Digital Health, Wearables, Public Health & Global AI
Session Overview
Artificial intelligence is extending the reach of healthcare beyond the hospital and clinic into the home, the community, and the population. The proliferation of wearable sensors, smartphone-based health applications, connected medical devices, and digital therapeutic platforms is generating continuous streams of health-relevant data that AI systems are uniquely positioned to analyze and act upon. Simultaneously, AI is transforming public health and epidemiological practice — enabling real-time disease surveillance, population health modeling, and the design of interventions that can reach underserved communities at scale. This session examines AI across the full spectrum of digital and community health, from individual-level behavioral monitoring to global health equity and pandemic preparedness.
This session features a keynote lecture, four oral presentations, and a poster presentation segment spanning wearable technology, digital therapeutics, population health AI, and the application of computational methods to global and public health challenges.
Why This Session Matters Now
The boundary between clinical care and everyday life is dissolving. Consumer-grade wearable devices now capture physiological signals — cardiac rhythm, oxygen saturation, sleep architecture, physical activity, and continuous glucose levels — with sufficient fidelity to generate clinically actionable insights between healthcare encounters. AI systems capable of detecting atrial fibrillation, predicting hypoglycemic events, or identifying early signs of mental health deterioration from passively collected behavioral data are moving from research settings into population-scale deployment. In public health, the COVID-19 pandemic demonstrated both the potential and the limitations of AI-driven surveillance and modeling, catalyzing sustained investment in more robust and equitable digital public health infrastructure. For 2027, the defining challenge is translating the technical capability of digital health AI into systems that are clinically validated, equitably accessible, and trusted by the populations they serve.
Key Scientific & Technical Themes
Wearable Sensors, Continuous Monitoring & IoT in Healthcare
The convergence of miniaturized sensor technology, wireless connectivity, and edge AI inference is enabling continuous physiological monitoring that was previously possible only in intensive care settings. Wearable devices capturing electrocardiographic, photoplethysmographic, accelerometric, and biochemical signals are generating longitudinal health data streams that machine learning models can interrogate for early signals of disease onset, deterioration, or treatment response. The Internet of Medical Things is integrating these device streams with clinical information systems, creating the infrastructure for proactive and personalized care management. Smart medical devices embedded with AI inference capabilities are enabling autonomous monitoring and alert generation without dependence on cloud connectivity, which is critical for deployment in resource-constrained environments. This theme examines the signal processing methodologies, AI architectures, and clinical validation standards relevant to wearable and connected health monitoring.
Digital Phenotyping, Behavioral Analytics & Mental Health AI
Smartphones and wearable devices passively capture behavioral signals — mobility patterns, sleep-wake cycles, social interaction frequency, voice characteristics, and screen engagement — that encode meaningful information about psychological and cognitive states. Digital phenotyping applies machine learning to these passive data streams to generate quantitative indices of mental health, cognitive function, and behavioral change that can complement or, in some contexts, substitute for periodic clinical assessment. AI-driven mental health screening tools and digital therapeutics are demonstrating efficacy in depression, anxiety, and PTSD in randomized controlled evaluations, with the potential to extend mental health support to populations with limited access to specialist care. Behavioral analytics and AI in rehabilitation are enabling remote physiotherapy monitoring, exercise prescription adherence tracking, and functional recovery assessment outside clinical settings. This theme addresses the methodological, ethical, and clinical dimensions of passive behavioral monitoring and AI-driven mental health intervention.
AI in Epidemiology, Disease Surveillance & Pandemic Preparedness
AI is transforming the speed, sensitivity, and resolution of epidemiological surveillance — integrating traditional health system data with digital signals from social media, mobility data, environmental sensors, and genomic sequencing to detect and characterize disease threats in near real-time. Machine learning models for outbreak prediction, transmission dynamic estimation, and intervention effectiveness modeling are becoming essential tools in the public health response to both endemic and emerging infectious disease threats. Pandemic preparedness frameworks are incorporating AI-driven scenario modeling, supply chain optimization, and vaccine distribution planning to reduce response time and improve equity in future health emergencies. This theme examines the computational architectures, data integration frameworks, and validation methodologies for AI in epidemiological surveillance and pandemic preparedness.
Population Health Modeling, Health Economics & Global Health Equity
AI-driven population health modeling is enabling health systems and policymakers to identify high-risk subpopulations, predict healthcare utilization, and design targeted interventions that address the social determinants of health. Health economics and cost-effectiveness modeling — historically reliant on static decision trees and Markov models — are being enhanced by machine learning approaches capable of incorporating high-dimensional patient-level data and dynamic treatment pathways. Global health equity is a defining challenge for AI in healthcare: models trained on data from high-income health systems frequently underperform in low- and middle-income country settings, and the infrastructure required for AI deployment is unevenly distributed. This theme addresses the methodological, policy, and equity dimensions of AI in population health, including strategies for developing and validating AI tools that perform equitably across diverse global health contexts.
Telehealth, Remote Care Delivery & AI in Aging Populations
The acceleration of telehealth adoption has created new modalities for AI integration — from AI-assisted triage and symptom assessment in virtual consultation platforms to remote monitoring and care coordination for patients with complex chronic conditions. AI in the care of aging populations addresses the intersection of multiple chronic disease management, cognitive decline monitoring, fall prediction, and social isolation detection — challenges that are simultaneously clinical and social in nature. Remote physiotherapy, rehabilitation, and chronic disease management powered by AI-driven feedback and personalization are demonstrating the capacity to maintain clinical effectiveness while reducing the burden on patients and healthcare systems. This theme covers the clinical, technical, and implementation dimensions of AI in telehealth, remote care, and the management of aging and multimorbid populations.
Research Landscape & Data Trends
Digital health AI is one of the most heterogeneous and rapidly evolving sectors of the biomedical research landscape, spanning consumer technology, clinical informatics, public health, and health policy. The literature is characterized by rapid innovation in sensor technology and AI methodology alongside an increasing recognition of the gap between technical performance and real-world clinical utility. Regulatory frameworks for digital therapeutics and AI-based wellness devices are at varying stages of development across major markets, creating both opportunity and uncertainty for developers and researchers. The public health AI literature has expanded substantially following the pandemic, with sustained focus on surveillance systems, modeling methodology, and the infrastructure required for equitable global deployment. By 2027, passive monitoring for mental health, AI-driven chronic disease management, and global health equity in AI deployment are expected to represent the most active and consequential research frontiers.
Who Should Attend
- Public health researchers, epidemiologists, and health systems scientists working with population-level AI and surveillance systems
- Digital health developers and engineers building AI-powered wearable, mobile, and connected health applications
- Mental health researchers and clinicians evaluating digital phenotyping, AI screening tools, and digital therapeutics
- Cardiologists, endocrinologists, and chronic disease specialists using continuous monitoring and AI-driven management tools
- Rehabilitation specialists and physiotherapists working with AI-assisted remote therapy and functional assessment
- Health economists and health technology assessment professionals modeling the cost-effectiveness of digital health interventions
- Global health researchers and practitioners addressing AI equity, accessibility, and deployment in low-resource settings
- Geriatricians and specialists in aging medicine applying AI to multimorbidity management and elder care
- Telehealth platform developers and clinical informaticists designing AI-integrated virtual care pathways
Session Perspective
Digital health AI carries a dual promise and responsibility: the promise of extending high-quality health intelligence beyond the clinic to every individual, and the responsibility to ensure that this extension does not deepen existing health inequities or substitute technology for the human dimensions of care. This session is oriented toward the rigorous, evidence-based examination of digital health AI across the full spectrum from individual wearable monitoring to global population health systems. Researchers, clinicians, technologists, and policymakers who are navigating this complex and consequential frontier are invited to contribute their work to a program committed to both scientific excellence and equitable impact.
If your research aligns with this session, we invite you to submit an abstract for consideration.
