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

Hemodynamics of the Frontopolar and Dorsolateral Pre-Frontal Cortex in People with Multiple Sclerosis During Walking, Cognitive Subtraction, and Cognitive-Motor Dual-Task

INTRODUCTION

Higher cortical activity has been observed in people with multiple sclerosis (pwMS) during walking and dual-tasking. However, further studies in overground walking and considering pre-frontal cortex (PFC) sub-areas are necessary.

OBJECTIVES

To investigate PFC activity during a cognitive-motor dual-task (DT) and its single component tasks, in combination with behavioral outcomes in pwMS.

METHODS

Fifteen pwMS (EDSS 3.5 [2-5.5], 42 ± 11 years) and 16 healthy controls (HC, 45.2 ± 13.2 years) performed 3 conditions: single motor-walking (SWT), single cognitive - subtracting sevens (SCT), and a DT. Meters walked and the number of correct answers were obtained from which, respectively, the motor (mDTC) and cognitive (cDTC) DT costs were calculated. A functional Near-Infrared Spectroscopy covering the frontopolar and dorsolateral PFC (DLPFC) areas was used to concentration of relative oxyhemoglobin (ΔHbO2) and deoxyhemoglobin (ΔHHb) in the PFC. A repeated 2-way ANOVA (group × conditions) was used to compare ΔHbO2/ΔHHb and behavioral outcomes.

RESULTS

PwMS walked shorter distances (P < .002) and answered fewer correct numbers (P < .03) than HC in all conditions, while cDTC and mDTC were similar between groups. PwMS presented higher ΔHbO2 in the frontopolar area than HC in the SWT (P < .001). HC increased ΔHbO2 in frontopolar during the SCT (P < .029) and DT (P < .037) compared with the SWT.

CONCLUSION

Higher frontopolar activity in pwMS compared to HC in the SWT suggests reduced gait automaticity. Furthermore, it seems that only HC increased neural activity in the frontopolar in the SCT and DT, which might suggest a limit of cognitive resources to respond to DT in pwMS.

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.

Motion acquisition of gait characteristics one week after total hip arthroplasty: a factor analysis

INTRODUCTION

Clinical gait analysis can be used to evaluate the recovery process of patients undergoing total hip arthroplasty (THA). The postoperative walking patterns of these patients can be significantly influenced by the choice of surgical approach, as each procedure alters distinct anatomical structures. The aim of this study is twofold. The first objective is to develop a gait model to describe the change in ambulation one week after THA. The secondary goal is to describe the differences associated with the surgical approach.

MATERIALS AND METHODS

Thirty-six patients undergoing THA with lateral (n = 9), anterior (n = 15), and posterior (n = 12) approaches were included in the study. Walking before and 7 days after surgery was recorded using a markerless motion capture system. Exploratory Factor Analysis (EFA), a data reduction technique, condensed 21 spatiotemporal gait parameters to a smaller set of dominant variables. The EFA-derived gait domains were utilized to study post-surgical gait variations and to compare the post-surgical gait among the three groups.

RESULTS

Four distinct gait domains were identified. The most pronounced variation one week after surgery is in the Rhythm (gait cycle time: + 32.9 % ), followed by Postural control (step width: + 27.0 % ), Phases (stance time: + 11.0 % ), and Pace (stride length: -  9.3 % ). In postsurgical walking, Phases is statistically significantly different in patients operated with the posterior approach compared to lateral (p-value = 0.017) and anterior (p-value = 0.002) approaches. Furthermore, stance time in the posterior approach group is significantly lower than in healthy individuals (p-value < 0.001).

CONCLUSIONS

This study identified a four-component gait model specific to THA patients. The results showed that patients after THA have longer stride time but shorter stride length, wider base of support, and longer stance time, although the posterior group had a statistically significant shorter stance time than the others. The findings of this research have the potential to simplify the reporting of gait outcomes, reduce redundancy, and inform targeted interventions in regards to specific gait domains.

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.

Between-Day Reliability of the Gait Characteristics and Their Changes During the 6-Minute Walking Test in People With Multiple Sclerosis

BACKGROUND

Gait characteristics and their changes during the 6-minute walking test (6MWT) in people with multiple sclerosis (pwMS) have been described in the literature, which one may refer to as walking fatigability in the body function level of the International Classification of Functioning, Disability, and Health. However, whether these metrics are reliable is unknown.

OBJECTIVE

To investigate the between-day reliability of the gait characteristics and their changes in pwMS and healthy controls (HCs).

METHODS

Forty-nine pwMS (EDSS 4.82 ± 1.22 and 54.7 ± 9.36 years) and 23 HCs (50.6 ± 6.1 years) performed the 6MWT, as fast as possible but safely while wearing Inertial Measurement Units. Gait characteristics were measured in the pace, rhythm, variability, asymmetry, kinematics, coordination, and postural control domains and were obtained in intervals of 1 minute during the 6MWT. In addition, gait characteristics change in the last minute compared with the first minute were calculated for all gait variables using a fatigability index (ie, distance walking index). The intraclass correlation coefficient (ICC), Bland-Altman Plots, and Standard error of measurement were applied to investigate reliability.

RESULTS

Reliability of gait characteristics, minute-by-minute, and for their changes (ie, using the fatigability index) ranged from poor to excellent (pwMS: ICC 0.46-0.96; HC: ICC 0.09-0.97 and pwMS: ICC 0-0.72; HC: ICC 0-0.77, respectively).

CONCLUSION

Besides coordination, at least 1 variable of each gait domain showed an ICC of moderate or good reliability for gait characteristics changes in both pwMS and HC. These metrics can be incorporated into future clinical trials and research on walking fatigability.Clinical Trial Registration: NCT05412043.

Innovations in Multiple Sclerosis Care: The Impact of Artificial Intelligence via Machine Learning on Clinical Research and Decision-Making

Artificial intelligence (AI) and its specialized subcomponent machine learning are becoming increasingly popular analytic techniques. With this growth, clinicians and health care professionals should soon expect to see an increase in diagnostic, therapeutic, and rehabilitative technologies and processes that use elements of AI. The purpose of this review is twofold. First, we provide foundational knowledge that will help health care professionals understand these modern algorithmic techniques and their implementation for classification and clustering tasks. The phrases artificial intelligence and machine learning are defined and distinguished, as are the metrics by which they are assessed and delineated. Subsequently, 7 broad categories of algorithms are discussed, and their uses explained. Second, this review highlights several key studies that exemplify advances in diagnosis, treatment, and rehabilitation for individuals with multiple sclerosis using a variety of data sources-from wearable sensors to questionnaires and serology-and elements of AI. This review will help health care professionals and clinicians better understand AI-dependent diagnostic, therapeutic, and rehabilitative techniques, thereby facilitating a greater quality of care.

Using the Instrumented Sway System (ISway) to Identify and Compare Balance Domain Deficits in People With Multiple Sclerosis

OBJECTIVE

To develop a multiple sclerosis (MS)-specific model of balance and examine differences between (1) MS and neurotypical controls and (2) people with MS (PwMS) with (MS-F) and without a fall history (MS-NF).

DESIGN AND SETTING

A cross-sectional study was conducted at the Gait and Balance Laboratory at the University of Kansas Medical Center. Balance was measured from the instrumented sway system (ISway) assessment.

PARTICIPANTS

In total, 118 people with relapsing-remitting MS (MS-F=39; MS-NF=79) and 46 age-matched neurotypical controls.

INTERVENTION

Not applicable.

OUTCOME MEASURES

A total of 22 sway measures obtained from the ISway were entered into an exploratory factor analysis to identify underlying balance domains. The model-derived balance domains were compared between (1) PwMS and age-matched, neurotypical controls and (2) MS-F and MS-NF.

RESULTS

Three distinct balance domains were identified: (1) sway amplitude and velocity, (2) sway frequency and jerk mediolateral, and (3) sway frequency and jerk anteroposterior, explaining 81.66% of balance variance. PwMS exhibited worse performance (ie, greater amplitude and velocity of sway) in the sway velocity and amplitude domain compared to age-matched neurotypical controls (P=.003). MS-F also exhibited worse performance in the sway velocity and amplitude domain compared to MS-NF (P=.046). The anteroposterior and mediolateral sway frequency and jerk domains were not different between PwMS and neurotypical controls nor between MS-F and MS-NF.

CONCLUSIONS

This study identified a 3-factor, MS-specific balance model, demonstrating that PwMS, particularly those with a fall history, exhibit disproportionate impairments in sway amplitude and velocity. Identifying postural stability outcomes and domains that are altered in PwMS and clinically relevant (eg, related to falls) would help isolate potential treatment targets.

Machine learning-based muscle mass estimation using gait parameters in community-dwelling older adults: A cross-sectional study

BACKGROUND

Loss of skeletal muscle mass is associated with numerous factors such as metabolic diseases, lack of independence, and mortality in older adults. Therefore, developing simple, safe, and reliable tools for assessing skeletal muscle mass is needed. Some studies recently reported that the risks of the incidence of geriatric conditions could be estimated by analyzing older adults' gait; however, no studies have assessed the association between gait parameters and skeletal muscle loss in older adults. In this study, we applied machine learning approach to the gait parameters derived from three-dimensional skeletal models to distinguish older adults' low skeletal muscle mass. We also identified the most important gait parameters for detecting low muscle mass.

METHODS

Sixty-six community-dwelling older adults were recruited. Thirty-two gait parameters were created using a three-dimensional skeletal model involving 10-meter comfortable walking. After skeletal muscle mass measurement using a bioimpedance analyzer, low muscle mass was judged in accordance with the guideline of the Asia Working Group for Sarcopenia. The eXtreme gradient boosting (XGBoost) model was applied to discriminate between low and high skeletal muscle mass.

RESULTS

Eleven subjects had a low muscle mass. The c-statistics, sensitivity, specificity, precision of the final model were 0.7, 59.5%, 81.4%, and 70.5%, respectively. The top three dominant gait parameters were, in order of strongest effect, stride length, hip dynamic range of motion, and trunk rotation variability.

CONCLUSION

Machine learning-based gait analysis is a useful approach to determine the low skeletal muscle mass of community-dwelling older adults.

Regulation of whole-body and segmental angular momentum in persons with Parkinson's disease on an irregular surface

BACKGROUND

Persons with Parkinson's disease have impaired motor control that increases their chance of falling when walking, especially on difficult terrains. This study investigated how persons with Parkinson's disease regulate their dynamic balance on a regular and an irregular surface.

METHODS

Nine participants with Parkinson's disease and nine healthy, age-matched control participants ambulated on both a regular and an irregular surface. Whole-body and segmental angular momenta were calculated using three-dimensional motion capture data. Major modes of variability between health groups on the two surfaces were investigated using principal component analysis, while differences within each health group between surfaces was investigated using statistical parametric mapping t-tests.

FINDINGS

Between groups, the Parkinson participants had greater sagittal, frontal, and transverse whole-body angular momentum on both surfaces, primarily following heel-strike, and the magnitude difference on the irregular surface was greater than on the regular surface. The greatest between group segmental differences on the irregular compared to the regular surface were the legs in the sagittal plane and the head/trunk/pelvis in the transverse plane, with the Parkinson group having greater magnitudes. The within-group comparison found the Parkinson participants had poorer regulation of whole-body angular momentum in the sagittal plane, while the healthy participants showed no consistent differences between surfaces.

INTERPRETATION

On an irregular surface, persons with Parkinson's disease exhibit poor control of dynamic balance in the frontal and sagittal planes. These results emphasize the need for weight transfer techniques and training in both the sagittal and frontal planes to maximize balance and reduce fall risk.

Role of artificial intelligence in MS clinical practice

Machine learning (ML) and its subset, deep learning (DL), are branches of artificial intelligence (AI) showing promising findings in the medical field, especially when applied to imaging data. Given the substantial role of MRI in the diagnosis and management of patients with multiple sclerosis (MS), this disease is an ideal candidate for the application of AI techniques. In this narrative review, we are going to discuss the potential applications of AI for MS clinical practice, together with their limitations. Among their several advantages, ML algorithms are able to automate repetitive tasks, to analyze more data in less time and to achieve higher accuracy and reproducibility than the human counterpart. To date, these algorithms have been applied to MS diagnosis, prognosis, disease and treatment monitoring. Other fields of application have been improvement of MRI protocols as well as automated lesion and tissue segmentation. However, several challenges remain, including a better understanding of the information selected by AI algorithms, appropriate multicenter and longitudinal validations of results and practical aspects regarding hardware and software integration. Finally, one cannot overemphasize the paramount importance of human supervision, in order to optimize the use and take full advantage of the potential of AI approaches.

Examining the Relationship Between Reactive Stepping Outcomes and Falls in People With Multiple Sclerosis

OBJECTIVE

Reactive stepping is critical for preventing falls and is impaired in people with multiple sclerosis (PwMS); however, which aspects of stepping relate to falls remains poorly understood. Identifying outcomes most related to falls is a first step toward improving rehabilitation for fall prevention. The purpose of this study was to assess whether reactive step latency or length during forward and backward losses of balance were related to a history of falls in PwMS.

METHODS

Of the 111 PwMS who participated in this study, 76 reported no falls in the previous 6 months, whereas 36 reported 1 or more falls. Participants completed 3 forward and 3 backward treadmill-induced reactive steps from stance. Step length (centimeters) and step latency (milliseconds) were measured using motion capture and analyzed via MATLAB.

RESULTS

Participants with a history of falls had significantly slower step latencies during backward stepping, but not forward stepping, than those without a history of falls. Step length did not differ between groups. Slower step latencies during backward stepping significantly increased the odds of having experienced a fall (β = .908, SE = 0.403, odds ratio = 2.479, 95% CI = 1.125 to 5.464).

CONCLUSION

PwMS and a history of falling show delayed step onsets during backward reactive stepping. Specifically, for every 10-millisecond increase in step latency, PwMS were 2.5 times more likely to have a fall history. Although clinical trials are necessary to determine whether interventions targeting reactive stepping reduce falls in PwMS, the current work indicates that the latency of steps may be a relevant target for this work.

IMPACT

Subsequent fall prevention clinical trials should consider targeting backward reactive step latency to further assess its relevance for rehabilitation in PwMS.

LAY SUMMARY

If you have MS and a history of falls, you may be more likely to have delayed reactive step latencies.

The relationship between plantar sensation and muscle onset during automatic postural responses in people with multiple sclerosis and healthy controls

BACKGROUND

Plantar sensation is critical for balance control in people with multiple sclerosis (PwMS). While previous research has described its impact on standing balance, the influence of plantar sensation during automatic postural responses (APRs) is not well understood in PwMS. The purpose of this study was to characterize the relationship between plantar sensation and APRs in PwMS and controls. A secondary aim was to determine whether the relationship between plantar sensation and APRs is different across PwMS and control groups.

METHODS

122 PwMS and 48 age-matched controls underwent forward and backward support-surface perturbations from stance. The onset of the tibialis anterior (TA) and medial gastrocnemius (MG) were the primary reactive balance outcome measures for backward and forward losses of balance, respectively. Plantar sensation was measured as the vibration sensation threshold (VT).

RESULTS

As expected, PwMS had significantly higher (i.e., worse) VT (p<0.001) and an increased MG and TA onset latency (TA: p<0.001, MG: p = 0.01) compared to the control group. A higher VT was related to increased MG (p<0.001) and TA latency (p<0.001) across all participants. However, no moderating effect of group (control or PwMS) was observed for the relationship between VT and muscle onset (MG: p = 0.14; TA: p = 0.34).

CONCLUSION

PwMS demonstrated poorer plantar sensation and delayed muscle onset during APRs compared to controls. Plantar sensation was also related to muscle onset after perturbations in all participants. Although this relationship was not moderated by group, this may be related to the lack of dynamic range of VT scores in controls. These results indicate that plantar sensation may be related to reactive balance and provides insight into a potential contributing factor of delayed automatic postural responses in people with MS.