AI & Public Health Conference 2026

Workshop #1​

Workshop Title:  "AI as a determinant of population health"

Date: Tuesday 10 November 2026

Time: 11:00am - 12:30pm

​Facilitated by: Deakin University

Theme: Policy/Pratice 

Key Words: Infrastrucute requirements, Public health research needs.

Speaker(s): 

• Prof. Kathryn Backholer

• Prof. Craig Olsson

​​

Workshop Summary:

Artificial intelligence is rapidly becoming embedded in the social, commercial and informational environments that shape health. As AI changes how people learn, work, connect, access information and services, encounter commercial influence and make decisions, it may increasingly reshape established determinants of health and their distribution across populations. For adolescents in particular, AI assistants, companions and increasingly agentic systems may influence development, wellbeing and future opportunity in ways that generate both benefits and harms.
 
This interactive workshop will bring together researchers, public health practitioners and policymakers to ask: what research do we need now to understand AI as an emerging determinant of population health, inform policy and practice, and prepare for the potentially transformative effects of increasingly capable AI?
 
Participants will examine priorities across three areas: (i) measurement and surveillance, including how we track changing AI exposures, experiences and population impacts; (ii) methods and evidence, including longitudinal studies, experiments, living evidence synthesis and algorithmic auditing; and (iii) policy and governance research, including how we generate evidence that can inform, evaluate and improve regulatory and policy responses. The workshop will begin with a series of short, thought-provoking presentations to challenge current thinking about how AI may shape population health now and into the future. These will be followed by facilitated small-group discussions to identify priority research questions, evidence gaps and policy-relevant methods, before bringing participants together to develop a shared research agenda for public health preparedness and action.
 

Learning Outcomes:

1. An understanding of how AI may reshape key social, commercial and informational determinants of population health.

2. dentify priority population-health research questions and evidence gaps arising from increasingly capable and agentic AI systems.

3. Define policy-relevant research priorities and evidence needs to support public-health preparedness, governance and evaluation as AI evolves.

​

Target Audience:

​Researchers, practitioners, policy makers

​

​Pre- reading Material: TBC​

​​

​

Workshop #2​

Workshop Title: "Case Studies in Applied Public Health"

Date: Tuesday 10 November 2026

Time: 11:00am - 12:30pm

Theme: Policy/ Practice 

Speaker(s): 

• Laura Espinosa (European Centre for Disease Prevention and Control) 

• Ben Scalley (WA Health)

• Craig Dalton (HNE Health) 

​​

Workshop Summary:

Join three public health practitioners for a workshop demonstrating practical applications of data automation, machine learning and AI that can be adapted for use in public health agencies.

The workshop will combine demonstrations with hands-on activities, through six practical case studies, helping participants build confidence to test and adopt appropriate solutions in their own workplaces.

(1) Demonstration of a reproducible R-based automated pipeline and train-of-thoughts from inception to deployment to streamline the collection, validation, summarisation, visualisation and reporting of recurrent global threat data.

(2) Demonstration of an AI-assisted solution on evidence synthesis to support transparent and more efficient assessment of impact, likelihood and overall risk of public health threats.

(3) Demonstration of unsupervised machine learning to identify meaningful subgroups within a fictional outbreak allowing tailored responses to subgroups within the outbreak.

(4) Demonstration of retrieval-augmented generation approach to produce evidence-based answers with traceable references to public health questions will be demonstrated.

(5) Hands-on activity to test and refine prompts or reusable skill files for scientific writing using their own draft manuscripts.

(6) Hands-on activity on using large language models for generating a REDCap project manual from an XML file , OR (participants choice)

(7) Hands-on activity on using a simulated Lassa fever exposure avatar to assess and improve their interactions with real potential imported Lassa fever cases.

Throughout, presenters will emphasise choosing the simplest fit-for-purpose approach, evaluating performance, recognising limitations and adapting solutions to participants' own settings.

​

Each presenter will present two case studies from their own practice. Participants will receive additional information and advice on what to bring to the workshop to maximise their experience.

​

Learning Outcomes:

Compare data automation, unsupervised machine learning, retrieval-augmented generation and generative AI, and select a fit-for-purpose approach for a public health task.  

• Explain how reproducible tools can support data collection, validation, summarisation, mapping, visualisation and routine reporting.  

• Construct an unsupervised machine learning model and interpret clustering outputs to identify meaningful patterns and subgroups in public health data.  

• Consider approaches to producing AI-assisted outputs, source traceability, and practical limitations.  

• Adapt a prompt or reusable skill file to improve scientific writing and prototype a practical public health workflow or simulation.

​

Target Audience:

​Public health practitioners seeking to deepen their understanding of useful applications of data automation, machine learning and AI in public health practice. No technical skills are required to participate in this workshop.

​

​Pre- reading Material: TBC​

​​

​

Workshop #3 (Please note there are two workshops is this timeslot) ​​

Workshop A

Workshop Title:  -Episomer: hands-on social media surveillance for early detection of public health threats in a changing digital landscape

Date: Tuesday 10 November 2026

Time: 11:00am - 11:45am

​Facilitated by: Laura Espinosa, European Centre for Disease Prevention and Control​

Theme: Policy/ Practice 

Speaker(s): 

• ​Dr Laura Espinosa

• Dr Craig Dalton 

​​

Workshop Summary:

Social media platforms are a valuable source of signals for public health surveillance, enabling early detection of threats, often before official reports are available. However, dependency on a single platform creates a critical vulnerability: when data access is lost, so is surveillance capacity. This is what happened when Twitter/X restricted its API.

This hands-on workshop presents episomer, a new free, open-source R-based tool developed by ECDC in response to this challenge in 2026. Episomer currently monitors BlueSky and is designed to be extended to other social media platforms, making it resilient to future changes in data accessibility.

The workshop opens with an introduction covering the rationale for social media surveillance in public health surveillance, the epitweetr story, and the systematic review of data accessibility that informed the development of episomer. This is followed by an overview of episomer's architecture, key features and functionalities. The core of the session is a hands-on exercise in which participants explore episomer's dashboard, geolocation, and signal detection functionalities, supported by facilitators. The session closes with a plenary discussion in which participants share observations and potential use cases from their own institutions, followed by a wrap-up on next steps and future developments.

Participants will be able to use episomer after the workshop for their specific use cases since it is a free, open-source tool, and it only requires social media credentials added from the user for data collection.

No technical skills are required. Participants will receive installation instructions in advance of the workshop.

​

Learning Outcomes: 

• Understand the rationale for using social media data in public health surveillance and public health intelligence, and the challenges posed by changes in platform data accessibility.

• Describe the key features and architecture of episomer, including data collection, geolocation, signal detection and alert functionalities.

• Apply episomer's core functionalities to analyse social media data for public health surveillance.

• Assess the potential for integrating episomer into their own public health surveillance workflows and identify relevant use cases in their institutional context.

​

Target Audience:​​

Workshop Title: Researchers and public health practitioners with an interest in or experience of public health surveillance, public health intelligence, or the use of social media data for public health purposes. No technical skills are required to participate in this workshop.

​

Pre- reading Material: TBC

​​

Workshop B

Workshop Title: Vaccine safety and misinformation in social media: what AI-based monitoring can tell us 

Date: Tuesday 10 November 2026

Time: 11:45am - 12:30pm

​Facilitated by: Sedigh Khademi, Murdoch Children's Research Institute (Centre for Health Analytics)​

Theme: Research 

Speaker(s): 

• ​Dr Sedigh Khademi

• Dr Gerado Luis Dimaguila

• Dr Javed Muhammd

​​

Workshop Summary:

Social media carries large volumes of first-person accounts of vaccine experience alongside circulating misinformation. Both are relevant to public health, and both are difficult to interpret at scale. 

This interactive session presents VaxPulse, a social media monitoring platform for vaccine safety and misinformation developed at the Murdoch Children's Research Institute Centre for Health Analytics. Data is collected across multiple platforms and feeds two analysis arms. The first detects vaccine misinformation, including the boundary between misinformation, legitimate safety concern and vaccine hesitancy. The second detects potential adverse events following immunisation using large language models, through identification of personal health mentions, extraction of reported reactions, and normalisation to coded medical terms (SNOMED CT / MedDRA). 

Three interactive segments are planned. Participants first triage posts spanning clear falsehood, alarming but legitimate concern, and hesitancy, deciding which warrant action, monitoring or neither. Second, participants classify real posts and extract reported reactions, comparing their classifications with model outputs; disagreement between participants illustrates why inter-rater agreement matters before any model is assessed. Finally, the session closes with a clustered set of reports and the question of whether it constitutes a signal, alongside the governance constraints encountered in this work, including institutional ethics review, privacy impact assessment and platform terms restricting inference of health signals from user content. 

This aligns with the conference themes of Novel applications in public health and Privacy & confidentiality, and with Maximising Benefits, Minimising Harms through its focus on both the capabilities and limits of automated monitoring. 

​

Learning Outcomes:

By the end of this workshop, participants will be able to:   Describe how unstructured social media text is processed into structured vaccine safety data, from collection through to coded reaction terms.   Identify common failure modes of LLM-based extraction from user-generated text, including negation, third-party reports and ambiguous phrasing.   Distinguish vaccine misinformation from legitimate safety concern and vaccine hesitancy and explain why the boundary is difficult to operationalise.   Recognise the ethical, regulatory and platform compliance constraints that apply to social media data in public health surveillance. 

​

Target Audience:

Public health practitioners, immunisation and vaccine safety staff, epidemiologists, health communication and program staff, health data scientists and informaticians, and researchers working with unstructured or user-generated text or evaluating AI systems in public health. No technical background is assumed; participants who work with surveillance data or manage immunisation programs will find the interactive segments directly applicable.    

​

​Pre- reading Material: TBC

​​​

​​

Workshop #4​

Workshop Title: "Anticipating the threat impacts of AI on public health: a strategic red-teaming exercise for policymakers and health system leaders"

Date: Tuesday 10 November 2026

Time: 11:00am - 12:30pm

​Facilitated by: The Education Futures Foundation​

Theme: Policy/ Practice

Keywords: Novel applications in Public health 

Speaker(s): 

• Mr Darren Menachemson

​​

Workshop Summary:

The next decade will see exponential growth of AI’s capability, use cases and impact. 

Like other general-purpose technologies before it - from the world wide web to social media - AI will create profound opportunities and serious, unprecedented risks to the health of Australians. The ability to anticipate the downsides of AI and inoculate society and organisations from them is difficult but urgent.

This workshop will focus on how advancing AI capabilities might be used by bad actors with geopolitical, profit or influence motives to degrade public health infrastructures, programming and trust.

Participants will:

* Learn about likely future capabilities and harms that the rise of AI will bring to public health in Australia, as well as as important concepts like the pacing problem and the Collingridge Dilemma of Control

* Engage with realistic future scenarios that make medium-term AI-enabled public health threats tangible 

* Use strategic red teaming to step into the role of a bad actor and examine how public health systems could be disrupted at government, community, organisational and sectoral levels

* Use anticipatory governance patterns to design effective and pre-emptive regulatory and policy responses that anticipate these threats and engage with the fuzziness that comes with exponential technology disruption.

The workshop is aimed at those with strategic roles to play in governing and stewarding public health systems and institutions, as AI’s impact on Australia’s public health system dials up.

​

Learning Outcomes:

Understand the AI threat landscape for public health. Apply Anticipative Governance approaches to respond preemptively to AI's threat footprint in public health. Understand the role of strategic red teaming in AI-resilient governance design

​

Target Audience:

Those with strategic responsibility for governing and stewarding Australia's public health systems and institutions - leaders who need to be ahead of AI's impact, not catching up to it.

​

​Pre- reading Material: TBC