Conference Program
Program at a Glance
All times are in US Eastern time. Click any session below to jump to its details. A printable PDF is also available.
Tuesday, August 4
-
8:00 AM–8:45 AMBreakfastForbes Room
-
8:45 AM–9:00 AMOpening RemarksSchenley Ballroom
-
9:00 AM–10:00 AMKeynote: Bin He Schenley Ballroom
-
10:00 AM–10:45 AMACM Health Session Schenley Ballroom
-
10:45 AM–11:00 AMCoffee Break
-
11:00 AM–12:15 PMConference Session I Schenley Ballroom
-
12:15 PM–1:30 PMLunchForbes Room
-
1:30 PM–2:30 PMKeynote: Guoliang Xing Schenley Ballroom
-
2:30 PM–2:45 PMCoffee Break
-
2:45 PM–4:00 PMClinical Panel Schenley Ballroom
-
4:00 PM–5:15 PMConference Session II Schenley Ballroom
-
5:15 PM–6:15 PMShort Paper Session I Schenley BallroomACM Health Editor Board Meeting Oakland RoomDemo / Poster Session Carnegie Room
Wednesday, August 5
-
8:00 AM–9:00 AMBreakfastForbes Room
-
9:00 AM–10:00 AMKeynote: Goli Yamini Schenley Ballroom
-
10:00 AM–12:00 PMNSF-NIH Smart and Connected Health Aspiring PI Panel Breakout Sessions Schenley Ballroom
-
12:00 PM–12:15 PMClosing Remarks of NSF-NIH SCH Aspiring PI WorkshopSchenley Ballroom
-
12:15 PM–1:30 PMLunchForbes Room
-
1:30 PM–2:45 PMConference Session III Schenley Ballroom
-
2:45 PM–4:00 PMIndustry Panel Schenley Ballroom
-
4:00 PM–4:15 PMCoffee Break
-
4:15 PM–5:15 PMShort Paper Session II Schenley Ballroom
-
5:15 PM–6:15 PMShort Paper Session III Schenley Ballroom
-
6:15 PM–8:00 PM
Thursday, August 6
-
8:00 AM–8:30 AMBreakfastForbes Room
-
8:30 AM–9:45 AMConference Session IV Schenley BallroomWorkshop: HARMONY (9:00 AM – 5:30 PM) Carnegie Room 1
-
9:45 AM–10:45 AMShort Paper Session IV Schenley BallroomElsevier SMHL Board Meeting Oakland Room
-
10:45 AM–11:00 AMCoffee Break
-
11:00 AM–12:00 PMShort Paper Session V Schenley Ballroom
-
12:00 PM–2:00 PMLunchForbes Room
-
2:00 PM–5:30 PMWorkshop: Generative AI (2:00 – 5:30 PM) Schenley Ballroom 1Workshop: AI-Powered Resilient Mobile Health (2:10 – 4:40 PM) Schenley Ballroom 2Workshop: Smart & Connected Health (2:00 – 5:05 PM) Oakland RoomWorkshop: AI Systems (2:30 – 4:20 PM) Schenley Ballroom 3Workshop: mHealth Security (2:30 – 5:00 PM) Carnegie Room 2
-
5:30 PM–5:45 PMClosing RemarksSchenley Ballroom
- Schenley Ballroom
- Forbes Room
- Oakland Room
- Carnegie Room
Technical Program
Full paper titles and authors for each session, with the session date, time, and room.
Regular Papers
Session 1: Large Language Models Multi-Agent Systems and Clinical NLP
-
Longitudinal Behavioral Change Coaching with Multi LLM Agents: Multi-Scale Summaries and Automated Dialogue Steering
-
TrialSim-10k: A Logic-Anchored Interactive Benchmark for Evaluating the Resilience of LLMs in Clinical Trial Eligibility Auditing
-
Validated Multi-Agent Simulation for Dementia Care: LLM-Based Agents with Biometric Feedback
-
Human-AI Collaborative Framework for Identifying Behavioral Health Conditions from Clinical Notes
-
Secure AI Orchestration for Digital Health with Differentially Private Analytics and Adaptive Group Coaching
-
From Detection to Forecasting: An Empirical Study of College Student Mental Health Using Smartphone Sensing
Session 2: Trustworthy AI Explainability and Privacy in Healthcare
-
Multimodal Routing for Interpretable, Robust, and Auditable Clinical Prediction
-
Membership Inference Attacks Expose Participation Privacy in ECG Foundation Encoders
-
NEURON: A Neuro-symbolic System for Grounded Clinical Explainability
-
Beyond Silos: Anchoring Trustworthy AI in Cross-Domain Knowledge Graphs for Rural Health Resilience
-
Evolving Sparse P2P Networks for Federated Survival Prediction with Adaptive Utility
-
Investigating Trustworthiness of Nonparametric Deep Survival Models for Alzheimer's Disease Progression Analysis
Session 3: Deep Learning for Medical Imaging and Biomedical Analysis
-
DySTGT-: Learning Interpretable Dynamic Brain Connectivity for Motor-Related BCI via Spatio-Temporal Graph Transformer
-
NeuroLens: A Multimodal Patient Digital Twin System for Early Screening and Real-Time Monitoring of Parkinson's Disease
-
Deep Learning Based Intestine Anatomical Sections Localization in Colonoscopy
-
A Framework for Automated Tracking of Morphologically Distinct Cell Populations in Time-Lapse Microscopy
-
Confidence-Gated Cloud-Edge Cascade Triage via Variational Risk Minimization for Medical Imaging
-
NUSAN: Medical Data Cleaning to Improve Class Separation with Minimal Structural Changes
Session 4: Advanced Sensing Cross-Modal Signal Generation and Edge Intelligence
-
LiftSafe: Predicting Unsafe Repetitions in Strength Training using a Single Wearable Sensor
-
P2Es: Physiology-Conditioned Diffusion for 12-Lead ECG Generation from PPG
-
SAFE: Sensor-Aware Fusion Engine for Fault-resilient In-home Health Activity Monitoring
-
KD-Judge: A Knowledge-Driven Automated Judge Framework for Functional Fitness Movements on Edge Devices
-
PhysQual: A Quality-Aware Learning Framework for Robust Remote Photoplethysmography
-
GoodVibes: Personalized Sports Injury Detection via Dual Gait Vector Context-Aware Learning of Human-induced Floor Vibrations
Short Papers
Short Paper Session 1: LLMs, Knowledge Graphs, and Digital Phenotyping for Clinical Support
-
Digital Phenotyping of Emotional Support: Predicting Feelings of Love from Adolescent Smartphone Text Messaging Data
-
DietTreeTalk: Translating Single Decision Tree Rules into LLM Reasoning for Explainable Diet Quality-Driven Diabetes Prediction
-
Healthcare-targeted Malicious URL Detection using LLM Integrated Dynamic Sandbox Environment
-
Generating High-Fidelity Synthetic Mental Health Records with Expert-in-the-Loop Verification
-
An Interactive LLM-Based Simulator for Dementia-Related Activities of Daily Living
-
DualCareKG: Integrating Clinical and Patient Knowledge Graphs for Dementia Caregiver Support
-
Large Language Models for Automatic ICD-10 Coding in Cancer Treatment and Billing: An Academic-Industry Partnership
Short Paper Session 2: Contactless Physiological Monitoring and Geriatric Sensing
-
Toward Vision-Based Parkinson's Assessment: Qualitative STS and Physiologically Constrained Turning
-
NIRNet: A Conditional GAN Framework for Transforming Non-NIR PPG Signals into NIR-Equivalent Waveforms for Contactless Physiological Monitoring
-
Deep Slice-Level Learning for Brain MRI Analysis: Toward Reliable Subject-Level Dementia Analysis
-
When PPG Meets ECG: Uncovering the Risks of Cross-Modal Biometric Matching
-
RFID-based Real-Time Geriatric Gait Speed Monitoring System: Design, Implementation and Clinical Evaluation
-
Equitable rPPG: Heart Rate Estimation for High-Melanin Skin using Triple-Stream 3D-CNNs
-
Decoupling Perception and Reasoning for Contactless Respiratory Rate with Vision Language and Small Language Models
Short Paper Session 3: Wearables IMU and Wireless Sensing for Health Monitoring
-
IMUVIE: Generalizable Pickup Measurement via Motion Movies
-
Physiohub: A Wirelessly Synchronized Multi-Node Wearable System
-
Physiological Workload Estimation from Single-Lead ECG via Learnable Time-Frequency Representations
-
Uncertainty Aware and Scalable WiFi CSI Sensing with Large Language Models
-
Evaluating Self-Supervised Pretraining for Wrist-Worn Physiological Signals in Cardiac Estimation and Gesture Recognition
-
Revisiting Time-Domain Interpretability for Self-Supervised IMU Sensing Models
-
X4Gait: Cross-Modal Supervision for Practical IMU-based Dual-Task Gait Recognition
Short Paper Session 4: Advanced Diagnostics and Clinical Assessment
-
A Hierarchical Deep Learning Framework for Gastric Anatomy Localization
-
Exploring Exertion-Aware AI Auscultation: Addressing Exercise-Induced Murmurs to Reduce False Pathological Alerts
-
CARE-ECG: Causal Agent-based Reasoning for Explainable and Counterfactual ECG Interpretation
-
A Modality-Adaptive System for Real-World Colorectal Polyp Classification
-
MTMed3D: A Multi-Task Transformer-Based Model for 3D Medical Imaging
-
Patch-MoE Mamba: A Patch-Ordered Mixture-of-Experts State Space Architecture for Medical Image Segmentation
-
PULSE: A Principled Framework for Multimodal Speech Sound Disorder Assessment Using Ultrasound Tongue Imaging
Short Paper Session 5: Computational Health Methods Prediction and Systems
-
Personalized Speed of Processing Training Online (pSOPT Online): A General Cloud-based Framework for Personalized Speed of Processing Training Tasks
-
CoughNet: A Lightweight, Low-Cost, and Energy-Efficient Multiple Coughers Detection and Identification System
-
A Multi-target Bayesian Transformer Framework for Predicting Cardiovascular Disease Biomarkers during Pandemics
-
HydroCare: Energy-Efficient Framework for Hydration Monitoring using Time-of-Flight Imaging
-
Event-Duration Distribution Modeling and Co-Adapted Ensembles for Speech-Based ADRD Screening
-
Adaptive Time-Series Forecasting through Reinforcement Learning Enhanced Attention
-
Bootstrapping Methodological Governance: A Deterministic Framework for Validating Public Health Data Analysis
Keynotes
Keynote: Bin He
Speaker: Bin He, Trustee Professor, Biomedical Engineering, Carnegie Mellon University
Topic: Bidirectional Brain-Computer Interfaces: Challenges and Opportunities
Keynote: Guoliang Xing
Speaker: Guoliang Xing, Professor, Department of Information Engineering, The Chinese University of Hong Kong
Topic: To be announced
Keynote: Goli Yamini
Speaker: Goli Yamini, Associate Program Director, National Science Foundation (NSF)
Topic: To be announced
Panels
Clinical Panel
Topic: Physicians and clinical practitioners share firsthand perspectives on the most pressing challenges in patient care, clinical workflow, remote monitoring, diagnosis, treatment support, health equity, and care coordination.
Panelists:
- Juan C. Celedon (UPMC Children's Hospital of Pittsburgh)
- Christopher deFilippi (University of Maryland School of Medicine)
- Goeran Fiedler (University of Pittsburgh)
- Florence Doo (University of Maryland School of Medicine)
Industry Panel
Topic: Company CEOs, incubator leaders, and technology managers discuss commercialization pathways, regulatory and reimbursement considerations, interoperability, data governance, AI reliability, scalability, user adoption, and partnership models.
Panelists:
- Beth Porter (C10 Labs)
- Daguang Xu (Nvidia)
- Zhang Zhang (TrialV.AI Inc.)
- Josh Caputo (Humotech Inc.)
Featured Sessions
ACM Health Session
Demo / Poster Session
Topic: Breakthrough poster, poster, and demo presentations from accepted submissions.
ACM Health Editor Board Meeting
NSF-NIH Smart and Connected Health Aspiring PI Workshop
Topic: Panel breakout sessions in which aspiring PIs meet with NSF/NIH Program Directors for individual feedback, followed by closing remarks and key takeaways.
NSF/NIH Program Directors:
- Dr. Goli Yamini (CISE/IIS, NSF)
- Dr. Andy Duan (CISE/IIS, NSF)
- Dr. Laurel Kuxhaus (Office of Strategic Coordination, NIH)
- Dr. Julia Berzhanskaya (NHLBI, NIH)
Elsevier Smart Health Journal Board Meeting
Workshops
Please note that all workshop schedules are tentative and are subject to changes.
HARMONY 2026 Workshop
Chair: Yixue Zhao (Yixue Research Institute)
Chair: Ping Wang (Stevens Institute of Technology)
Lightning-talk style: 10-minute talks followed by 5 minutes of Q&A.
-
Toward Contemplative LLM: A Modular Framework for Evaluating and Enhancing LLM Alignment in Mental Health
-
AIM: A Framework for Understanding How AI Literacy Shapes Software Practitioners' Mental Well-Being
-
The Effect of AI Feedback on Confidence and Self-Assessment
-
Human-AI Social Bonds: Evaluating Connection with Multimodal Synchrony
-
Verifiable AI-Assisted Mental Health Diagnosis via Logical Reasoning
Lightning-talk style: 10-minute talks followed by 5 minutes of Q&A.
-
On-Device Language Models for Privacy-Preserving Stress Prediction: A Multimodal Evaluation on Mobile Health
-
Optimizing Symptom Surveys with Machine Learning to Predict PTSD One Year Post-trauma
-
Towards LLM-Enhanced Cross-Domain Transfer Learning for Clinical Personality Prediction
-
Contemplative AI for Youth Stress: A New Paradigm for Digital Mental Health Support
-
Moodoodle: Supporting Emotional Self-Reflection Through Generative Soundscapes
-
Not All Nudges Land: Behavioral Controllability and Elaboration Quality in AI-Supported Journaling
Speaker: David Creswell — William S. Dietrich II Professor of Psychology and Neuroscience, Carnegie Mellon University; CEO, Equa Health
Title: Digital mindfulness meditation training, respiration tracking AI, and health
Panelists:
- David Creswell (keynote speaker) (Carnegie Mellon University; Equa Health)
- Rayid Ghani (Distinguished Career Professor, Machine Learning Department and Public Policy, Carnegie Mellon University)
- Josh Oltmanns (Assistant Professor of Psychological & Brain Sciences, Washington University in St. Louis; Licensed Clinical Psychologist)
- Andrew Begel (Associate Professor, Software and Societal Systems, Carnegie Mellon University; Affiliate Professor, Information School, University of Washington)
Tailored, small-group discussions; participants grouped by mutual interests to exchange ideas and find collaborators.
GenAI4HealthBI 2026: Generative AI for Smart Health and Biomedical Informatics
Chair: Jingping Nie (University of North Carolina at Chapel Hill)
Speaker: Xiang Li — Assistant Professor, Massachusetts General Hospital (MGH) and Harvard Medical School (HMS), Department of Radiology
Title: From Pixel to Mind: Generative AI for Smart Health and Patient World Model
Chair: Jingping Nie (University of North Carolina at Chapel Hill)
10-minute presentation + 2 minutes Q&A per paper.
-
Investigation on the Robustness of Acoustic Foundation Models on Post Exercise Speech
-
Towards Foundation Model-Based Stress and Emotion Recognition from Multimodal Physiological Signals
-
From Labels to Language: Zero-Shot Radiology Report Generation with Hybrid Retrieval Augmentation
-
Evaluating a Multi-Specialty Mixture-of-Experts Framework for Medical Question Answering Using LLM Agents and a DSPy Dispatcher
-
LOGAR: A Local-Online Generate-Audit-Refine Framework for Mental Health De-identification
Chair: Yiting Wang (Florida International University)
5-minute presentation + 1 minute Q&A per paper.
-
AI-Care: A Conversational Agentic System for Task Coordination in Alzheimer's Disease Care
-
Human-Governed Multi-Agent Clinical Reasoning Framework
-
ReCLLaMA: A Reasoning-Centered LLM Agent for Medical Diagnosis
-
From Closed-Set Classification to Open-Vocabulary Prediction: Stress Testing of SNOMED CT Relationship Prediction
-
Agentic AI-driven Immersive Simulation: A Knowledge-Aware Virtual Training Platform for High Dose Rate (HDR) Brachytherapy
-
Unraveling How Generative AI and Agentic AI Can Reshape the Scope of Digital Health: The Good, The Bad, and The Ugly
-
Order-Invariant ICD-10-CM Embedding for Readmission and Mortality Prediction: Toward Multimodal Generative Patient Models (poster)
-
Real-Time Neural Musculoskeletal Pose Estimation (demo)
-
Improving Clinical Note De-identification via Post-NER Verification and Candidate Expansion
-
Reliability Stress Tests and Decision-Time Routing for Chest X-ray Vision-Language Models
ARMH Workshop: AI-Powered Resilient Mobile Health — From AI-RAN to Application
Chair: Tian Xie (Utah State University)
Speaker: Chixiang Chen, University of Maryland, Baltimore
Chair: Yi Zhu (Wayne State University)
10-minute presentation for each paper.
-
E-SIMS: A Human-Centered Vision for Personalized Elderly Health Monitoring
-
Rethinking Federated Learning for Mobile Health Therapeutic Research: A Principled Framework
-
Robust Long-Term Calibration of Vision-Based Ground Truth for Home-Based Human Tracking
-
Attack and Failure Indistinguishability in Wearable Systems: An End-to-End Pipeline Modeling Approach
-
PRISM: Predictive and Interpretable Multi-Omics Integration for Clinical Outcome Modeling
-
Speech-Based Concussion Detection Using CNNs: A Comparative Study of Acoustic Feature Representations for Digital Health Monitoring
Chair: Yiwen Hu (University of Maryland, Baltimore County)
10-minute presentation for each paper.
-
Towards Robust CLIP Adaptation for Medical Image Classification via Text Prototype Adaptation
-
Beyond Blur: A Semantic Tri-view Pipeline for Teledermatology Gradability via Skin Micro-relief
-
Heart2act Activity State Clustering for Longitudinal Heart Rate Data with Few Labels
-
The WellnessWatch: A Wearable Device Integrating Fall Detection With Environmental Monitoring
-
When Caregiving Datasets Disagree: A Cross-Source Analysis of BRFSS and AARP/NAC Trends for Public Health Surveillance
-
Hierarchical Contrastive Multimodal Alignment for Contactless Sensing: An Empirical Study on Zero-shot mmWave-based HAR
The 2nd Workshop on Sensing and Computing for Smart and Connected Health (SCH)
Speaker: Dr. Shijia Pan
30-minute talk + 10 minutes Q&A.
-
Personalized Counterfactual Framework: Generating Potential Outcomes from Wearable Data
-
Beyond AHI: An Interpretable Causal-Discovery–Guided Framework for Sleep Recovery in Connected Health
-
MedIntelliX – AI-Powered Medical Decision Support System
-
AlzGood: Validating Remote Care Systems in the Wild via an Interactive Deployment Framework
Speaker: Dr. Fei Dou
30-minute talk + 10 minutes Q&A.
-
Forecasting Minute-by-Minute Stress, Anxiety, and Affective States Using Time-Series Analysis of Wearable Sensor Data
-
An Anomaly Detection Approach for Foot Displacement Detection in Power Wheelchairs
-
Agentic Multimodal Sensing for Energy-Efficient Fall Detection in Powered Exoskeletons for Spinal Cord Injury
-
A Quality-Aware Framework for Contactless Respiratory Monitoring Under Variable Sensing Conditions
The 2nd Workshop on Data Quality-Aware, High-Performance, and Trustworthy AI Systems for Healthcare (TAIS4H)
Session Moderator: Dr. Kewei Sha (University of North Texas)
-
An Efficient and Interpretable Learning Approach for Large-Scale Histopathology Data
-
GuardChain: A Layered Middleware Framework for PII-Aware Guardrails in Healthcare and Financial LLM Agents
-
Spatially Grounded Concept Bottleneck Models for Trustworthy Breast Ultrasound Diagnosis
-
A Two-Stage AI System for Interpretable ACL Tear Screening in Connected Health Environments
-
X-Beat: An Explainable Framework for ECG Image Classification
mHealth Security Workshop
Speaker: Prof. Shiwen Mao, Auburn University
Title: Functional Data Analysis for Intelligent Wireless Sensing: Principles, Methods, and Applications
Each paper: 20 minutes (15-minute presentation + 5 minutes Q&A).
-
Secure Remote PPG-based Verification for mHealth under Heavy Facial Occlusion
-
Enhancing NAC-ABE to Support Access Control for mHealth Applications and Beyond
-
X-Beat: An Explainable Framework for ECG Image Classification




