Balancing Information Richness and Cognitive Load: A Scoping Review of Multimodal AI Systems for Older Adults in Home Environments
TL;DR
This scoping review maps current research on multimodal AI systems for older adults in home environments and proposes the Context-Adaptive Information Layering framework, which organizes information into Essential, Contextual, and Exploratory layers that adapt based on learned user patterns, task criticality, and cognitive state indicators.
Abstract
As the global population ages, older adults increasingly rely on AI-assisted systems to support independent living. However, current multimodal systems do not account for the wide range of cognitive abilities among older adults, often either overwhelming them with redundant information or over-automating decisions in ways that reduce autonomy. This scoping review maps current research on multimodal AI systems for older adults in home environments, focusing on balancing information richness with cognitive load. Following the PRISMA framework, we searched IEEE Xplore, ACM Digital Library, and Scopus, identifying 681 records, of which 5 studies met the inclusion criteria after screening. Our findings highlight four key design strategies: modality distribution based on information criticality, contextual automation to reduce query formulation burden, single-result confidence versus multi-option exploration, and context-dependent information delivery. Based on these insights, we propose the Context-Adaptive Information Layering framework, which organizes information into Essential, Contextual, and Exploratory layers that adapt based on learned user patterns, task criticality, and cognitive state indicators.