Psychophysiological monitoring and closed-loop neuromodulation for precision health
Organizers:
- Asim H. Gazi, Harvard University, USA
- Rayan Bahrami, University of Maryland, College Park, USA
- Omer T. Inan, Georgia Tech, USA
- Jin-Oh Hahn, University of Maryland, College Park, USA
Abstract:
Neuromodulation technologies such as nerve and brain stimulation are promising non-pharmacological therapies for central and peripheral nervous system disorders. A key challenge with neuromodulation interventions is the variability in their therapeutic effects that are often person-specific and context-specific, differing from timepoint to timepoint due to psychophysiological state changes. To tackle this challenge, solutions are needed to better monitor psychophysiology to estimate state changes, dynamically model intervention effects for digital twin-informed decision making, and control neuromodulation delivery in closed-loop to optimize for precision support.
Invited Speakers:
- Jose del R. Millan, University of Texas at Austin, USA
- Mayuresh Kothare, Lehigh University, USA
- Theodoros Zanos, Feinstein Institutes for Medical Research, USA
- Asimina Kiourti, Ohio State University, USA
- Rayan Bahrami, University of Maryland, College Park, USA
- Asim H. Gazi, Harvard University, USA
Intelligent and timely health support outside the clinic
Organizers:
- Asim H. Gazi, Harvard University, USA
- Ziping Xu, Harvard University, USA
- Susan Murphy, Harvard University, USA
Abstract:
To treat and prevent chronic illnesses, traditional healthcare relies on synchronous clinical support that can only track the dynamics of 1% of daily life (e.g., 1 hour/week of psychotherapy). Yet, many of the challenges faced and changes required in behavior are most critical during the remaining 99% of daily life. Novel mobile health interventions to support individuals during daily life are promising, but interventions are often delivered without AI-driven personalization. Advances in ubiquitous sensing enable biobehavioral tracking during daily life to inform personalization, but principled approaches to process sensor data and infer actionable information are limited.
Invited Speakers:
- Edison Thomaz, University of Texas at Austin, USA
- Laura E. Barnes, University of Virginia, USA
- Varun Mishra, Northeastern University, USA
- Kelly W. Zhang, Imperial College London, UK
- Ziping Xu, UNC Charlotte, USA
- Asim H. Gazi, Harvard University, USA
Advances in fetal-maternal cardiovascular coupling: interdisciplinary approaches in monitoring and modelling
Organizers:
- Alessandra Galli, Eindhoven, University of Technology, Netherlands
- Ahsan H. Khandoker, Khalifa University, UAE
Fetal-maternal cardiovascular coupling represents a frontier in biomedical research, where the integration of physiological monitoring, signal processing, and clinical insight can lead to breakthroughs in maternal and fetal health. This coupling refers to the dynamic and bidirectional interactions between maternal and fetal cardiovascular systems, influenced by autonomic nervous system activity, respiration, endocrine factors, and developmental processes. Understanding these mechanisms has significant clinical implications, particularly for predicting and preventing complications such as fetal distress, intrauterine growth restriction, and preeclampsia.
Despite its promise, this field remains underrepresented in the biomedical engineering community due to the complexity of simultaneous monitoring and the lack of standardized tools for interpreting coupling phenomena. However, recent advances, including wearable sensors, multimodal physiological data integration, and personalized AI-driven modeling, make this an ideal time to bring focused attention to the topic within a translational context.
By gathering leading researchers from engineering, clinical medicine, and physiology, this session will showcase state-of-the-art research, highlight emerging diagnostic strategies, and foster interdisciplinary collaborations toward safer pregnancies and healthier birth outcomes.
Invited Speakers:
- Giulio Steyde, Politecnico di Milan, Italy
- Jacopo Pavan, University of Virginia, USA
- Anita Krishnan, Children’s National Medical Center, USA
- Namareq Widatalla, Khalifa University, UAE
- Lochana Mendis, University of Melbourne, Australia
- Irene Lensen, Eindhoven University of Technology, Netherlands
From code to clinic: accelerating the translation and adoption of pediatric AI
Organizers:
- Yun Wang, Emory University, USA
- Ruiying Liu, Emory University, USA
- Xuzhe Zhang, Columbia University, USA
Ruiying Liu, Emory University, USA
The pediatric AI gap represents one of healthcare’s most pressing inequities. While AI transforms adult medicine, only 17% of FDA-cleared AI/ML devices include pediatric labeling, with most lacking transparent validation for children. This affects every pediatric specialty—from congenital heart disease detection to epilepsy monitoring, from sickle cell genomics to cancer treatment optimization. Children’s unique developmental physiology demands purpose-built AI solutions, yet most algorithms train exclusively on adult data, risking both missed opportunities and potential harm. This special topic session assembles leading experts from hospital and academia who are pioneering pediatric AI applications across diverse clinical domains. From addressing EHR integration challenges to ensuring AI deployment in these populations, from leveraging real-world data for optimal outcomes to advancing computational modeling of developing brains, our speakers will share cutting-edge approaches that bridge the gap between AI’s promise and pediatric reality. Together, we’ll explore how to accelerate safe, effective AI adoption for every child.
Invited Speakers:
- Evan Orenstein, Children’s Healthcare of Atlanta/Emory University, USA
- Lakshmanan Krishnamurti, Children’s Healthcare of Atlanta/Emory University, USA
- Robert C.Gross, Children’s Healthcare of Atlanta/Emory University, USA
- Hao Huang, University of Pennsylvania/Children’s Hospital of Philadelphia, USA
- Geraldine Dawson, Duke University, USA
The success and future promise of AI in ophthalmology
Organizers:
- Minhaj Nur Alam, UNC Charlotte, USA
- Kaveri Thakoor, Columbia University, USA
- Yu Gan, Stevens Institute of Technology, USA
Abstract:
With the advent and proliferation of medical artificial intelligence (AI) in vision and eye care, numerous innovations are emerging with the potential for transformative impact. These innovations include developing foundational models for different downstream tasks, using federated learning for collaborative model training without sharing multi-site data, integrating multiple modalities (image, text, gaze, sensors etc.) for enhanced model training, and exploring the utility of generative AI in ophthalmic diagnostic applications. In this special session, world-renowned experts will cover the latest developments in the field of ophthalmic diagnostics.
Invited Speakers:
- Minhaj Alam, UNC Charlotte, USA
- Kaveri Thakoor, Columbia University, USA
- Homa Rashidisabet, University of Illinois at Chicago
- Xincheng Yao, University of Illinois at Chicago, USA
- Yu Gan, Stevens Institute of Technology, USA
Multimodal AI for personalized health management: opportunities and challenges
Organizers:
- Muhammad Salman Haleem, Queen Mary University of London, UK
- Giussepe Fico, Universidad Politecnica de Madrid, Spain
- Dimitrios Fotiadis, University of Ioannina, Greece
Abstract:
The integration of artificial intelligence (AI) into personalized holds the potential to revolutionize personalized health management. With the advent of modern technology, it is now possible to acquire real-time signals via wearables and wireless sensors which enable individuals to track their well-being, allowing them to adjust their daily routine based on their underline comorbidities and chronic conditions (e.g. diabetes, cancer etc.). Research is being conducted based on design and development of novel multimodal techniques which allow training the real-time signal variations based on underline comorbidities acquired through medical testing, electronic health records, imaging techniques etc. However, despite technological advancements, the design and development of multimodal AI encounters challenges such as information fusion, prediction explainability, practicalities in real-time implementation etc. In this special session, we will discuss these challenges, cutting-edge research, innovative applications, and successful case studies of multimodal AI design. From the insights provided by our expert speakers, participants will gain a comprehensive understanding of the role of multimodal AI in personalized health management and precision medicine.
Invited Speakers:
- Muhammad Salman Haleem, Queen Mary University of London, UK
- Liangxiu Han, Manchester Metropolitan University,
- Edward Sazonov, University of Alabama, USA
- Samantha Kleinberg, Stevens Institute of Technology, USA
- Sean Banerjee, Wright University, USA
- Giussepe Fico, Universidad Politecnica de Madrid, Spain
- Nina (Catharina) Van Oost, Measure, Model & Manage Bioresponses’ (M3-BIORES) Lab
Digital Biomarker Discovery Pipeline – Autonomic: integrating multimodal data into Autonomic Nervous System signal analysis
Organizers:
- Jessilyn Dunn, Duke University, USA
- Md Mobashir Hasan Shandhi, Arizona State University, USA
- Anita (Silver) Shlesinger, Duke University, USA
Abstract:
DBDP-Autonomic (DBDP-A) is a proposed extension of the Digital Biomarker Discovery Pipeline (DBDP) framework, aimed at fostering reproducible research on autonomic nervous system (ANS) signals collected via mobile or wearable technologies. This special session will emphasize current challenges in analyzing ANS signals from mobile or wearable devices, and opportunities for integrating context from multimodal data. A motivating question to prompt discussion is: Can we disambiguate physiological signals arising from different sources, such as psychological stress, physical activity, or chronic health conditions. to avoid misattribution in downstream analysis? The session will focus on identifying potential benchmark challenges (such as Kaggle competitions), open-source codebases, and shared datasets that could serve as testbeds for evaluating disambiguation strategies, ultimately working toward more transparent, personalized, and reproducible ANS signal research.
Invited Speakers:
- Douglas Bremner, Emory University, USA
- Matthew Goodwin, Northeastern University, USA
- Varun Mishra, Northeastern University, USA
- Nil Gurel, Reality Labs Meta, USA
- Jessilyn Dunn. Duke University, USA
- Mobashir H. Shandhil. Arizona State University, USA
LLM-Empowered Data and Knowledge Ecosystem for Healthcare
Organizers:
- Dr. Carl Yang, Emory University
- Dr. Beiyu Lin, University of Texas at Dallas
- Dr. Quan Wang, San Francisco State University
Carl Yang, Emory University, USA
Beiyu Lin, University of Texas at Dallas, USA
Quan Wang, San Francisco State University, USA
The rapid evolution of Large Language Models (LLMs) opens the door to a new era of data collection, storage, and utilization. By enabling the understanding, representation, and organization of rich healthcare data at scale, LLMs facilitate deeper knowledge extraction and more insightful pattern discovery. Realizing this potential requires a robust ecosystem—one that unifies structured and unstructured data through advanced database architectures, integrates domain-specific knowledge for rigorous evaluation and real-world deployment, and upholds regulatory compliance, privacy-preserving learning, explainability, and ethical AI practices across healthcare applications.
In this special session, we aim to present a vision and explore the emerging paradigm of an LLM-Empowered Data and Knowledge Ecosystem for Healthcare, highlighting architectures, frameworks, use cases, clinical practices, and the challenges of deploying LLMs across diverse healthcare domains. We welcome contributions spanning theoretical, technical, and applied perspectives—from foundational research on aligning LLMs with medical knowledge to practical implementations in clinical settings.
Invited Speakers:
- Dr. Sriraam Natarajan, University of Texas at Dallas
- Dr. Xiao Hu, Emory University
- Dr. Abeed Sarker, Emory University
- Dr. Xinyue Zhang, Kennesaw State University
- Dr. Yingzhou Lu, Stanford University