Mild cognitive impairment identification based on motor and cognitive dual-task pooled indices

Area of Science:

• Neuroscience
• Gerontology
• Biomedical Engineering

Background:

• Mild cognitive impairment (MCI) and subjective cognitive impairment (SCI) are precursors to dementia.
• Early identification is crucial for timely intervention and management.
• Current diagnostic methods can be limited in sensitivity.

Purpose of the Study:

• To investigate the efficacy of motor and cognitive dual-task (MCDT) approaches in differentiating between cognitively normal adults (CNA), individuals with SCI, and those with MCI.
• To assess the contribution of motor performance indices (PIs) derived from MCDTs, demographic data (age), and clinical scores (Frontal Assessment Battery - FAB) in diagnostic models.

Main Methods:

• 44 older adults underwent assessments using the SensHand and SensFoot wearable systems during three MCDTs: forefinger tapping (FTAP), toe-tapping heel pin (TTHP), and 10 m walking (GAIT).
• Five pooled indices (PIs) were developed from MCDT data.
• Logistic regression models were constructed incorporating PIs, age, and FAB scores to classify participants into CNA, SCI, or MCI groups.

Main Results:

• Models distinguishing between CNA and MCI achieved accuracies of 67-78% with PIs and age alone, increasing to 85-89% with the addition of clinical scores.
• For classifying CNA, SCI, and MCI, models using PIs and age yielded 50-59% accuracy, which improved by 18% when FAB scores were included.
• The TTHP PI demonstrated particularly high performance in differentiating among the three groups.

Conclusions:

• MCDT-derived PIs combined with age are effective for distinguishing between CNA and MCI.
• Incorporating clinical scores significantly enhances the accuracy of these diagnostic models.
• The TTHP PI shows promise for differentiating between CNA, SCI, and MCI, suggesting MCDTs offer valuable tools for clinical assessment.