JMIR Publications

ABSTRACT

Background:

Alzheimer disease and age-related cognitive decline reduce memory engagement and limit caregiver insight, creating a need for accessible tools that support everyday cognitive activity in older adults. Although artificial intelligence (AI) holds promise for personalized cognitive support, few AI-based applications have been developed and evaluated for memory engagement in this population, and fewer incorporate on-device emotional analysis with privacy-preserving design.

Objective:

This study developed and evaluated RecallLive, an AI-assisted mobile application supporting structured memory interaction for older adults, examining its acceptability, engagement, perceived usefulness, and behavioral intention, guided by the Technology Acceptance Model.

Methods:

RecallLive integrates metadata-based photo clustering to generate memory videos, an on-device convolutional neural network that classifies frame-level emotional responses, and an LLM-based module that converts these outputs into caregiver summaries. A sequential two-phase mixed methods design was used. In Phase 1, 202 US adults aged ≥65 years viewed a structured demonstration and completed a survey measuring ease of use, engagement, design clarity, perceived usefulness, and intention to use. In Phase 2, 10 participants completed a hands-on session followed by semi-structured interviews analyzed thematically. Quantitative analyses [insert statistical software and version] included internal consistency estimates, one-sample t tests against the scale midpoint, and linear regression.

Results:

All scales showed strong reliability (Cronbach α=.86-.92). Engagement (mean 4.09, SD 0.67) and perceived usefulness (mean 4.05) were rated highly, and both significantly exceeded the scale midpoint (t=14.00 and t=23.19; both P<.001). Perceived usefulness strongly predicted intention to use or recommend the application (β=.796; R²=0.634; F1,200=346.18; P<.001). Phase 2 corroborated these results, showing clear navigation and interpretable feedback; initial concerns about front-facing camera use resolved once the on-device, no-image-storage design was explained.

Conclusions:

RecallLive was perceived as usable, engaging, and useful, with perceived usefulness the primary driver of adoption intention. Emotional relevance, not efficiency alone, shaped engagement, and on-device processing addressed privacy concerns. Limitations include the video-based Phase 1 evaluation, short interaction period, and small Phase 2 sample; longitudinal and clinical-integration studies are needed.