F.1. Practice session: Public health research when artificial intelligence in the room: an interactive, hands-on workshop
Abstract
Context and Relevance: Generative AI-enabled research tools are rapidly being adopted across research environments, yet guidance on how to use them responsibly within population health and epidemiology remains limited. Many researchers are experimenting informally with AI for literature synthesis, data cleaning, analytic coding, and interpretation, but lack structured training on integrating these tools while preserving transparency, methodological rigour, and disciplinary standards. This workshop addresses the growing international demand to equip trainees and researchers with practical and discipline-anchored guidance for incorporating generative AI into public health research whilst preserving methodological integrity. The session will appeal to and benefit epidemiologists, public health researchers, trainees, and practitioners seeking applied skills for responsible, effective use of AI in real-world research settings.Aims and Learning
Objectives: The workshop aims to equip participants with practical skills and critical frameworks to integrate generative AI into population health research workflows. By the end of the session, participants will be able to: 1. Describe appropriate use-cases for generative AI-enabled research tools across stages of epidemiologic research. 2. Apply generative AI tools to support core analytic tasks (e.g., code development, variable specification, interpretation support). 3. Identify risks related to bias, reproducibility, privacy, and over-reliance on AI outputs. 4. Implement strategies to maintain methodological rigour and disciplinary standards when using AI-enabled research tools.
Workshop Format: This skills-building seminar combines short framing presentations with interactive exercises and group reflection. Participants will engage in guided tasks using generative AI for common epidemiologic activities, followed by facilitated discussion on validity, reproducibility, ethics, and transparency. The session concludes with a practical framework for integrating AI into research workflows and identifying context-appropriate applications in participants’ own settings. The structure prioritizes collaboration, peer learning, and critical debate to ensure active participation and relevance for an international public health audience.
Added Value: The added value lies in positioning AI not as a replacement for disciplinary methods, but as a structured “sparing-partner” embedded within established disciplinary-specific workflows. The workshop brings together applied examples, critical appraisal, and hands-on activities to support responsible adoption across diverse research settings and health systems.
Key messages: • Generative AI can strengthen population health research when embedded within rigorous epidemiologic workflows and used with clear safeguards.
• Interactive training is needed to help researchers adopt AI responsibly while maintaining transparency, validity, and disciplinary standards.
Speakers/Panellists: Arnaud Chiolero
Population Health Laboratory (#PopHealthLab), University of Fribourg, Fribourg, Switzerland
Viktor Von Wyl
University of Zurich, Zurich, Switzerland
Related
- Early insights into nurses' perceptions, opportunities, and concerns regarding Ambient artificial intelligence in nursing practice
- Harnessing Artificial Intelligence to Predict Dental Crowding in Modern Orthodontic Practice: A Comprehensive Review
- Artificial intelligence-assisted bronchoscopy for the diagnosis and treatment of pulmonary diseases: Advances and clinical practice
- Artificial Intelligence in suicide prevention: promise, peril, and clinical implications for clinical practice
- Artificial Intelligence and AI-Adjacent Digital Technologies in Nursing Practice Within Gastroenterology: A Scoping Review of Current Applications, Challenges, and Future Directions.
BibTeX
@article{universityofzurichswitzeralnd2026practice,
title = {{F.1. Practice session: Public health research when artificial intelligence in the room: an interactive, hands-on workshop}},
author = {University of Zürich (Switzeralnd), University of Fribourg (Switzeralnd), University of Toronto (Canada) and Gemma Postill},
journal = {The European Journal of Public Health},
year = {2026},
month = oct,
doi = {10.1093/eurpub/ckag169.026},
url = {https://doi.org/10.1093/eurpub/ckag169.026},
note = {CC BY-NC 4.0},
}
RIS
TY - JOUR
TI - F.1. Practice session: Public health research when artificial intelligence in the room: an interactive, hands-on workshop
AU - University of Zürich (Switzeralnd), University of Fribourg (Switzeralnd), University of Toronto (Canada)
AU - Gemma Postill
PY - 2026
DA - 2026/10/01
JO - The European Journal of Public Health
DO - 10.1093/eurpub/ckag169.026
UR - https://doi.org/10.1093/eurpub/ckag169.026
AB - Context and Relevance: Generative AI-enabled research tools are rapidly being adopted across research environments, yet guidance on how to use them responsibly within population health and epidemiology remains limited. Many researchers are experimenting informally with AI for literature synthesis, data cleaning, analytic coding, and interpretation, but lack structured training on integrating these tools while preserving transparency, methodological rigour, and disciplinary standards. This workshop addresses the growing international demand to equip trainees and researchers with practical and discipline-anchored guidance for incorporating generative AI into public health research whilst preserving methodological integrity. The session will appeal to and benefit epidemiologists, public health researchers, trainees, and practitioners seeking applied skills for responsible, effective use of AI in real-world research settings.Aims and Learning Objectives: The workshop aims to equip participants with practical skills and critical frameworks to integrate generative AI into population health research workflows. By the end of the session, participants will be able to: 1. Describe appropriate use-cases for generative AI-enabled research tools across stages of epidemiologic research. 2. Apply generative AI tools to support core analytic tasks (e.g., code development, variable specification, interpretation support). 3. Identify risks related to bias, reproducibility, privacy, and over-reliance on AI outputs. 4. Implement strategies to maintain methodological rigour and disciplinary standards when using AI-enabled research tools. Workshop Format: This skills-building seminar combines short framing presentations with interactive exercises and group reflection. Participants will engage in guided tasks using generative AI for common epidemiologic activities, followed by facilitated discussion on validity, reproducibility, ethics, and transparency. The session concludes with a practical framework for integrating AI into research workflows and identifying context-appropriate applications in participants’ own settings. The structure prioritizes collaboration, peer learning, and critical debate to ensure active participation and relevance for an international public health audience. Added Value: The added value lies in positioning AI not as a replacement for disciplinary methods, but as a structured “sparing-partner” embedded within established disciplinary-specific workflows. The workshop brings together applied examples, critical appraisal, and hands-on activities to support responsible adoption across diverse research settings and health systems. Key messages: • Generative AI can strengthen population health research when embedded within rigorous epidemiologic workflows and used with clear safeguards. • Interactive training is needed to help researchers adopt AI responsibly while maintaining transparency, validity, and disciplinary standards. Speakers/Panellists: Arnaud Chiolero Population Health Laboratory (#PopHealthLab), University of Fribourg, Fribourg, Switzerland Viktor Von Wyl University of Zurich, Zurich, Switzerland
SN - 1101-1262
SN - 1464-360X
ER -