Machine learning based estimation of dynamic balance and gait adaptability in persons with neurological diseases using inertial sensors

Abstract

Poor dynamic balance and impaired gait adaptation to different contexts are hallmarks of people with neurological disorders (PwND), leading to difficulties in daily life and increased fall risk. Frequent assessment of dynamic balance and gait adaptability is therefore essential for monitoring the evolution of these impairments and/or the long-term effects of rehabilitation. The modified dynamic gait index (mDGI) is a validated clinical test specifically devoted to evaluating gait facets in clinical settings under a physiotherapist’s supervision. The need of a clinical environment, consequently, limits the number of assessments. Wearable sensors are increasingly used to measure balance and locomotion in real-world contexts and may permit an increase in monitoring frequency. This study aims to provide a preliminary test of this opportunity by using nested cross-validated machine learning regressors to predict the mDGI scores of 95 PwND via inertial signals collected from short steady-state walking bouts derived from the 6-minute walk test. Four different models were compared, one for each pathology (multiple sclerosis, Parkinson’s disease, and stroke) and one for the pooled multipathological cohort. Model explanations were computed on the best-performing solution; the model trained on the multipathological cohort yielded a median (interquartile range) absolute test error of 3.58 (5.38) points. In total, 76% of the predictions were within the mDGI’s minimal detectable change of 5 points. These results confirm that steady-state walking measurements provide information about dynamic balance and gait adaptability and can help clinicians identify important features to improve upon during rehabilitation. Future developments will include training of the method using short steady-state walking bouts in real-world settings, analysing the feasibility of this solution to intensify performance monitoring, providing prompt detection of worsening/improvements, and complementing clinical assessments.

Characterization of Walking in Mild Parkinson’s Disease: Reliability, Validity and Discriminant Ability of the Six-Minute Walk Test Instrumented with a Single Inertial Sensor

“…Unexpectedly, Lyapunov exponents (LyE) did not show significant correlations with any clinical evaluations, including balance measures (i.e., PIGD and TUG). This is in contrast with previous results on a group of people with PD, multiple sclerosis and stroke showing a significant association between increasing LyE Step AP and decreased balance as measured by the mDGI [ 70 ]. This can be due to the fact that our sample was composed of persons with PD who showed less severe walking impairment, as suggested by the 6MWT distance which was significantly higher (+156 m) compared to that characterizing the PD group tested by Liuzzi et al [ 70 ].…”

“…This is in contrast with previous results on a group of people with PD, multiple sclerosis and stroke showing a significant association between increasing LyE Step AP and decreased balance as measured by the mDGI [ 70 ]. This can be due to the fact that our sample was composed of persons with PD who showed less severe walking impairment, as suggested by the 6MWT distance which was significantly higher (+156 m) compared to that characterizing the PD group tested by Liuzzi et al [ 70 ]. Another possible explanation could be that, in the present study, LyE was computed over the duration of one step and stride.…”

Gait Analysis in Neurorehabilitation: From Research to Clinical Practice

“…They found that a type of neural network was the best to recognize neurological patients, based on EMG data, allowing a classification accuracy of 80 to 90%, even in small samples. Similarly, Liuzzi et al [71] provided an estimation using ML to detect important information on dynamic balance and gait adaptability in ND to aid clinicians to identify clinical features that need to be improved in the rehabilitation setting.…”

AI in Rehabilitation Medicine: Opportunities and Challenges

“…www.e-arm.org Similarly, sensor data during walking have been combined with clinical information to estimate dynamic balance ability in individuals with stroke, multiple sclerosis, and Parkinson's disease [36]. In the upper limb, IMUs have shown promise in assessing motor deficits in stroke and traumatic brain injury during the Wolf Motor Function Test [37], or evaluating tremor and bradykinesia for individuals with Parkinson's disease [38,39].…”