Background: Psychological distress, particularly symptoms of depression and anxiety (D&A), is highly prevalent among family caregivers of individuals living with cancer, who often assume central roles in care coordination, treatment adherence, symptom monitoring, and emotional support. Rates of distress among caregivers frequently equal or exceed those observed in patients themselves. Despite increased attention to caregivers' mental health needs, routine distress screening remains limited in oncology care settings. Advances in mobile health technology and artificial intelligence (AI) offer opportunities to address these needs by providing accessible and user-driven tools. The Ellipsis Caregiver Assessment Enhancement (eCARE; Ellipsis Health, Inc) is a speech-based, AI-enabled mobile app designed to screen and monitor symptoms of depression and anxiety. By collecting brief voice recordings and in-app survey data, eCARE offers a scalable approach for integrating caregiver distress monitoring into cancer care.
Objective: This single-arm trial will evaluate the feasibility and acceptability of the eCARE app among family members who are the primary caregivers of patients diagnosed with cancer within the past 5 years. Specifically, the study aims to (1) determine feasibility based on platform completion rates, (2) assess acceptability using validated measures, and (3) identify barriers and facilitators influencing the uptake and sustained use of eCARE.
Methods: In Phase 1, a total of 60 United States-based family caregivers will be recruited from community health clinics, cancer and caregiving advocacy groups, and online postings. Screened and enrolled caregivers will complete 6 eCARE sessions over an 8-week period. Pre- and posttest surveys assess depression, anxiety, caregiving burden, and relational processes. Feasibility will be evaluated based on the proportion of participants who complete at least 66% of weekly assessments, and acceptability will be assessed using the acceptability of intervention measure (AIM). In Phase 2, a total of 20 caregivers will be invited to participate in semi-structured online interviews to explore user experience, including perceived benefits, barriers to use, and preferences for future implementation. Qualitative data will be analyzed thematically to inform tool refinement.
Results: The study has received Institutional Review Board approval from the University of Houston. Participant recruitment and enrollment began in June 2024, with data collection expected to conclude by August 2025. Data analysis will begin in December 2025, with preliminary results anticipated by May 2026.
Conclusions: This study will generate preliminary evidence on the feasibility, acceptability, and utility of a speech-based, AI-enabled smartphone tool for monitoring D&A symptoms among family cancer caregivers. Findings will inform the design of a larger, fully powered trial and guide future implementation of remote psychological distress monitoring strategies in oncology care. By offering a low-burden, caregiver-centered approach, eCARE has the potential to expand access to psychosocial support and facilitate timely identification of needs and coordination of services across cancer care settings.
International registered report identifier (irrid): DERR1-10.2196/83276.
Keywords: acoustic analysis; anxiety; artificial intelligence (AI); cancer; caregiving; depression; feasibility & acceptability study; mobile health (mHealth); psychological distress; semantic analysis; speech-based monitoring.
©Chiara Acquati, Michael Aratow, Tahmida Nazreen, Arunima Bhattacharjee, Isabella K Marra, Ashley S Alexander. Originally published in JMIR Research Protocols (https://www.researchprotocols.org), 12.02.2026.