A virtual reality test was linked to standard cognitive scores in older adults

In a preliminary study, performance on Cogniclear was associated with results from the Montreal Cognitive Assessment.

Editorial illustration — not from the study.

Researchers evaluated Cogniclear, a virtual reality assessment environment, against the Montreal Cognitive Assessment, a standard cognitive screening test. Forty older adults took part, and 38 completed both assessments and were included in the analysis.

Several measures recorded by the virtual reality system were associated with Montreal Cognitive Assessment scores, including its overall score, success rate and task duration. The researchers also found that cognitive status and age were independently associated with the system’s overall score after accounting for participant characteristics.

What the VR test measured

Cogniclear performance was associated with scores on the Montreal Cognitive Assessment. The associations included the system’s Global Score, Success Rate and task duration. Analyses of individual cognitive domains found moderate-to-strong correlations between corresponding domains measured by the two systems. In regression analyses, cognitive status and age remained independently associated with the virtual reality system’s Global Score. Prior virtual reality experience, workload and usability were not independently associated with that score.

Why the link matters

The findings suggest that an immersive virtual reality assessment can capture aspects of cognitive functioning that relate to an established screening measure. Because the system records behavior during tasks, it may complement traditional cognitive screening with information about how people interact with the assessment, rather than relying only on a final test score. The study does not establish that Cogniclear can replace existing screening tools.

Evidence and limits

This was a preliminary validation study based on associations between a virtual reality assessment and the Montreal Cognitive Assessment. Forty older adults were recruited, but only 38 completed both assessments and were included in the analysis. The results support a relationship between the measures, but they do not by themselves establish diagnostic accuracy or show how well the tool would perform in larger or different groups. The abstract does not report a clinical diagnosis comparison or follow-up over time.

Face-recognition AI can score well overall while treating groups unevenly

A study of three widely used image models found that high overall performance in facial representation tasks could coexist with uneven results across demographic groups. The researchers argue that race–gender intersectional testing is needed alongside average accuracy.

1 hour ago

AI & Computing

AI scores for grant proposals were less reliable than expert reviews

Researchers compared scores from several large language models with expert ratings of 142 Swedish medical fellowship applications. The AI scores showed weaker agreement with expert judgments than the reviewers showed with one another, although the systems could still have a limited role in sorting applications.

21 hours ago·8 views

AI & Computing

High-mounted cameras spot pedestrians on the device at busy intersections

Researchers introduced a 13,314-image dataset for testing AI systems that view urban intersections from above. The results show that detection can run on edge devices such as the Jetson Orin Nano, although pedestrians remain harder to detect than vehicles and performance changes with scene conditions.

1 day ago·10 views