# Automated Shoulder Girdle Rigidity Assessment in Parkinson’s Disease via an Integrated Model- and Data-Driven Approach

## TL;DR

A new method combining biomechanical and data-driven features from wearable sensors accurately assesses shoulder rigidity in Parkinson’s disease, enabling remote monitoring and earlier diagnosis.

## Contribution

A hybrid model-data-driven framework with weak supervision improves rigidity assessment accuracy and introduces interpretable biomarkers for Parkinson’s disease.

## Key findings

- The hybrid framework achieved a strong correlation (r = 0.78) with UPDRS rigidity scores.
- Classification accuracy improved by 10% over data-driven methods using damping ratio and maximum detail coefficient as key biomarkers.
- The model challenges the assumption that rigidity is velocity-independent by showing velocity-dependent features are predictive.

## Abstract

What are the main findings?
A hybrid framework integrating model-driven (damping ratio, decay rate) and data-driven (maximum detail coefficient) features via weak supervision achieved a strong correlation (r = 0.78, p < 0.001) with UPDRS rigidity scores, outperforming traditional Wartenberg pendulum test metrics like maximum velocity.The integrated model improved PD/HC classification accuracy by 10% over data-driven methods, with damping ratio and maximum detail coefficient identified as highly predictive biomarkers.

A hybrid framework integrating model-driven (damping ratio, decay rate) and data-driven (maximum detail coefficient) features via weak supervision achieved a strong correlation (r = 0.78, p < 0.001) with UPDRS rigidity scores, outperforming traditional Wartenberg pendulum test metrics like maximum velocity.

The integrated model improved PD/HC classification accuracy by 10% over data-driven methods, with damping ratio and maximum detail coefficient identified as highly predictive biomarkers.

What is the implication of the main finding?
Combining biomechanical and statistical features through weak supervision enables objective, interpretable shoulder rigidity assessment in Parkinson’s Disease. The results suggest that rigidity, generally considered velocity-independent, can be inferred by velocity-dependent features like the damping ratio.Because rigidity assessment typically requires in-person, hands-on examination, wearable sensors in the current framework enable scalable, remote monitoring that facilitates earlier diagnosis and ongoing longitudinal tracking within telemedicine settings.

Combining biomechanical and statistical features through weak supervision enables objective, interpretable shoulder rigidity assessment in Parkinson’s Disease. The results suggest that rigidity, generally considered velocity-independent, can be inferred by velocity-dependent features like the damping ratio.

Because rigidity assessment typically requires in-person, hands-on examination, wearable sensors in the current framework enable scalable, remote monitoring that facilitates earlier diagnosis and ongoing longitudinal tracking within telemedicine settings.

Parkinson’s disease (PD) is characterized by motor symptoms, with key diagnostic features, such as rigidity, traditionally assessed through subjective clinical scales. This study proposes a novel hybrid framework integrating model-driven biomechanical features (damping ratio, decay rate) and data-driven statistical features (maximum detail coefficient) from wearable sensor data during a modified pendulum test to quantify shoulder girdle rigidity objectively. Using weak supervision, these features were unified to generate robust labels from limited data, achieving a 10% improvement in PD/healthy control classification accuracy (0.71 vs. 0.64) over data-driven methods and matching model-driven performance (0.70). The damping ratio and decay rate, aligning with Wartenberg pendulum test metrics like relaxation index, revealed velocity-dependent aspects of rigidity, challenging its clinical characterization as velocity-independent. Outputs correlated strongly with UPDRS rigidity scores (r = 0.78, p < 0.001), validating their clinical utility as novel biomechanical biomarkers. This framework enhances interpretability and scalability, enabling remote, objective rigidity assessment for early diagnosis and telemedicine, advancing PD management through innovative sensor-based neurotechnology.