An official website of the United States government
Patient-generated data, such as recorded Observations of Daily Living (ODL) and Patient-Reported Outcomes (PRO) data, are valued sources of information in oncology care. However, prior work largely focuses on capturing clinician-defined, patient-generated data in adult oncology care. Emerging research at the intersection of human–computer interaction and medical informatics suggests that visual narratives of patients’ observations of daily living (Visual ODLs) could better support multi-party review of patients’ everyday symptoms and quality of life, potentially improving patient–clinician communication. In this paper, we build on a prior study of Visual ODLs by describing a formative, two-phase study with 15 pediatric oncology clinicians. In Phase I, we analyzed data from ethnographic interviews in a pediatric oncology setting to capture the needs of nurses, nurse practitioners, and oncologists. In Phase II, we constructed two low-fidelity dashboard display prototypes, populated with Visual ODLs contributed by actual adolescent oncology patients, and we subsequently interviewed pediatric oncology clinicians who reviewed each dashboard design. Findings from our study contribute four key design objectives for presenting interactive Visual ODL dashboards in pediatric oncology, along with three use cases for using these dashboards for symptom tracking and communication.
more »
« less
This content will become publicly available on April 26, 2026
Exploring Caregivers’ Acceptance of Conversational AI in Pediatric Cancer Caregiving: A Mixed-Methods Study
Caring for a child with cancer involves navigating through complex medical information, often delivered through lengthy handbooks and consultations with healthcare providers. Overnight, parents are expected to become an expert on a domain which they knew noth- ing about. Conversational UIs, powered by Large Language Models (LLMs) and validated information sources, could play a key role in supporting caregivers. In this paper, we investigate the usability, acceptance, and perceived utility of an LLM-based conversational AI tool for pediatric cancer caregiving, grounded in the Children’s Oncology Group Family Handbook–the leading resource in pe- diatric oncology care. We employed a mixed-methods approach, interviewing and surveying 12 caregivers as they engaged with a functional prototype. We offer insights into caregiver’s needs and expectations from AI-driven tools, and design guidelines for devel- oping safer, more personalized, and supportive AI interventions for pediatric cancer care.
more »
« less
- Award ID(s):
- 2047432
- PAR ID:
- 10577183
- Publisher / Repository:
- ACM SIGCHI - CHI 2025 Late-Breaking Work
- Date Published:
- Format(s):
- Medium: X
- Location:
- Yokohama, Japan
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
BackgroundAlthough family caregivers play a critical role in care delivery, research has shown that they face significant physical, emotional, and informational challenges. One promising avenue to address some of caregivers’ unmet needs is via the design of digital technologies that support caregivers’ complex portfolio of responsibilities. Augmented reality (AR) applications, specifically, offer new affordances to aid caregivers as they perform care tasks in the home. ObjectiveThis study explored how AR might assist family caregivers with the delivery of home-based cancer care. The specific objectives were to shed light on challenges caregivers face where AR might help, investigate opportunities for AR to support caregivers, and understand the risks of AR exacerbating caregiver burdens. MethodsWe conducted a qualitative video elicitation study with clinicians and caregivers. We created 3 video elicitations that offer ways in which AR might support caregivers as they perform often high-stakes, unfamiliar, and anxiety-inducing tasks in postsurgical cancer care: wound care, drain care, and rehabilitative exercise. The elicitations show functional AR applications built using Unity Technologies software and Microsoft Hololens2. Using elicitations enabled us to avoid rediscovering known usability issues with current AR technologies, allowing us to focus on high-level, substantive feedback on potential future roles for AR in caregiving. Moreover, it enabled nonintrusive exploration of the inherently sensitive in-home cancer care context. ResultsWe recruited 22 participants for our study: 15 clinicians (eg, oncologists and nurses) and 7 family caregivers. Our findings shed light on clinicians’ and caregivers’ perceptions of current information and communication challenges caregivers face as they perform important physical care tasks as part of cancer treatment plans. Most significant was the need to provide better and ongoing support for execution of caregiving tasks in situ, when and where the tasks need to be performed. Such support needs to be tailored to the specific needs of the patient, to the stress-impaired capacities of the caregiver, and to the time-constrained communication availability of clinicians. We uncover opportunities for AR technologies to potentially increase caregiver confidence and reduce anxiety by supporting the capture and review of images and videos and by improving communication with clinicians. However, our findings also suggest ways in which, if not deployed carefully, AR technologies might exacerbate caregivers’ already significant burdens. ConclusionsThese findings can inform both the design of future AR devices, software, and applications and the design of caregiver support interventions based on already available technology and processes. Our study suggests that AR technologies and the affordances they provide (eg, tailored support, enhanced monitoring and task accuracy, and improved communications) should be considered as a part of an integrated care journey involving multiple stakeholders, changing information needs, and different communication channels that blend in-person and internet-based synchronous and asynchronous care, illness, and recovery.more » « less
-
Cancer research encompasses data across various scales, modalities, and resolutions, from screening and diagnostic imaging to digitized histopathology slides to various types of molecular data and clinical records. The integration of these diverse data types for personalized cancer care and predictive modeling holds the promise of enhancing the accuracy and reliability of cancer screening, diagnosis, and treatment. Traditional analytical methods, which often focus on isolated or unimodal information, fall short of capturing the complex and heterogeneous nature of cancer data. The advent of deep neural networks has spurred the development of sophisticated multimodal data fusion techniques capable of extracting and synthesizing information from disparate sources. Among these, Graph Neural Networks (GNNs) and Transformers have emerged as powerful tools for multimodal learning, demonstrating significant success. This review presents the foundational principles of multimodal learning including oncology data modalities, taxonomy of multimodal learning, and fusion strategies. We delve into the recent advancements in GNNs and Transformers for the fusion of multimodal data in oncology, spotlighting key studies and their pivotal findings. We discuss the unique challenges of multimodal learning, such as data heterogeneity and integration complexities, alongside the opportunities it presents for a more nuanced and comprehensive understanding of cancer. Finally, we present some of the latest comprehensive multimodal pan-cancer data sources. By surveying the landscape of multimodal data integration in oncology, our goal is to underline the transformative potential of multimodal GNNs and Transformers. Through technological advancements and the methodological innovations presented in this review, we aim to chart a course for future research in this promising field. This review may be the first that highlights the current state of multimodal modeling applications in cancer using GNNs and transformers, presents comprehensive multimodal oncology data sources, and sets the stage for multimodal evolution, encouraging further exploration and development in personalized cancer care.more » « less
-
PURPOSE: Despite decades of effort, burnout among physicians remains elevated compared with that of other working populations, and it yields catastrophic consequences, including medical errors and physician suicide. Burnout leaves oncologists feeling like they are alone, but this is not the case—it affects everyone. To effectively address burnout, it is not enough to look only at oncologists; instead, we must include all those involved in the delivery of cancer care. With this aim, we present an overview of the organizational science strategies and initial evidence for the value of a comprehensive, team-focused approach to addressing oncology provider burnout. METHODS: We describe the development of a team-focused burnout intervention approach, implemented for oncology providers, which focuses on the importance of encouraging communication and psychological safety to reduce feelings of isolation and fragmentation. We discuss the initial findings from 1 such team-based initiative currently underway within an academic medical center, presenting data from 409 cancer care providers embedded in 30 oncology units participating in this intervention approach. RESULTS: Preliminary results demonstrate that units that integrated a team-focused intervention for burnout reported significantly higher levels of teamwork and lower levels of burnout. We also describe lessons learned and recommendations for implementing this type of intervention on the basis of best practices from organizational science. CONCLUSION: This approach can positively affect the delivery of cancer care, interprofessional relationships among oncology staff, and the well-being of both patients and providers. Treating physician burnout alone will treat 1 symptom of the overall issue of burnout in oncology. As burnout pulls oncology clinicians apart, our solution must be to bring them together.more » « less
-
While AI holds immense potential for accelerating advances in oncology, we must be intentional in developing and applying these technologies responsibly, equitably, and ethically. One path forward is for cancer care providers and researchers to be among the architects of AI and its adoption in medicine. Given the limitations of traditional top-down, hypothesis-driven design in an exponentially expanding data universe, on one hand, and the danger of spiraling into artificial ignorance (ai) from rushing into a purely ‘synthetic’ method on the other, this article proposes a ‘scienthetic’ method that synergizes AI with human wisdom. Tracing philosophical underpinnings of the scientific method from Socrates, Plato, and Aristotle to the present, it examines the critical juncture at which AI stands to either augment or undermine new knowledge. The scienthetic method seeks to harness the power and capabilities of AI responsibly, equitably, and ethically to transcend the limitations of both the traditional scientific method and purely synthetic methods, by intentionally weaving machine intelligence together with human wisdom.more » « less
