, and health system levels. Leveraging advances in health informatics, such Behavior Change Support Systems can reinforce health promotion, patient education, disease prevention, and care decision‑making by delivering timely, personalized, and context‑aware interventions. When embedded within clinical and consumer digital ecosystems, persuasive technologies have great potential to transform how individuals engage with their health and how organizations deliver care.

This minitrack focuses on Design, Development, Implementation, and Evaluation of Health Behavior Change Support Systems (HBCSSs) that harness contemporary informatics technologies to influence health behaviors. These systems employ a range of evidence‑based strategies, such as adaptive feedback, intelligent nudging, education, motivation, and goal‑setting, delivered through intentional technological artifacts. Particular emphasis is placed on how persuasive theories and behavioral models can be operationalized using modern platforms, including mobile health applications, wearable and sensor‑based systems, electronic health record (EHR) -integrated tools, Virtual Reality/Augmented Reality, and AI‑driven decision support.

As digital health adoption accelerates, the relevance of HBCSSs to consumer‑centered health management continues to grow. Designing persuasive systems with consumers as end‑users, while ensuring usability, equity, transparency, and trust, is a critical research priority. Emerging approaches such as machine learning -driven personalization, digital phenotyping, real‑time analytics, and just‑in‑time adaptive interventions offer new opportunities to tailor behavior change strategies at scale. Example topics include persuasive technologies for self‑care and prevention, serious games and interactive tools for chronic disease management, participatory and co‑design methods involving patients and clinicians, and innovative evaluation frameworks that move beyond short‑term outcomes to sustained behavior change.

This minitrack showcases cutting‑edge, interdisciplinary research that addresses the sociotechnical challenges of deploying persuasive health technologies in real‑world settings. Contributions may examine system design and architecture, implementation within clinical or community infrastructures, or rigorous evaluation of behavioral, clinical, and population‑level impact illustrating how HBCSSs can improve health outcomes. The topics of interest include, but are not limited to:

• Design and development
  1. Create digital health interventions for behavior change using stakeholders’ perspectives (users and experts)
  2. HBCSS development that incorporates users early on in order to tailor systems with user profiles, characteristics or preferences
  3. Persuasive strategies for social support
  4. Design of mobile technologies for health and mobile approaches to HBCSSs
  5. Persuasive prompts to create engagement and involvement in serious game interventions
  6. Creation and testing of user profiles to identify which persuasive strategies matter most for whom
  7. Discussion or evaluation of design approaches for developing HBCSSs, including considerations for personalization, privacy and security
  8. Ethical perspectives on health behavior change support systems
  9. Utilization of behavior change techniques and persuasive technology for health conditions
  10. Augmented and Virtual Reality to promote health behavior change
• Implementation and evaluation
  1. Health behavior change through mobile technologies, teleconsultation and telemedicine
  2. Petient/consumer education, consumer empowerment, decision support tools for consumers, and remote monitoring
  3. Evaluation of persuasiveness of different types of HBCSSs, moving towards a checklist for practice
  4. Adequate design for measuring the effect of persuasive strategies on task adherence during usage and long-term effects
  5. Frameworks and methodologies to measure A/B/C-Changes (attitude change, behavior change, or an act of compliance)
  6. Profiling personalities and matching them with persuasive strategies
  7. Multimodal cues and measurement of the effects on adherence and outcomes
  8. Advanced analytics to predict adherence, and to identify usage patterns and the effects on adherence

Minitrack Co-Chairs:

Sriram Iyengar (Primary Contact)
University of Arizona
msiyengar@arizona.edu

Harri Oinas-Kukkonen
University of Oulu
Harri.Oinas-Kukkonen@oulu.fi

Elena Vlahu-Gjorgievska
University of Wollonging
elenavg@uow.edu.au

Khin Than Win
University of Wollongong
win@uow.edu.au

The integration of Artificial Intelligence (AI) into healthcare promises transformative improvements in diagnostics, treatment planning, and resource management. However, its ultimate value is not determined by algorithmic performance alone, but by how it is embedded within complex human workflows and collaborative decision-making processes. Current research often focuses on AI’s technical capabilities or its impact on individual users, leaving a critical gap in understanding the sociotechnical dynamics of AI as a participant in multi-actor, multi-context healthcare ecosystems.

This minitrack addresses this gap by shifting the focus from AI as a tool to AI as a collaborative agent within and across three critical levels of healthcare: clinical care, operational management, and community health. We seek to explore how AI recommendations are interpreted, negotiated, adapted, and acted upon by diverse stakeholders—including physicians, nurses, administrators, public health officials, community health workers, patients, and informal caregivers. The core challenge lies in designing and deploying AI systems that enable, rather than disrupt, the value of trust, communication, and shared responsibility that underpins effective care delivery and health system resilience.

This minitrack aims to foster interdisciplinary knowledge exchange that examines both the potential and the pitfalls of human-AI collaboration across these workflows. We invite both theoretical and empirical research that investigates the human-AI collaboration in healthcare through multiple levels or through multiple actors. Our goal is to generate actionable knowledge that can guide the design of more effective, equitable, and trustworthy AI systems for the future of AI in healthcare. Topics of Interest (including but not limited to):

• Theorizing Human-AI Collaboration: New models and frameworks for understanding trust, authority, and responsibility in AI-mediated clinical, operational, or community health decisions
• Workflow Integration & Adaptation: Empirical studies on how AI tools reshape clinical protocols, operational routines (e.g., scheduling, capacity planning), and community health outreach practices
• Inter-Professional Dynamics with AI: Investigations into how AI affects communication, coordination, and power dynamics among different professional groups (e.g., doctor-nurse-administrator collaborations)
• AI in Community and Public Health Workflows: Studies on the use of AI by community health workers, in health promotion campaigns, or in managing population health equity, focusing on accessibility and cultural relevance
• Decision-Making under AI Influence: Behavioral research on cognitive bias, automation complacency, and skill degradation in clinicians, administrators, or patients interacting with AI support
• Co-Design and Implementation Strategies: Design science research on participatory methods for developing AI tools with diverse stakeholder groups to ensure usability and adoption
• Ethical and Governance Challenges: Analyses of algorithmic fairness, accountability, and transparency in cross-workflow AI systems that impact patient care and resource allocation
• Measuring Impact and Outcomes: Novel methods for evaluating the success of human-AI collaboration not just by technical accuracy, but by improvements in team performance, patient outcomes, operational efficiency, and community health indicators
• Case Studies of Success and Failure: In-depth examinations of deployed AI systems, analyzing the factors that led to effective or problematic collaboration across organizational boundaries

This minitrack welcomes diverse methodological approaches, including qualitative studies, quantitative surveys, experimental designs, action research, and design science. We encourage submissions that bridge information systems, computer science, healthcare management, social psychology, and human-computer interaction to build a richer understanding of the future of collaborative intelligence in healthcare.

High quality and relevant papers from this minitrack will be selected for fast-tracked development towards Internet Research. Selected papers will need to expand in content and length in line with the requirements for standard research articles published in the journal. Although the minitrack co-chairs are committed to guiding the selected papers towards final publication, further reviews may be needed before a final publication decision can be made. Internet Research (IntR) is an international and refereed journal that is indexed and abstracted in major databases (e.g., SSCI, SCI, ABI/INFORM Global), with an impact factor 6.8 in 2025 JCR.

Minitrack Co-Chairs:

Jueni Lyu (Primary Contact)
Hong Kong Baptist University
joylyu@hkbu.edu.hk

Christy M.K. Cheung
Hong Kong Baptist University
ccheung@hkbu.edu.hk

Lu Zhang
Hong Kong Baptist University
ericluzhang@comp.hkbu.edu.hk

Aiping Lyu
Hong Kong Baptist University
aipinglu@hkbu.edu.hk

This minitrack explores the adoption, implementation, diffusion, use, and evaluation of healthcare technologies, with a particular focus on how these dynamics interact at multiple levels (individual, group, organizational, regional, national, and international) to influence outcomes for patients, professionals, and healthcare systems.

To sustain the minitrack’s strong community and continued relevance, we intentionally keep the scope broad and open to a wide range of healthcare-related IS research. In addition, the minitrack explicitly welcomes research on digital innovations for inclusive health and well-being, including patient- and consumer-facing technologies (e.g., mobile apps, wearables, online platforms and communities), as well as clinical and administrative information systems (e.g., EMRs, telemedicine, decision support, AI-enabled solutions). We particularly encourage work examining how design, implementation, governance, and context shape access, usability, trust, and outcomes for diverse and potentially vulnerable populations across the life course.

This minitrack is open to a variety of established methodologies including (but not limited to) case studies (business/IS oriented), surveys, experimental designs, workflow and other forms of business process modeling, interviews, content analysis, conceptual papers, and quantitative analyses. Submissions should reflect mature work (data collected and some analysis performed), though not necessarily in the final stage. Completed, high-quality research and studies that spark scholarly and/or practitioner conversations will receive special consideration. Topics include (but are not limited to):

• Application of adoption, implementation, diffusion, and evaluation theories to healthcare
  1. Unified Theory of Acceptance and Use of Technology (UTAUT)
  2. Technology Acceptance Model (TAM), social learning, and related behavioral theories
  3. Diffusion of Innovation (DOI) theory
  4. IS success/value models
  5. Theory of Planned Behavior (TPB)
  6. Organizing vision and organizational adoption models
  7. Information assurance (confidentiality, integrity, availability), privacy, cybersecurity, and trust
• Adoption at the individual, project, organizational, or system level
  1. Stakeholder analysis and multi-stakeholder adoption dynamics
  2. User characteristics (including differences across age groups and health status)
  3. Organizational/project structure, strategies, and change management
  4. Regional initiatives, global development, and cross-national comparisons
  5. Interaction among individual-, organizational-, project-, and system-level factors
  6. Role/impact of regulatory, reimbursement, and policy structures
  7. Adoption and continued use of digital health and well-being innovations (e.g., lifestyle apps, wearables, patient portals, online communities)
  8. Training and onboarding impacts on adoption and sustained use
• IT Implementation
  1. Effective implementation strategies for clinical, administrative, and consumer-facing systems
  2. EMRs/PHRs and interoperability initiatives
  3. Health IT project management and governance
  4. Participation of professionals and patients/consumers in e-health projects
  5. Influence of local context, workflow, and organizational culture
  6. Workflow analysis and redesign
  7. Serious gaming and gamified interventions in health
  8. Inclusive and participatory design/implementation approaches (including integrating vulnerable users in design and deployment)
• IT Use (including inclusive health and well-being contexts)
  1. Factors and models of continued use and routinization
  2. Human-computer interaction in healthcare and well-being contexts
  3. Usability, accessibility, and inclusive interaction design (e.g., for older adults, people with disabilities, underserved groups)
  4. Online platforms and virtual communities supporting health, well-being, and social connection (e.g., loneliness reduction)
  5. Trust/distrust, privacy, transparency, explainability, and user reliance
  6. Technostress and unintended consequences of health and well-being technologies
  7. Standards, process controls, and meaningful use
• IT Evaluation
  1. Evidence-based support of emerging healthcare technologies
  2. Measures/frameworks for evaluating healthcare and well-being technologies
  3. Levels of IT capabilities and digital maturity
  4. Health IS success factors and value realization
  5. Feasibility analysis; business modeling and business cases
  6. Evaluation of digital innovations aimed at improving health and well-being outcomes (clinical, psychological, social)
  7. Equity and inclusivity outcomes: how they are measured, achieved, and sustained

Minitrack Co-Chairs:

Karoly Bozan (Primary Contact)
Duquesne University
bozank@duq.edu

Manuel Schmidt-Kraepelin
Technical University of Munich
manuel.schmidt-kraepelin@tum.de

Heiko Gewald
Neu-Ulm University of Applied Sciences
heiko.gewald@hnu.de

Scott Thiebes
Tongji University
scott.thiebes@tongji.edu.cn

Artificial Intelligence, particularly deep learning architectures such as computer vision, large language model, has demonstrated significant potential in healthcare by assisting with disease diagnosis, treatment planning, and patient monitoring. However, training these models requires vast amounts of diverse, high-quality data. For example, AI-driven radiology applications require extensive labeled datasets of medical images, such as X-rays, MRIs, and CT scans, to develop accurate diagnostic models. Similarly, large language models in healthcare rely on vast amounts of structured and unstructured clinical notes, medical literature, and patient records to provide accurate recommendations and decision support. However, due to privacy regulations, institutional restrictions, and ethical concerns, acquiring such large and comprehensive datasets remains a major challenge, which limiting the ability to build robust AI models.

Synthetic data generation emerges as a powerful technique to bridge this data gap by creating realistic, privacy-preserving, and high-quality datasets. Advances in generative models, such as Generative Adversarial Networks (GANs) and diffusion models, enable the creation of synthetic medical images, speech, and textual data to supplement real-world datasets. The use of synthetic data in medical imaging has already shown promise. For instance, GANs can generate high-resolution synthetic MRI or CT scan images that closely mimic real scans, helping to train AI models while reducing reliance on sensitive patient data. Additionally, synthetic ECG and EEG data can be produced to aid in training models for cardiovascular and neurological disorder detection. Large-scale text-based medical datasets, which are crucial for training AI-powered clinical decision-support systems, can also be synthesized to protect patient confidentiality while maintaining the integrity of AI learning models. Beyond diagnostics, synthetic data is proving invaluable for AI models aimed at predictive analytics and personalized medicine. For example, synthetic patient records can be generated to train AI systems in forecasting disease progression, optimizing treatment plans, and improving hospital resource allocation.

As the field continues to evolve, novel techniques such as multimodal synthetic data generation—combining image, text, and speech synthesis—are enabling even more comprehensive AI model training. These methods allow AI to achieve a deeper understanding of patient data by integrating diverse inputs, leading to more accurate and holistic healthcare solutions. This minitrack invites research contributions exploring the development, evaluation, and application of synthetic data in healthcare AI, including but not limited to:

• Novel synthetic data generation techniques for medical images, text, and audio
• Applications of synthetic data in disease diagnosis, medical imaging, and patient monitoring
• Ethical considerations and regulatory compliance for synthetic healthcare data
• Comparative analysis of real vs. synthetic data performance in AI models 
• Case studies of synthetic data implementation in clinical practice

Minitrack Co-Chairs:

Siavash H. Khajavi (Primary Contact)
Aalto University
siavash.khajavi@aalto.fi

Zixuan Liu
Tulane University
zliu41@tulane.edu

Anu Vehkamäki
Aalto University
anu.vehkamaki@aalto.fi

Jan Holmström
Aalto University
jan.holmstrom@aalto.fi