Objectively quantifying walking ability in degenerative spinal disorder patients using sensor equipped smart shoes.

Area of Science:

• Biomedical Engineering
• Rehabilitation Medicine
• Computational Science

Background:

• Lumbar spinal stenosis (LSS) is a prevalent degenerative condition affecting the elderly, necessitating improved functional outcome assessment.
• Current methods for evaluating LSS patient function are often subjective or costly.
• There is a critical need for accurate, objective, and inexpensive tools to monitor functional status in LSS patients.

Purpose of the Study:

• To develop and validate a machine learning model for quantifying functional levels in LSS patients.
• To assess the utility of sensorized shoe data and clinical information in estimating functional outcomes.
• To establish a reliable method for monitoring LSS patient function in clinical and remote settings.

Main Methods:

• Utilized machine learning algorithms to analyze data from a 10m self-paced walking test using sensorized shoes.
• Collected data from 29 patients diagnosed with Lumbar Spinal Stenosis.
• Estimated the Oswestry Disability Index (ODI) using patient's gait parameters and clinical data.

Main Results:

• Machine learning models accurately estimated patient-reported Oswestry Disability Index scores (r=0.81, p<3.5×10(-11)).
• Gait data from sensorized shoes were the primary contributors to the accurate ODI estimations.
• Clinical information provided minimal contribution to the predictive accuracy of the model.

Conclusions:

• Sensorized shoes combined with machine learning offer a promising, objective method for assessing LSS functional status.
• This approach can facilitate continuous patient monitoring in diverse healthcare environments.
• Future research can leverage this technology for personalized rehabilitation and treatment strategies for LSS.