On this page

Study design

This staged study recruited 108 adults aged 50 or older from five long-term-care facilities. An AI food scanner estimated intake for four weeks; researchers then classified participants by nutrient adequacy before providing four weeks of tailored food support. This was not a randomized test of AI software against usual care.

Findings

Energy intake rose in all three nutrient-adequacy groups. Nutritional status and cognitive measures improved mainly in the severely inadequate group, while EEG changes were reported across groups. Support could include nut mixes, senior-friendly meat products or oral nutrition products. Because the software was used to guide food support, the design cannot isolate the software’s contribution.

Limitations and disclosures

The intervention was short and nonrandomized, and the abstract gives no cognitive effect sizes. The findings may not generalize beyond long-term-care residents. Several authors were affiliated with Nuvilab or iMediSync; public grants were listed. The results support further study of nutrition screening and targeted food support, not a claim that AI itself improves cognition.

This sourced news summary and translation were prepared with AI assistance. Source links, the news date and research limitations are disclosed; this is not a claim of independent medical expert review. News production method.

Sources

Research news is not medical advice or a recommendation to use a substance. Read findings in the context of the study design, participants and limitations. Editorial standards.

← All news