2.C. Skills building seminar: Advanced Integrated Epidemiological Modeling to Quantify Chronic Disease Burden and Inform Policy

Uloženo v:

Podrobná bibliografie
Vydáno v:	European Journal of Public Health vol. 35, no. Supplement_4 (Oct 2025)
Hlavní autor:	EUPHA Chronic Diseases section, EUPHA Public Health Economics section
Další autoři:	Chair persons: Saverio Stranges (EUPHA-CHR), Raffaele Palladino (Italy)
Vydáno:	Oxford University Press
Témata:	Health promotion Bias Epidemiology Chronic conditions Economic models Skills Resource allocation Medical records Machine learning Seminars Electronic medical records Economics Computer simulation Heterogeneity Intervention Forecasting Missing data Health planning Epidemic models Value Case studies Effectiveness Public health Estimation Addictions Biostatistics Decision making Health policy Chronic illnesses Health economics Disability Policy making Dynamic models Health care policy Electronic health records Neural networks Data science Disease Simulation Mathematical models Health care expenditures Research methodology Identification Uncertainty Medical screening People with disabilities Budgets Medical diagnosis Budget constraint Measurement Cost analysis Frame analysis Health education Capacity building approach Neurological disorders Health services Artificial intelligence Computerized medical records Social
On-line přístup:	Citation/Abstract Full Text - PDF
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Abstrakt:	Accurate and robust quantification of chronic disease burden is critical for effective health policy, strategic resource allocation, and cost-effective interventions. This skill-building seminar aims to enhance participants’ capacity to apply advanced, integrative modeling techniques to assess and forecast chronic disease burden using real-world health data. Organized by the EUPHA Chronic Disease and Public Health Economics sections, the seminar will review methodological tools combining epidemiology, biostatistics, AI, and health economics. Emphasis will be placed on scalable approaches that account for demographic and clinical heterogeneity, supporting their use across diverse health systems and epidemiological settings. The workshop includes four expert-led technical sessions: 1. Disease Identification and Profiling Using Linked Health Data - Use of algorithms and machine learning models to identify chronic conditions from routinely collected, multi-source healthcare data (e.g., electronic health records, claims, and registries), addressing underdiagnosis, misclassification bias, and missing data. 2. AI-Based Population-Level Disability Estimation and Trajectory Forecasting - Application of neural networks to estimate disability-adjusted metrics and simulate disease trajectories over time, incorporating uncertainty and dynamic covariates. 3. Quantitative Health Priority-Setting Frameworks - Tools such as Programme Budgeting and Marginal Analysis (PBMA), burden-of-disease metrics (e.g., DALYs), and equity-informed frameworks that support efficient, transparent decision-making by balancing disease burden, economic value, and fairness. 4. Health Economic Modeling for Policy Simulation - Cost-effectiveness analysis and dynamic modeling of public health interventions (e.g., screening programs, early detection strategies) to guide decisions under budget constraints. Applied examples will focus on neurological conditions and addictions-areas with substantial challenges in diagnosis, disability estimation, and long-term forecasting. Case studies will highlight profiling of neurological conditions with variable resource needs and evaluate screening strategies through simulated health-economic outcomes. Each session will integrate methodological depth with practical application. Participants will engage with adaptable modeling frameworks and interact with domain experts to examine data assumptions, methodological trade-offs, and potential biases. The seminar is designed for professionals with foundational knowledge in epidemiology, biostatistics, data science, or health economics who seek to deepen their skills in integrative modeling for chronic disease burden assessment and public health policy planning. Key messages • This seminar aims to build capacity in the use of advanced modeling tools to quantify and forecast chronic disease burden using integrated real-world health data. • Practical, expert-led sessions on disease identification, disability estimation, priority-setting, and policy simulation, with applied examples focusing on neurological conditions and addictions.
ISSN:	1101-1262 1464-360X
DOI:	10.1093/eurpub/ckaf161.085
Zdroj:	ABI/INFORM Global