Mindfulness, Breathing, and Biofeedback Technologies

会議の名前
CHI 2026
Encouraging Breath: Increasing Out‑of‑Session DMHI Engagement using a Shape‑Changing Biofeedback Physicalization within a Longitudinal RCT
要旨

Out-of-session or "homework'' engagement is a primary limiting factor in clinical mental health outcomes. Despite weekly practitioner contact, adherence to prescribed Digital Mental Health Interventions (DMHIs) typically drops by 96.1% within two weeks. We evaluate Ankor, a handheld shape-changing biofeedback physicalization, as an adjunct to standard audio-guided mindfulness. In a longitudinal randomized controlled study (N=69), participants were assigned to Ankor+audio or audio-only control across six weekly 15-minute laboratory sessions, with optional DMHI use between sessions. Relative to control, Ankor yielded a 351% increase in total DMHI practice initiations and, by week 2, maintained 29.4% active users versus 2.9% in control, indicating substantially higher out-of-session engagement and reduced early disengagement. These findings demonstrate the capacity of shape-changing biofeedback physicalizations to extend adherence to DMHIs, highlighting kinaesthetic interactions as a promising design pathway for sustaining engagement in mental health interventions.

著者
Alexz Farrall
ADA University, Baku, Azerbaijan
Adwait Sharma
University of Bath, Bath, United Kingdom
Ben Ainsworth
University of Southampton, Southampton, United Kingdom
Pamela Jacobsen
University of Bath, Bath, United Kingdom
Jason Alexander
University of Bath, Bath, United Kingdom
AI-generated AR Reassembly Guidance from Disassembly Videos to Scaffold Everyday Repair
要旨

Repair is a valuable yet challenging activity, especially when product manuals are missing or outdated. Augmented Reality (AR) has been widely explored for repair tasks, but most systems rely on CAD models or pre-constructed assets, which escalate authoring costs and constrain scalability. We introduce RePairAR, a system that leverages multimodal large language models (MLLMs) to generate interactive AR reassembly guidance derived directly from user-recorded egocentric disassembly videos. RePairAR deduces step-part-relation structures, reverses these for reassembly planning, and delivers the guidance through mixed-media AR visualizations. In a user study with repair novices, RePairAR significantly reduced perceived temporal demand compared to traditional how-to videos. Both media improved self-efficacy, with RePairAR providing greater gains. Follow-up interviews revealed the mechanisms behind these effects. We contribute a validated MLLM-driven pipeline and highlight design implications for scalable, situated support in everyday repair practices.

著者
Wenjing Deng
Tsinghua University, Beijing, China
Zhihao Yao
Tsinghua University, Beijing, Beijing, China
Xinhui Kang
Tsinghua University, Beijing, China
Qirui Sun
Tsinghua University, Beijing, China
Xintong Wu
Tsinghua University, Beijing, China
Sisi He
Nanyang Institute of Technology, Nanyang City, Henan Province, China
Chenzhuo Xiang
Tsinghua University, Beijing, China
Haipeng Mi
Tsinghua University, Beijing, China
Enabling Adaptive Cardio-Respiratory Biofeedback Training on Ubiquitous Hand-Worn Devices
要旨

We introduce an adaptive cardio-respiratory biofeedback system implemented on ubiquitous hand-worn devices such as smart watches and rings, enabling accessible and real-time physiological training outside clinical settings. Users place a hand on their abdomen to promote embodied awareness of breathing rhythms, while PPG and IMU sensors continuously capture cardio-respiratory signals. Unlike conventional open-loop biofeedback that delivers fixed breathing guidance irrespective of user response, our system employs a closed-loop adaptation: real-time physiological signals adjust breathing cues to optimize cardio-respiratory coupling, ensuring personalized training trajectories. This shift from static to adaptive guidance markedly improves user engagement and training efficacy. A user performance evaluation study further showed that adaptive biofeedback significantly boosts HRV, prolongs high-HRV states, and enhances user experience, demonstrating clear advantages over non-adaptive methods. Together, these findings position adaptive, hand-worn biofeedback as a promising approach for ubiquitous, user-centered mental health interventions.

著者
Ruotong Yu
Tsinghua University, Beijing, China
Xintong Wu
Tsinghua University, Beijing, China
Lily Sheng
Tsinghua University, Beijing, China
ZIHAO DONG
Tsinghua University, BEIJING, China
Yuntao Wang
Tsinghua University, Beijing, China
Yuanchun Shi
Tsinghua University, Beijing, China
Stress Mindset Matters: Rethinking Mental Stress Detection with Multimodal Wearable Sensors
要旨

The mindset people have about stress is important to be studied because this core belief, that stress is either enhancing or debilitating, fundamentally alters a person’s physiological and psychological responses to stressors. However, this crucial construct is rarely considered in prior research on momentary stress detection with wearables, leaving two fundamental questions unanswered: can wearable data identify an individual’s stress mindset, and can mindset be leveraged to build better performing stress detection models? To investigate that, we conducted an in-lab study with wearable devices by inducing mental stress in participants (N=23). First, we found that heart rate variability and electrodermal activity features carry signatures of stress mindset. Second, machine learning models can discriminate stress mindset with sensors, achieving AUCs upto 0.88. Finally, a random forest model trained for stress-is-enhancing participants outperformed a one-size-fits-all model (AUC=0.91 vs. 0.78, p<0.05), for the task of stress detection. Our findings show that stress mindset leaves a measurable physiological footprint and that mindset-aware models open the potential for more personalized stress detection and interventions. To support future research, we publicly release the anonymized dataset at https://social-dynamics.net/stress/mindset

受賞
Best Paper
著者
Lakmal Meegahapola
Nokia Bell Labs, Cambridge, United Kingdom
Marios Constantinides
CYENS Centre of Excellence, Nicosia, Cyprus
Zoran Radivojevic
Nokia Bell Labs, Cambridge, Cambridgeshire, United Kingdom
Hongwei Li
Nokia Bell Labs, Cambridge, United Kingdom
Michael S. Eggleston
Nokia Bell Labs, Murray Hill, New Jersey, United States
Daniele Quercia
Nokia Bell Labs, Cambridge, United Kingdom
MindfulAgents: Personalizing Mindfulness Meditation via an Expert-Aligned Multi-Agent System
要旨

Mindfulness meditation is a widely accessible and evidence-based method for supporting mental health. Despite the proliferation of mindfulness meditation apps, sustaining user engagement remains a persistent challenge. Personalizing the meditation experience is a promising strategy to improve engagement, but it often requires costly and unscalable manual effort. We present MindfulAgents, a multi-agent system powered by large language models that: (1) generates guided meditation scripts based on an expert-established mindfulness framework, (2) encourages users' reflection on emotional states and mindfulness skills, and (3) enables real-time personalization of the mindfulness meditation experience for each user. In a formative lab study (N=13), MindfulAgents significantly improved in-session engagement (p = 0.011) and self-awareness (p = 0.014), as well as reduced momentary stress (p = 0.020). Furthermore, a four-week deployment study (N=62) demonstrated a notable increase (p = 0.002) in long-term engagement and level of mindfulness (p = 0.023). Participants reported that MindfulAgents offered more relevant meditation sessions personalized to individual needs in various contexts, supporting sustained practice. Our findings highlight the potential of LLM-driven personalization for enhancing user engagement in digital mindfulness meditation interventions.

受賞
Honorable Mention
著者
Mengyuan Wu
Columbia University, New York, New York, United States
Zhihan Jiang
The University of Hong Kong, Hong Kong, China
Yuang Fan
Columbia University, New York, New York, United States
Richard Feng
St. Margaret's Episcopal School, San Juan Capistrano, California, United States
Sahiti Dharmavaram
Columbia University, New York, New York, United States
Mathew Polowitz
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Shawn Fallon
Carnegie Mellon University, Pittsburg, Pennsylvania, United States
Bashima Islam
Worcester Polytechnic Institute , Worcester , Massachusetts, United States
Lizbeth Benson
Institute for Social Research, University of Michigan, Ann Arbor, Michigan, United States
Irene Tung
California State University Dominguez Hills, Carson, California, United States
David Creswell
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Xuhai "Orson" Xu
Columbia University, New York City, New York, United States
CalmReminder: A Design Probe for Parental Engagement with Children with Hyperactivity, Augmented by Real-Time Motion Sensing with a Watch
要旨

Families raising children with ADHD often experience heightened stress and reactive parenting. While digital interventions promise personalization, many remain one-size-fits-all and fail to reflect parents' lived practices. We present CalmReminder a watch-based system that detects children's calm moments and delivers just-in-time prompts to parents. Through a four-week deployment with 13 families (nine completed) of children with ADHD, we compared notification strategies ranging from hourly to random to only when the child was inferred to be calm. Our sensing-based notifications were frequently perceived as arriving during calm moments. More importantly, parents adopted the system in diverse ways: using notifications for praise, mindfulness, activity planning, or conversation. These findings show that parents are not passive recipients but active co-designers, reshaping interventions to fit their parenting styles. We contribute calm detection pipeline, empirical insights into families' flexible appropriation of notifications, and design implications for intervention systems that foster agency.

著者
Riku Arakawa
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Shreya Bali
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Anupama Sitaraman
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Woosuk Seo
Yale University, New Haven, Connecticut, United States
Sam Shaaban
NuRelm, Pittsburgh, Pennsylvania, United States
Oliver Lindhiem
University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, United States
Traci M.. Kennedy
University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, United States
Mayank Goel
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Breathing Inward: A Targeted-heat Wearable Designed to Deepen the Benefits of Diaphragmatic Breathing
要旨

Deliberate regulation of diaphragmatic breathing can contribute to well-being. We present a targeted-heat wearable designed to direct attention inward during breathing practice. In a mixed-methods study, breathing was guided with a pulsing-heat or a screen-based app. We included physiological measures of heart-rate, HRV, and breathing pace; self-report questionnaires on interoception and mindfulness; and qualitative interviews. Results show both groups adhered well to the breathing guidance, yet heat-condition participants reached lower heart-rate and reduced sympathetic activation, physiological markers associated with stress reduction. They also reported higher interoceptive awareness, specifically self-regulation and body-listening abilities, alongside significantly higher state mindfulness. Qualitative findings revealed that targeted-heat fostered a stronger connection with bodily sensations and emotions, while visual feedback was often experienced as pulling attention outward. Our work suggests that breathing with the heat wearable increases the known positive outcomes of diaphragmatic breathing, helping people connect more deeply with their bodies by directing attention inward.

著者
Tamar Dublin
Reichman University, Herzliya, Israel
Jonathan Giron
Reichman University , Herzeliya, Israel, Israel
Andrey Grishko
Reichman University, Herzliya, Israel
Emanuel Talmasky
Reichman University , Herzliya, Israel
Gil Zilberstein
Reichman University , Herzliya , Israel
Hadas Erel
Reichman University, Herzliya, Israel
Oren Zuckerman
Reichman University, Herzliya, Israel