Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Jul 13, 2024
Date Accepted: Jan 31, 2025
A Sensorized Motor and Cognitive Dual-Task Framework for Dementia Diagnosis: Preliminary Insights from a Cross-Sectional Study
ABSTRACT
Background:
this study explores the utilization of novel Motor and Cognitive Dual-Task (MCDT) approaches, based on Upper Limb Motor Function (ULMF) and Lower Limb Motor Function (LLMF), for discerning subjects with Mild Cognitive Impairment (MCI) and Subjective Cognitive Impairment (SCI) in comparison to Cognitively Normal Adults (CNA).
Objective:
the study objectives encompass: 1) the exploration of alternatives to the traditional walking MCDT; 2) The examination of various ULMF and LLMF MCDT modalities, incorporating different exercises with varying motor difficulties and eventually, 3) the assessment of CNA in comparison with MCI and SCI to acquire more nuanced insights into different stages of the diseases.
Methods:
the upper and lower limbs motor performances of 44 older adults were evaluated using a wearable inertial system during five MCDTs, comprising two ULMF tasks: fore-finger tapping (FTAP) and thumb-index tapping (THFF), and two LLMF tasks: toe-tapping heel pin (TTHP) and heel-tapping toe pin (HTTP). The gold standard for MCDT, 10-meter walking (GAIT), was included. Five pooled indices (PIs) based on MCDTs, demographic data and clinical scores, were incorporated into logistic regression models.
Results:
In 2-class classification models (MCI vs CNA), HTTP showed the highest accuracy at 93%; TTHP and TTHF models reached 89% accuracy; FTAP and GAIT achieved 85% accuracy in distinguishing between the two groups of subjects. In 3-class classification models (MCI vs SCI vs CNA), transitioning from FTAP to THFF improved subject characterization by +5%. TTHP outperformed HTTP by +9%. Furthermore, models effectively identify individuals with MCI, with HTTP achieving a 76% recall and TTHP achieving 88%.
Conclusions:
this study emphasizes the potential of an integrated sensorized MCDT framework, which combines a broader theoretical foundation and task selection with neuropsychological and behavioral data. This approach can enhance our understanding of dementia and provide clinicians with valuable diagnostic tools. While these tasks demonstrate ease and efficiency, validation in subsequent clinical studies is necessary.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.