An official website of the United States government
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
To Address Burnout in Oncology, We Must Look to Teams: Reflections on an Organizational Science Approach
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
- Award ID(s):
- 1654054
- PAR ID:
- 10145579
- Date Published:
- Journal Name:
- JCO Oncology Practice
- Volume:
- 16
- Issue:
- 4
- ISSN:
- 2688-1527
- Page Range / eLocation ID:
- e377 to e383
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
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
-
null (Ed.)In this paper, we describe the iterative participatory design of SOPHIE, an online virtual patient for feedback-based practice of sensitive patient-physician conversations, and discuss an initial qualitative evaluation of the system by professional end users. The design of SOPHIE was motivated from a computational linguistic analysis of the transcripts of 383 patient-physician conversations from an essential office visit of late stage cancer patients with their oncologists. We developed methods for the automatic detection of two behavioral paradigms, lecturing and positive language usage patterns (sentiment trajectory of conversation), that are shown to be significantly associated with patient prognosis understanding. These automated metrics associated with effective communication were incorporated into SOPHIE, and a pilot user study identified that SOPHIE was favorably reviewed by a user group of practicing physicians.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
-
Background Over the past 2 decades, various desktop and mobile telemedicine systems have been developed to support communication and care coordination among distributed medical teams. However, in the hands-busy care environment, such technologies could become cumbersome because they require medical professionals to manually operate them. Smart glasses have been gaining momentum because of their advantages in enabling hands-free operation and see-what-I-see video-based consultation. Previous research has tested this novel technology in different health care settings. Objective The aim of this study was to review how smart glasses were designed, used, and evaluated as a telemedicine tool to support distributed care coordination and communication, as well as highlight the potential benefits and limitations regarding medical professionals’ use of smart glasses in practice. Methods We conducted a literature search in 6 databases that cover research within both health care and computer science domains. We used the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology to review articles. A total of 5865 articles were retrieved and screened by 3 researchers, with 21 (0.36%) articles included for in-depth analysis. Results All of the reviewed articles (21/21, 100%) used off-the-shelf smart glass device and videoconferencing software, which had a high level of technology readiness for real-world use and deployment in care settings. The common system features used and evaluated in these studies included video and audio streaming, annotation, augmented reality, and hands-free interactions. These studies focused on evaluating the technical feasibility, effectiveness, and user experience of smart glasses. Although the smart glass technology has demonstrated numerous benefits and high levels of user acceptance, the reviewed studies noted a variety of barriers to successful adoption of this novel technology in actual care settings, including technical limitations, human factors and ergonomics, privacy and security issues, and organizational challenges. Conclusions User-centered system design, improved hardware performance, and software reliability are needed to realize the potential of smart glasses. More research is needed to examine and evaluate medical professionals’ needs, preferences, and perceptions, as well as elucidate how smart glasses affect the clinical workflow in complex care environments. Our findings inform the design, implementation, and evaluation of smart glasses that will improve organizational and patient outcomes.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1200/JOP.19.00631
