Does fear of falling predict gait variability in multiple sclerosis?

Using machine learning algorithms to detect fear of falling in people with multiple sclerosis in standardized gait analysis

INTRODUCTION

Multiple sclerosis (MS) is the most common chronic inflammatory disease of the central nervous system. The progressive impairment of gait is one of the most important pathognomic symptoms which are associated with falls and fear of falling (FOF) in people with MS (pwMS). 60 % of pwMS show a FOF, which leads to restrictions in mobility as well as physical activity and reduces the quality of life in general. Therefore, early detection of FOF is crucial because it enables early implementation of rehabilitation strategies as well as clinical decision-making to reduce progression. Qualitative and quantitative evaluation of gait pattern is an essential aspect of disease assessment and can provide valuable insights for personalized treatment decisions in pwMS. Our objective was to identify the most appropriate clinical gait analysis methods to identify FOF in pwMS and to detect the optimal machine learning (ML) algorithms to predict FOF using the complex multidimensional data from gait analysis.

METHODS

Data of 1240 pwMS was recorded at the MS Centre of the University Hospital Dresden between November 2020 and September 2021. Patients performed a multidimensional gait analysis with pressure and motion sensors, as well as patient-reported outcomes (PROs), according to a standardized protocol. A feature selection ensemble (FS-Ensemble) was developed to improve the classification performance. The FS-Ensemble consisted of four filtering methods: Chi-square test, information gain, minimum redundancy maximum relevance and ReliefF. Gaussian Naive Bayes, Decision Tree, k-Nearest Neighbor, and Support Vector Machines (SVM) were used to identify FOF.

RESULTS

The descriptive analysis showed that 37 % of the 1240 pwMS had a FOF (n = 458; age: 51 ± 16 years, 76 % women, median EDSS: 4.0). The FS-Ensemble improved classification performance in most cases. The SVM showed the best performance of the four classification models in detecting FOF. The PROs showed the best F1 scores (Early Mobility Impairment Questionnaire F1 = 0.81 ± 0.00 and 12-item Multiple Sclerosis Scale F1 = 0.80 ± 0.00).

CONCLUSION

FOF is an important psychological risk factor associated with an increased risk of falls. To integrate a functional early warning system for fall detection into MS management and progression monitoring, it is necessary to detect the relevant gait parameters as well as assessment methods. In this context, ML strategies allow the integration of gait parameters from clinical routine to support the initiation of early rehabilitation measures and adaptation of course-modifying therapeutics. The results of this study confirm that patients' self-assessments play an important role in disease management.

Fear of falling and common symptoms of multiple sclerosis: Physical function, cognition, fatigue, depression, and sleep - A systematic review

BACKGROUND

Fear of falling (FOF) is a common concern among persons with multiple sclerosis (MS) and affects the performance of their daily living activities. Falls may result in FOF, leading to worsening of symptoms of MS, physical deconditioning, and exposure to future falls. This may trigger a vicious cycle between FOF and falls. A better understanding of the relationship between FOF and symptoms of MS may be helpful to develop a conceptual model to guide fall prevention interventions.

OBJECTIVE

To synthesize the correlational and predictive relationships between FOF and common symptoms of MS.

METHODS

Databases including PubMed, Embase, Web of Science, Scopus, CINHAL, PsycINFO, and SPORTDiscuss were searched from inception to October 2023. Studies examining correlations and/or predictions between FOF and common MS symptoms that include measures of gait, postural control, fatigue, cognition, pain, sleep, depression, and anxiety were identified by two independent reviewers. Both reviewers also conducted the methodological quality assessment of the included studies.

RESULTS

Twenty-three studies with a total of 2819 participants were included in the review. Correlational findings indicated that increased FOF was significantly associated with greater walking deficits (lower gait speed, smaller steps), reduced mobility, and poorer balance. Increased FOF was also significantly correlated with higher cognitive impairments, more fatigue, sleep disturbances, and depression. Decreased gait parameters, reduced balance, lower physical functions, cognitive impairments, and sleep deficits were found as significant predictors of increased FOF.

CONCLUSION

Evidence indicates significant correlational and bidirectional predictive relationships exist between FOF and common MS symptoms. A comprehensive conceptual framework accounting for the interaction between FOF and MS symptoms is needed to develop effective falls prevention strategies.

Quantifying lower extremity inter-segmental coordination variability during walking in people with multiple sclerosis with high and low fear of falling

BACKGROUND

Fear of falling (FOF) is associated with gait disturbances in people with multiple sclerosis (PwMS). However, previous studies mostly assessed FOF-related changes in gait patterns of PwMS using spatio-temporal gait parameters. Considering the complex nature of gait control, investigation of the higher order properties of the human movement system, particularly inter-segmental coordination variability may provide valuable information about underlying deficits in motor control patterns in PwMS with different levels of FOF. Therefore, the purpose of this study was to clarify the differences in lower extremity inter-segmental coordination variability between healthy controls and PwMS with high and low FOF.

METHODS

This cross-sectional study examined gait patterns of 40 PwMS and 20 age-and-sex-matched healthy controls during treadmill walking at a preferred walking speed for 3 min. The falls efficacy scale-international questionnaire was used to stratify PwMS into high and low FOF subgroups. Variability in coordinative relationships between shank-thigh and foot-shank segments was determined using deviation phase (DP), which is the average standard deviation calculated from all points of the ensemble continuous relative phase (CRP) curve during the stance and swing phases of gait.

RESULTS

DP values for shank-thigh (p = 0.005 and p < 0.001, respectively) and foot-shank inter-segmental relationships (p < 0.001) during the stance phase as well as for foot-shank inter-segmental relationships during the swing phase (p = 0.03) were significantly greater in PwMS with high FOF compared to those with low FOF and healthy controls. In addition, both groups of PwMS with high and low FOF indicated greater shank-thigh DP values compared to healthy controls during the swing phase (p < 0.001 and p = 0.002, respectively).

CONCLUSION

The findings suggest unsteadiness in neuromuscular organization during walking in PwMS with high FOF. Rehabilitative interventions targeting impairments in lower extremity inter-segmental coordination and FOF may be useful to improve walking and reduce risk of falls in PwMS with high FOF.

Bridging the callosal gap in gait: corpus callosum white matter integrity's role in lower limb coordination

Bilateral coordination of the lower extremities is an essential component of mobility. The corpus callosum bridges the two hemispheres of the brain and is integral for the coordination of such complex movements. The aim of this project was to assess structural integrity of the transcallosal sensorimotor fiber tracts and identify their associations with gait coordination using novel methods of ecologically valid mobility assessments in persons with multiple sclerosis and age-/gender-matched neurotypical adults. Neurotypical adults (n = 29) and persons with multiple sclerosis (n = 27) underwent gait and diffusion tensor imaging assessments; the lower limb coordination via Phase Coordination Index, and radial diffusivity, an indirect marker of myelination, were applied as the primary outcome measures. Persons with multiple sclerosis possessed poorer transcallosal white matter microstructural integrity of sensorimotor fiber tracts compared to the neurotypical adults. Further, persons with multiple sclerosis demonstrated significantly poorer bilateral coordination of the lower limbs during over-ground walking in comparison to an age and gender-matched neurotypical cohort. Finally, bilateral coordination of the lower limbs was significantly associated with white matter microstructural integrity of the dorsal premotor and primary motor fiber bundles in persons with multiple sclerosis, but not in neurotypical adults. This analysis revealed that persons with multiple sclerosis exhibit poorer transcallosal microstructural integrity than neurotypical peers. Furthermore, these structural deficits were correlated to poorer consistency and accuracy of gait in those with multiple sclerosis. Together, these results, emphasize the importance of transcallosal communication for gait coordination in those with multiple sclerosis.

The application of principal component analysis to characterize gait and its association with falls in multiple sclerosis

People with multiple sclerosis (PwMS) demonstrate gait impairments that are related to falls. However, redundancy exists when reporting gait outcomes. This study aimed to develop an MS-specific model of gait and examine differences between fallers and non-fallers. 122 people with relapsing-remitting MS and 45 controls performed 3 timed up-and-go trials wearing inertial sensors. 21 gait parameters were entered into a principal component analysis (PCA). The PCA-derived gait domains were compared between MS fallers (MS-F) and MS non-fallers (MS-NF) and correlated to cognitive, clinical, and quality-of-life outcomes. Six distinct gait domains were identified: pace, rhythm, variability, asymmetry, anterior-posterior dynamic stability, and medial-lateral dynamic stability, explaining 79.15% of gait variance. PwMS exhibited a slower pace, larger variability, and increased medial-lateral trunk motion compared to controls (p < 0.05). The pace and asymmetry domains were significantly worse (i.e., slower and asymmetrical) in MS-F than MS-NF (p < 0.001 and p = 0.03, respectively). Fear of falling, cognitive performance, and functional mobility were associated with a slower gait (p < 0.05). This study identified a six-component, MS-specific gait model, demonstrating that PwMS, particularly fallers, exhibit deficits in pace and asymmetry. Findings may help reduce redundancy when reporting gait outcomes and inform interventions targeting specific gait domains.

Fear of falling and falls in people with multiple sclerosis: A literature review

INTRODUCTION

Fear of falling (FOF) is a widespread problem affecting about 60% of people with multiple sclerosis (pwMS). Inflammatory lesions in the brain that are caused by the disease result in gait deficits and increase the risk of fall. Falls induce fear of falling and trigger a vicious circle, which in turn increases the likelihood of falling. Objective of this review was to provide an overview of existing research on the effects of FOF and therapy options in multiple sclerosis.

METHODS

A systematic search at Web of Science and PubMed was conducted. The search included the terms (fear of falling) OR (concern about falling) OR (fall anxiety) AND (multiple sclerosis).

RESULTS

In included studies, FOF was measured by different instruments. The Falls Efficacy Scale-International (FES-I) was the most frequently used instrument for pwMS. Patients with a higher FOF score fell more frequently, had lower walking speed, shorter stride length, larger ellipse sway area and a more severe disability. At present, therapeutic offers exist mainly in the field of physiotherapy. For reducing FOF, assisted vibration (d_z = 0.68), VR (d_z =0.87) and bicycle training (d_z = 1.23) were the most effective methods.

CONCLUSION

It is advisable to develop therapies that incorporate both physical and psychological aspects in neurorehabilitation, like in a cognitive behavioral therapy. Moreover, FOF monitoring should be integrated into the clinical routine.

The relationship between gait variability and cognitive functions differs between fallers and non-fallers in MS

The objective of the study was to determine if cognitive function is associated with step time variability in people with multiple sclerosis (PwMS). The study included 355 PwMS (218 women), average age 41.1 (SD = 13.5), disease duration 5.9 (SD = 7.3) years, and a median expanded disability status scale score of 2.5. We separately analyzed the sample group of fallers and non-fallers based on their fall history. Gait variability was measured by an electronic walkway and all participants completed a computerized cognitive test battery designed to evaluate multiple cognitive domains. Fallers (43.7%) demonstrated elevated step time variability (%CV), 5.0 (SD = 3.4) vs. 3.5 (SD = 1.6), P < 0.001 compared to the non-faller subjects. According to the regression analysis in the non-fallers' group, step time variability was found significantly associated with the global cognitive score (P = 0.001), executive function subcategory (P = 0.038), and motor skills subcategory (P < 0.001). No relationship between step time variability and any cognitive domain was demonstrated in the faller group. This study illustrated that the association between gait variability and cognition occurs only in PwMS without a fall history. From a clinical standpoint, these findings might help medical professionals to create improved assessment tests and rehabilitation strategies in the MS population.