Call for Papers: Special Issue on Artificial Intelligence for Population Data Science
The International Journal of Population Data Science (IJPDS) is pleased to invite submissions for a special issue on the theme of "Artificial Intelligence for Population Data Science."
Artificial intelligence (AI) is opening new possibilities for understanding and improving population-level systems across a wide range of domains—including healthcare services, education, social care, justice, labour markets, housing, and the environment.
While several countries have developed secure infrastructures for accessing and linking administrative, environmental, and statistical data, the availability and quality of large-scale, linked, and multimodal population datasets remain uneven. Many jurisdictions still face technical, legal, and governance barriers that limit interoperability, data sharing, and equitable access. These constraints highlight both the challenges and opportunities for applying machine learning and generative AI to complex, real-world population data: AI can help uncover patterns, forecast trends, and evaluate policies even where data are fragmented or infrastructures are still evolving. At the same time, deploying AI at population scale demands rigorous attention to fairness, transparency, interpretability, privacy, community participation, and responsible stewardship.
This special issue invites contributions that advance methodological innovation, trustworthy data governance, and high-impact applications of AI across all domains of population data science.
Scope and Themes
We welcome original research articles, review articles, methodological developments, application and case studies, and data/methodology notes that explore the use of AI as a method and/or tool across the following broad areas:
- AI Methodologies for Population-Level Inference and Forecasting
Methodologically rigorous work on scalable AI techniques tailored to population-level datasets across sectors.
Sub-topics:
- Causal and predictive AI for population systems (e.g., health outcomes, educational attainment, labour market transitions, environmental exposure risk).
- Generative AI and machine learning models, including hybrid mechanistic–AI models combining simulation, econometrics, system dynamics, or epidemiological models.
- Spatial–temporal and network models for analysing flows, mobility, neighbourhood effects, or social/systemic interactions at population scale.
- Generalizability and transfer learning across regions, sectors, and demographic groups, including robustness and fairness considerations.
- Scalable, reproducible AI pipelines using distributed analytics, cloud platforms, and transparent workflow management for population datasets.
- Population-Level Linkage, Multimodality, and Synthetic Data
Advances in datasets, data engineering, and stewardship practices that enable responsible population-level AI.
Sub-topics:
- AI-driven synthetic population data (e.g., synthetic registries, synthetic longitudinal trajectories, privacy protection and analytic utility evaluation).
- Multimodal data integration, including administrative records, clinical and primary care data, environmental exposures, remote sensing, geospatial layers, and economic indicators.
- AI-assisted record linkage and harmonisation, including error handling and quality assessment.
- Data governance and stewardship models (e.g., data trusts, federated access, secure research environments) supporting responsible AI use.
- Metadata, provenance, and data lifecycle management for transparent, trustworthy AI development using population datasets.
- Fairness, Transparency, Interpretability, Privacy, and Ethics in Population-Level AI
Responsible and accountable use of AI across public-sector and societal systems.
Sub-topics:
- Bias detection and mitigation in AI models using, but not limited to, administrative, clinical, educational, environmental, or justice datasets.
- Fairness-aware design and assessment standards for population-scale AI, including documentation tools and reporting frameworks.
- Explainable and interpretable AI supporting decision-making at population-level in areas such as healthcare, education, labour, justice, housing, or environmental planning.
- Privacy-preserving AI techniques (differential privacy, federated learning, secure computation) for population data analytics.
- Ethical and regulatory frameworks ensuring accountability, data justice, community participation, and rights-preserving AI deployment.
- AI Applications in Population-Level Systems
Domain-agnostic application studies that demonstrate the value of AI for societal insight or public service improvement.
Sub-topics:
- Healthcare and public health analytics using primary care, administrative, claims, or surveillance data for system-level insight.
- Education and life-course modelling (e.g., progression prediction, resource planning, early-warning indicators).
- Labour market and economic systems forecasting employment dynamics, sectoral transitions, or workforce shortages.
- Justice, social care, and public safety applications that prioritise fairness, transparency, and accountability in population-level decision contexts.
- Environmental and urban systems including climate risk modelling, exposure mapping, housing needs assessment, and mobility analytics.
- AI for Policy Evaluation and Public-Sector Decision-Support
Impact of AI in policy design, monitoring, and evaluation across population-level domains.
Sub-topics:
- Causal AI and counterfactual modelling for evaluating population-level interventions and public programmes.
- Generative scenario modelling to explore alternative policy actions and long-term population outcomes.
- Uncertainty modelling and decision-support tools for policymakers across sectors.
- AI-supported monitoring of equity and distributional impacts of public policies.
- Cross-agency and cross-sector AI systems that integrate multiple administrative data sources for public service improvement.
Submission Information
We will accept the following manuscript types:
- Original research articles
- Review articles
- Methodological development articles
- Application and case studies
- Data or methodology notes
Important Note: Submissions should explicitly demonstrate the role of AI as the central method or tool, and engage with issues of fairness, transparency, interpretability, privacy, and ethics wherever relevant. All submissions must include a data provenance statement, and where applicable, details of bias and fairness audits, privacy safeguards, and reproducibility resources (e.g., code, synthetic data).
Submission Deadline:
- 30th September 2026
- To Submit Your Manuscript, Click Here
Editorial Panel
Dr Marcos E. Barreto (Lead Editor), London School of Economics and Political Science, United Kingdom
Marcos is an Associate Professor in Artificial Intelligence, Deep Learning, Databases, and Big Data in the Department of Statistics at LSE. He holds a PhD in Computer Science (emphasis on high-performance computing) from Federal University of Rio Grande do Sul (2010, UFRGS, Brazil) and a postgraduate certificate in Health Data Science (2018, UCL Institute of Health Informatics, UK), where he was also a postdoctoral fellow funded by The Royal Society (2016-2018). His research concentrates mostly on data linkage tools and computational analytical models applied to massive databases. He led the design of AtyImo and contributed to CIDACS-RL, two mixed (deterministic and probabilistic) data linkage tools used for the design of the 100 Million Brazilian Cohort and other population-based cohorts at CIDACS (Salvador, Brazil), where he is also an associate researcher.
Website: https://marcosebarreto.github.io/
LinkedIn: www.linkedin.com/in/marcosennesbarreto
University Profile: https://www.lse.ac.uk/people/marcos-barreto
Yang Lu, Loughborough University, United Kingdom
Yang Lu is a Senior Lecturer in Computer Science at Loughborough University. Her research focuses on trustworthy data governance, privacy, and artificial intelligence, with expertise in privacy-preserving data integration and record linkage, semantic governance frameworks, synthetic data governance, and trust, identity, and privacy in distributed systems. Dr. Lu also works on ethical AI and human-in-the-loop approaches to support transparent, policy-aligned use of population-scale health and administrative data. Her work combines technical innovation with policy insight, and she collaborates with partners including the Alan Turing Institute, Energy Systems Catapult, and the UK Department for Science, Innovation and Technology.
LinkedIn: https://www.linkedin.com/in/yang-lu-684156a7/
University Profile: https://www.lboro.ac.uk/departments/compsci/staff/yang-lu/
Professor Abraham D. Flaxman, University of Washington, USA
Abraham Flaxman, PhD, is a Professor of Health Metrics Sciences at the Institute for Health Metrics and Evaluation (IHME) at the University of Washington. He is currently leading the development of a simulation platform to derive “what-if” results from Global Burden of Disease estimates and is engaged in methodological and operational research on verbal autopsy. Dr. Flaxman has previously designed software tools such as DisMod-MR that IHME uses to estimate the Global Burden of Disease, and the Bednet Stock-and-Flow Model, which has produced estimates of insecticide-treated net coverage in sub-Saharan Africa.
Webpage: https://healthyalgorithms.com/
Bluesky: https://bsky.app/profile/healthyalgo.bsky.social
Professor Spiros Denaxas, University College London, United Kingdom; Interdisciplinary Transformation University, Austria; National & Kapodistrian University of Athens, Greece
Spiros is Professor of Biomedical Informatics based at the University College London Institute of Health Informatics, Professor of Computational Medicine at the Interdisciplinary Transformation University (IT:U) in Austria, and Associate Director at the British Heart Foundation Data Science Centre leading the Defining Disease work area. His research (http://denaxaslab.org) focuses on creating and evaluating algorithms for phenotyping, risk prediction, data modelling, and disease subtype discovery in structured electronic health records, clinical and omics data.
Dr Adolphus Wagala, Harvard T.H. Chan School of Public Health and the Dana-Farber Cancer Institute, USA
Adolphus Wagala is a statistician and data scientist currently serving as a Research Fellow in the Department of Data Science at the Dana-Farber Cancer Institute and the Department of Biostatistics at the Harvard T.H. Chan School of Public Health in Boston, Massachusetts . He holds a Ph.D. in Probability and Statistics and has a strong academic and research background in statistical modeling, data analysis, and computational biology.
Before his current role, Dr. Wagala was a senior lecturer in the Department of Mathematics and Computer Science at Bomet University College in Kenya. His research has spanned various domains, including financial time series modeling, exchange rate volatility, and macroeconomic forecasting, with a particular focus on the Kenyan economy. Notable publications include studies on forecasting crude oil prices, modeling exchange rate volatility, and analyzing the relationship between GDP and wage growth in Kenya. Dr. Wagala has also contributed to methodological advancements in statistics, such as developing a likelihood ratio test for correlated paired multivariate samples and proposing classification algorithms for microarray data analysis.
In his current position, Dr. Wagala continues to apply his expertise in statistical modeling and data science to public health research, contributing to advancements in biostatistics and computational biology.
Professor Honghan Wu, University of Glasgow, United Kingdom
Honghan Wu is a Professor of Health Informatics and AI, based in the School of Health and Wellbeing of the University of Glasgow, where he leads the research theme of data science and AI. Prof Wu is a co-director of Health Data Research Scotland. He also is an honorary professor at Hong Kong University, an honorary associate professor at Institute of Health Informatics, UCL, and a former Turing Fellow of The Alan Turing Institute, UK's national institute for data science and artificial intelligence. Prof Wu holds a PhD in Computing Science. His current research focuses on machine learning, natural language processing, knowledge graph and their applications in medicine.
X: @hhwu
LinkedIn: linkedin.com/in/honghan-wu
Professor Mark J. Taylor, Melbourne Law School, Australia
Associate Professor, Health Law and Regulation; Deputy Director, HeLEX@Melbourne, Melbourne Law School. Author of Genetic Data and the Law (CUP,2012) Mark’s research interests include the regulation of personal information with particular emphasis upon health data governance. Immediate past Chair of the Confidentiality Advisory Group (England and Wales), he has served as policy advisor to the Health Research Authority (England) and as a member of the drafting group for the OECD Recommendation on Health Data Governance. He is a member of the Ethics Advisory Group for Genomics England and an advisor to the Data Protection (GDPR) and International Health Data Sharing Forum (GA4GH).
X: @DrMJTaylor
LinkedIn: https://www.linkedin.com/in/mark-taylor-94a1579
Professor Peter Christen, Australian National University, Australia
Peter Christen is a Professor in the School of Computing at the Australian National University (ANU) in Canberra. He graduated with a PhD in Computer Science from the University of Basel, Switzerland, in 1999. His research interests are in record linkage and data mining, with a focus on privacy and machine learning aspects of record linkage. He has published over 200 articles in these areas, including the two books "Data Matching" in 2012 and "Linking Sensitive Data" (co-authored with Thilina Ranbaduge and Rainer Schnell) in 2020.
Webpage: http://users.cecs.anu.edu.au/~christen/
Professor Laura C. Rosella, University of Toronto, Canada
Dr. Laura C. Rosella is a Full Professor at the Dalla Lana School of Public Health, University of Toronto, and holds a Tier 1 Canada Research Chair in Population Health Transformation & Analytics. She founded the Population Health Analytics Laboratory, pioneering data-driven approaches to improve population health, and leads the national AI for Public Health Research Training Platform (AI4PH). The author of more than 310 peer-reviewed publications, she also serves as Editor-in-Chief of the Canadian Journal of Public Health. Dr. Rosella’s contributions have been recognized with numerous honours, including Canada’s Top 40 Under 40, election to the Royal Society of Canada’s College of New Scholars, the CIHR-IPPH Mid-Career Trailblazer Award, and induction as a Fellow of the Canadian Academy of Health Sciences in 2025.
Professor Mark Elliot, University of Manchester, United Kingdom
Mark Elliot has worked at the University of Manchester since 1996, where he currently holds a chair in data science. His research is focused on the topics of data privacy and anonymisation. He founded the international recognised Confidentiality and Privacy Research Group (CAPRI) in 2002, and has run numerous research projects within the CAPRI remit. He leads the UK Anonymisation Network and is one of the key international researchers in the field of Statistical Disclosure and has an extensive portfolio of research grants and publications in the field.
Professor Elliot has extensive experience in collaboration with non-academic partners, particularly with national statistical agencies (e.g. Office for National Statistics, US Bureau of the Census, Australian Bureau of Statistics, Statistics Singapore) where he has been a key influence on disclosure control methodology used in censuses and surveys and where the SUDA software, he developed in collaboration with colleagues in Computer Science at Manchester, is currently employed.
Aside from Privacy his research interests also include AI and Society and substantive social science topics under the broad heading of Psychological Sociology (including studies of fathering, personal relationships and social and political attitudes).
Professor Bruno Arpino, University of Padua, Italy
Bruno Arpino is Full Professor of Social Statistics in the Department of Statistical Sciences at the University of Padua, Italy. His research combines methodological work on causal inference and the application of machine learning techniques in the social sciences with substantive work in social gerontology and social demography. He is particularly interested in intergenerational and family relationships, and in how these shape the health, wellbeing and digital engagement of older adults. He is Principal Investigator of the project “Social relations, digital technologies and wellbeing of older people” (SOCIAL), funded by the Italian Ministry of University and Research through the Italian Fund for Science (FIS2). He is also a co-founder of the “Sustainable Ageing” Working Group of the European Association for Population Studies and an Associate Editor of the European Journal of Population.
Personal website: https://sites.google.com/site/brunoarpino/
Dr Robespierre Dantas da Rocha Pita, Federal University of Bahia, Brazil
Holds a PhD and master's degree in computer science from the Federal University of Bahia (UFBA), a specialization in Computer Networks, and a bachelor's degree in information systems from the University of Salvador (UNIFACS). He is an Adjunct Professor in the Department of Computer Science at the Institute of Computing, UFBA, and a member of the Formalisms and Semantic Applications (FORMAS) research group. His research focuses primarily on big data analytics, data science, and computing applied to healthcare.