Health and AI C

会議の名前
CHI 2024
Memoro: Using Large Language Models to Realize a Concise Interface for Real-Time Memory Augmentation
要旨

People have to remember an ever-expanding volume of information. Wearables that use information capture and retrieval for memory augmentation can help but can be disruptive and cumbersome in real-world tasks, such as in social settings. To address this, we developed Memoro, a wearable audio-based memory assistant with a concise user interface. Memoro uses a large language model (LLM) to infer the user’s memory needs in a conversational context, semantically search memories, and present minimal suggestions. The assistant has two interaction modes: Query Mode for voicing queries and Queryless Mode for on-demand predictive assistance, without explicit query. Our study of (N=20) participants engaged in a real-time conversation, demonstrated that using Memoro reduced device interaction time and increased recall confidence while preserving conversational quality. We report quantitative results and discuss the preferences and experiences of users. This work contributes towards utilizing LLMs to design wearable memory augmentation systems that are minimally disruptive.

受賞
Honorable Mention
著者
Wazeer Deen. Zulfikar
MIT Media Lab, Cambridge, Massachusetts, United States
Samantha Chan
MIT Media Lab, Cambridge, Massachusetts, United States
Pattie Maes
MIT Media Lab, Cambridge, Massachusetts, United States
論文URL

https://doi.org/10.1145/3613904.3642450

動画
Artful Path to Healing: Using Machine Learning for Visual Art Recommendation to Prevent and Reduce Post-Intensive Care Syndrome (PICS)
要旨

Staying in the intensive care unit (ICU) is often traumatic, leading to post-intensive care syndrome (PICS), which encompasses physical, psychological, and cognitive impairments. Currently, there are limited interventions available for PICS. Studies indicate that exposure to visual art may help address the psychological aspects of PICS and be more effective if it is personalized. We develop Machine Learning-based Visual Art Recommendation Systems (VA RecSys) to enable personalized therapeutic visual art experiences for post-ICU patients. We investigate four state-of-the-art VA RecSys engines, evaluating the relevance of their recommendations for therapeutic purposes compared to expert-curated recommendations. We conduct an expert pilot test and a large-scale user study (n=150) to assess the appropriateness and effectiveness of these recommendations. Our results suggest all recommendations enhance temporal affective states. Visual and multimodal VA RecSys engines compare favourably with expert-curated recommendations, indicating their potential to support the delivery of personalized art therapy for PICS prevention and treatment.

著者
Bereket A.. YILMA
University of Luxembourg, Luxembourg, ESCH/ALZETTE, Luxembourg
Chan Mi Kim
University of Twente, Enschede, Netherlands
Gerald C. Cupchik
University of Toronto, Toronto, Ontario, Canada
Luis A.. Leiva
University of Luxembourg, Esch-sur-Alzette, Luxembourg
論文URL

https://doi.org/10.1145/3613904.3642636

動画
Explainable Notes: Examining How to Unlock Meaning in Medical Notes with Interactivity and Artificial Intelligence
要旨

Medical progress notes have recently become available to patients at an unprecedented scale. Progress notes offer patients insight into their care that they cannot find elsewhere. That said, reading a note requires patients to contend with the language, unspoken assumptions, and clutter common to clinical documentation. As the health system reinvents many of its interfaces to incorporate AI assistance, this paper examines what intelligent interfaces could do to help patients read their progress notes. In a qualitative study, we examine the needs of patients as they read a progress note. We then formulate a vision for the explainable note, an augmented progress note that provides support for directing attention, phrase-level understanding, and tracing lines of reasoning. This vision manifests in a set of patient-inspired opportunities for advancing intelligent interfaces for writing and reading progress notes.

著者
Hita Kambhamettu
University of Pennsylvania, Philadelphia, Pennsylvania, United States
Danaë Metaxa
University of Pennsylvania, Philadelphia, Pennsylvania, United States
Kevin Johnson
University of Pennsylvania, Philadelphia, Pennsylvania, United States
Andrew Head
University of Pennsylvania, Philadelphia, Pennsylvania, United States
論文URL

https://doi.org/10.1145/3613904.3642573

動画
ConverSense: An Automated Approach to Assess Patient-Provider Interactions using Social Signals
要旨

Patient-provider communication influences patient health outcomes, and analyzing such communication could help providers identify opportunities for improvement, leading to better care. Interpersonal communication can be assessed through “social-signals” expressed in non-verbal, vocal behaviors like interruptions, turn-taking, and pitch. To automate this assessment, we introduce a machine-learning pipeline that ingests audiostreams of conversations and tracks the magnitude of four social-signals: dominance, interactivity, engagement, and warmth. This pipeline is embedded into ConverSense, a web-application for providers to visualize their communication patterns, both within and across visits. Our user study with 5 clinicians and 10 patient visits demonstrates ConverSense's potential to provide feedback on communication challenges, as well as the need for this feedback to be contextualized within the specific underlying visit and patient interaction. Through this novel approach that uses data-driven self-reflection, ConverSense can help providers improve their communication with patients to deliver improved quality of care.

著者
Manas Satish Bedmutha
University of California San Diego, San Diego, California, United States
Anuujin Tsedenbal
UC San Diego, La Jolla, California, United States
Kelly Tobar
University of California, San Diego, San Diego, California, United States
Sarah Borsotto
UC San Diego, La Jolla, California, United States
Kimberly R. Sladek
University of California, San Diego, San Diego, California, United States
Deepansha Singh
University of California, San Diego, San Diego, California, United States
Reggie Casanova-Perez
University of Washington, Seattle, Washington, United States
Emily Bascom
University of Washington, Seattle, Washington, United States
Brian Wood
University of Washington, Seattle, Washington, United States
Janice Sabin
University of Washington, Seattle, Washington, United States
Wanda Pratt
University of Washington, Seattle, Washington, United States
Andrea Hartzler
University of Washington, Seattle, Washington, United States
Nadir Weibel
UC San Diego, La Jolla, California, United States
論文URL

https://doi.org/10.1145/3613904.3641998

動画
Sketching AI Concepts with Capabilities and Examples: AI Innovation in the Intensive Care Unit
要旨

Advances in artificial intelligence (AI) have enabled unprecedented capabilities, yet innovation teams struggle when envisioning AI concepts. Data science teams think of innovations users do not want, while domain experts think of innovations that cannot be built. A lack of effective ideation seems to be a breakdown point. How might multidisciplinary teams identify buildable and desirable use cases? This paper presents a first hand account of ideating AI concepts to improve critical care medicine. As a team of data scientists, clinicians, and HCI researchers, we conducted a series of design workshops to explore more effective approaches to AI concept ideation and problem formulation. We detail our process, the challenges we encountered, and practices and artifacts that proved effective. We discuss the research implications for improved collaboration and stakeholder engagement, and discuss the role HCI might play in reducing the high failure rate experienced in AI innovation.

著者
Nur Yildirim
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Susanna Zlotnikov
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Deniz Sayar
Izmir University of Economics, Izmir, Turkey
Jeremy M.. Kahn
University of Pittsburgh, Pittsburgh, Pennsylvania, United States
Leigh A. Bukowski
University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, United States
Sher Shah Amin
University of Pittsburgh, Pittsburgh, Pennsylvania, United States
Kathryn A,. Riman
University of Pittsburgh, Pittsburgh, Pennsylvania, United States
Billie S.. Davis
University of Pittsburgh, Pittsburgh, Pennsylvania, United States
John S. Minturn
University of Pittsburgh, Pittsburgh, Pennsylvania, United States
Andrew J King
University of Pittsburgh, Pittsburgh, Pennsylvania, United States
Dan Ricketts
University of Pittsburgh, Pittsburgh, Pennsylvania, United States
Lu Tang
University of Pittsburgh, Pittsburgh, Pennsylvania, United States
Venkatesh Sivaraman
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Adam Perer
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Sarah M. Preum
Dartmouth College, Hanover, New Hampshire, United States
James McCann
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
John Zimmerman
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
論文URL

https://doi.org/10.1145/3613904.3641896

動画