Gait analysis for Parkinson's disease using multiscale entropy.

Area of Science:

• Neuroscience
• Biomedical Engineering
• Data Science

Background:

• Parkinson's disease (PD) presents complex gait abnormalities that traditional linear analysis methods struggle to capture.
• Understanding gait dynamics is crucial for early diagnosis and effective management of PD.

Purpose of the Study:

• To review the application of Multiscale Entropy (MSE) in assessing gait dynamics in Parkinson's disease.
• To highlight MSE's potential in distinguishing between healthy and pathological gait patterns.

Main Methods:

• Review of literature focusing on Multiscale Entropy (MSE) analysis of gait in Parkinson's disease.
• Integration of findings from studies utilizing wearable sensors, artificial intelligence (AI), and machine learning (ML).

Main Results:

• Multiscale Entropy (MSE) provides deeper insights into movement variability across multiple temporal scales, outperforming linear methods.
• MSE demonstrates efficacy in differentiating gait patterns associated with PD.
• Advances in wearable sensors and AI/ML enhance the clinical relevance of MSE for real-time, personalized gait assessments.

Conclusions:

• MSE is a promising tool for the objective assessment of gait in Parkinson's disease, aiding in early diagnosis and monitoring.
• Addressing challenges like computational demands and data requirements is key for broader clinical adoption.
• Further large-scale studies and standardized protocols are needed to establish a robust normative database for MSE in PD gait analysis.