Deep Neural Network for Stroke Patient Gait Analysis and Classification

NCT04968418 | Unknown

• 1 other identifier: (870)110-16
• Study Type: observational
• Target: 100
• Locations: 1 country
• Sites: 1

Brief Summary

Lower limbs of stroke patients gradually recover through Brunnstrom stages, from initial flaccid status to gradually increased spasticity, and eventually decreased spasticitiy. Throughout this process. after stroke patients can start walking, their gait will show abnormal gait patterns from healthy subjects, including circumduction gait, drop foot, hip hiking and genu recurvatum. For these abnormal gait patterns, rehabilitation methods include ankle-knee orthosis(AFO) or increasing knee/pelvic joint mobility for assistance. Prior to this study, similar research has been done to differentiate stroke gait patterns from normal gait patterns, with an accuracy of over 96%. This study recruits subject who has encountered first ever cerebrovascular incident and can currently walk independently on flat surface without assistance, and investigators record gait information via inertial measurement units strapped to their bilateral ankle, wrist and pelvis to detect acceleration and angular velocity as well as other gait parameters. The IMU used in this study consists of a 3-axis accelerometer, 3-axis gyroscope and 3-axis magnetometer, with a highest sampling rate of 128Hz. Afterwards, investigators use these gait information collected as training data and testing data for a deep neural network (DNN) model and compare clinical observation results by physicians simultaneously, in order to determine whether the DNN model is able to differentiate the types of abnormal gait patterns mentioned above. If this model is applied in the community, investigators hope it is available to early detect abnormal gait patterns and perform early intervention to decrease possibility of fallen injuries. This is a non-invasive observational study and doesn't involve medicine use. Participants are only required to perform walking for 6 minutes without assistance on a flat surface. This risk is extremely low and the only possible risk of this study is falling down during walking.

Conditions

Gait Disorders, Neurologic; Artificial Intelligence

Outcome Measures

Primary Outcomes (1)

• Deep neural network (DNN) model accuracy of detecting abnormal stroke gait patterns

  Investigators compare clinically observed abnormal gait patterns with DNN model detection. Accuracy of the DNN model will be compared to clinical observed data after cross validation, which results in a series of labeling. Investigators compare those labels with actual observed clinical abnormal gait patterns to determine whether DNN is available of identifying abnormal stroke gait patterns accurately.

  2 years

Interventions

APDM OPAL system wearable IMU DEVICE

The OPAL system contains wearable IMUs with a sampling rate of 128 Hz and a resolution of 17.5 bits. Each IMU has a size of about 44mm 40mm 14mm × × and weighs less than 25 gm.

Eligibility Criteria

• Age: 20 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Investigators focus on unilateral stroke patient over 20 years old who visit Cheng Hsin General Hospital outpatient clinic on a regular basis.

You may qualify if:

• Age over 20 years old with first time stroke
• And affected lower limb Brunnstrom stage III-V
• Functional ambulation category VI
• Participants should be able to walk on flat surface without assistance for 6 minutes
• Mini-Mental State Examination (MMSE) should be over 25 and can comply to orders and cooperate with our study

You may not qualify if:

• Severe central nervous system(CNS)/peripheral nervous system(PNS)neurological disorders apart from stroke
• Patients with high risk of falling down during walking
• Patients who cannot cooperate with testing
• Patients with severe visual/auditory/cognition deficits
• Patients with lower limb fracture within recent 6 months

Sponsors & Collaborators

• Cheng-Hsin General Hospital: lead
• National Taiwan University: collaborator

Study Sites (1)

Cheng Hsin General Hospital

Taipei, 112401, Taiwan

Location

Related Publications (3)

• Kerrigan DC, Frates EP, Rogan S, Riley PO. Hip hiking and circumduction: quantitative definitions. Am J Phys Med Rehabil. 2000 May-Jun;79(3):247-52. doi: 10.1097/00002060-200005000-00006.

  PMID: 10821310 BACKGROUND

• Trojaniello D, Cereatti A, Pelosin E, Avanzino L, Mirelman A, Hausdorff JM, Della Croce U. Estimation of step-by-step spatio-temporal parameters of normal and impaired gait using shank-mounted magneto-inertial sensors: application to elderly, hemiparetic, parkinsonian and choreic gait. J Neuroeng Rehabil. 2014 Nov 11;11:152. doi: 10.1186/1743-0003-11-152.

  PMID: 25388296 BACKGROUND

• Abaid N, Cappa P, Palermo E, Petrarca M, Porfiri M. Gait detection in children with and without hemiplegia using single-axis wearable gyroscopes. PLoS One. 2013 Sep 4;8(9):e73152. doi: 10.1371/journal.pone.0073152. eCollection 2013.

  PMID: 24023825 BACKGROUND

MeSH Terms

Conditions

Gait Disorders, Neurologic

Condition Hierarchy (Ancestors)

Neurologic Manifestations; Nervous System Diseases; Signs and Symptoms; Pathological Conditions, Signs and Symptoms

Study Officials

• Szu-Fu Chen, MD, PHD

  Szu-Fu Chen

  STUDY DIRECTOR

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: CROSS SECTIONAL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: July 8, 2021
• First Posted: July 20, 2021
• Study Start: July 20, 2021
• Primary Completion: May 1, 2023
• Study Completion: May 31, 2023
• Last Updated: March 9, 2022

Record last verified: 2022-03

Data Sharing

• IPD Sharing: Will not share

Locations

TW (1)