Conference Themes
Three programme-led tracks connecting exposure science, infectious-disease AI, and trustworthy medical data use.
The 22 September programme brings three complementary tracks into a single conversation: how exposures become disease evidence, how infectious-disease AI performs beyond the laboratory, and how complex health data can be used responsibly. The themes below reflect the confirmed keynote and invited-talk programme.
Track A
Bridging Classical Toxicology and Exposomics
Linking environmental exposures to disease through toxicological validation, spatial exposomics, and genomic evidence.
The programme follows exposure evidence from mechanism to population impact. Talks examine closed-loop toxicological validation, pesticide mixtures and environmental inequities, and the genomic landscape of exposure-associated disease.
Key Discussion Topics
- Closed-loop toxicological validation in exposomics
- Spatial exposomics of pesticide mixtures and cancer risk
- Environmental inequities in population-level exposure
- Endocrine disruptors and early-onset hepatocellular carcinoma
Programme Emphasis
- Toxicological and mechanistic validation
- Spatial exposure and mixture analysis
- Population-scale risk assessment
- Genomic profiling of exposure-associated disease
Programme Speakers
Qian Liu · Guibin Jiang · Jorge Honles · Stéphane Bertani · Pascal Pineau
Track B
Respiratory Epidemic AI
Strengthening infectious-disease intelligence with One Health evidence, representative training data, and trusted analytical environments.
This track connects emerging viral threats at the animal–human interface with the practical conditions required for dependable AI. The programme addresses influenza, coronaviruses and arboviruses, trusted research environments, and the impact of training data on real-world infectious-disease classification.
Key Discussion Topics
- Emerging viral diseases at the animal–human interface
- Influenza, coronaviruses, and arboviruses
- Training-data quality and real-world AI performance
- Trusted research environments for public health and medical AI
Programme Emphasis
- One Health epidemic intelligence
- Representative dataset design and curation
- Real-world model validation
- Secure, collaborative health-data analysis
Programme Speakers
Hui-Ling YEN · Chitin Hon · Etienne Charlier · Nicolas Berthet · Liang Wenhua
Track C
Public Health Data Governance / Trusted Research Environment
Turning complex health data into responsible medical AI, clinically relevant evidence, and trustworthy collaboration.
The programme brings governance into direct conversation with medical innovation. It covers AI-enabled medical development, big-data investigation of biomarkers in urological tumours, and a wider perspective on how AI is reshaping health research and care.
Key Discussion Topics
- Artificial intelligence in medical development
- Big-data analysis of biomarkers in urological tumours
- Responsible translation of AI into health research and care
- Governance and trusted access for data-intensive research
Programme Emphasis
- Big-data biomarker investigation
- Clinical and translational AI
- Governance-by-design for sensitive health data
- Trusted cross-institutional research workflows
Programme Speakers
Zhang Wenhong · Zhong Weide · Lu Jianming · Yuxing Han
How the Three Tracks Connect
The tracks converge around a shared question: what makes health evidence useful in the real world? Track A establishes credible links between exposure and disease. Track B tests how infectious-disease intelligence and AI depend on sound data and secure analysis. Track C extends these principles into medical innovation, biomarker research, and trustworthy collaboration. The roundtable then brings all three perspectives together to identify priorities for future research and international partnership.