Gait analysis with videogrammetry can differentiate healthy elderly, mild cognitive impairment, and Alzheimer's disease: A cross-sectional study

Detection of mild cognitive impairment using various types of gait tests and machine learning

Introduction

Alzheimer's disease and related disorders (ADRD) progressively impair cognitive function, prompting the need for early detection to mitigate its impact. Mild Cognitive Impairment (MCI) may signal an early cognitive decline due to ADRD. Thus, developing an accessible, non-invasive method for detecting MCI is vital for initiating early interventions to prevent severe cognitive deterioration.

Methods

This study explores the utility of analyzing gait patterns, a fundamental aspect of human motor behavior, on straight and oval paths for diagnosing MCI. Using a Kinect v.2 camera, we recorded the movements of 25 body joints from 25 individuals with MCI and 30 healthy older adults (HC). Signal processing, descriptive statistical analysis, and machine learning techniques were employed to analyze the skeletal gait data in both walking conditions.

Results and discussion

The study demonstrated that both straight and oval walking patterns provide valuable insights for MCI detection, with a notable increase in identifiable gait features in the more complex oval walking test. The Random Forest model excelled among various algorithms, achieving an 85.50% accuracy and an 83.9% F-score in detecting MCI during oval walking tests. This research introduces a cost-effective, Kinect-based method that integrates gait analysis-a key behavioral pattern-with machine learning, offering a practical tool for MCI screening in both clinical and home environments.

The association between cognitive impairment, gait speed, and Walk ratio

Background

Gait speed has been found to be associated with cognitive function. However, gait speed is an unspecific measure that may not be informative about gait patterns. The Walk ratio (step length divided by step frequency) can be measured without specialized equipment, and has been suggested as an indicator of central gait control. However, the association with cognitive function is unknown.

Research question

Is there a relationship between Walk ratio and cognitive function, and gait speed and cognitive function?

Methods

This was a systematic literature review of studies where spatiotemporal gait parameters was reported in populations with cognitive impairment. The search was performed through PubMed, PEDro, AMED, Cochrane, Embase, MEDLINE, and PsycINFO. The studies had to contain either the Walk ratio, or report average step length and average step frequency. In the latter case, the average step length was divided by the average step frequency. The studies also had to report gait speed and the minimal mental state examination (MMSE). Studies testing patients on treadmills or that did not state the exclusion of patients with neurologic or orthopedic diseases, possible affecting gait ability, were excluded.

Results

A total of 24 studies were included, consisting of 909 patients with cognitive impairment and 4,108 healthy controls. The patient group had a lower Walk ratio (mean difference 0.07, p ≤ 0.001) and gait speed (mean difference 0.26, p ≤ 0.001) than the healthy controls. Using linear regression models, we found an association between the MMSE and the Walk ratio (R² = 0.29, p < 0.001) and gait speed (R² = 0.41, p < 0.001) in separate, unadjusted models. In a final model with Walk ratio, gait speed and age, Walk ratio was not significantly associated with MMSE, while gait speed was.

Significance

Our results suggest that preferred gait speed may be preferable to the Walk ratio when assessing older adults with cognitive impairment.

Geriatric Care Management System Powered by the IoT and Computer Vision Techniques

The digitalisation of geriatric care refers to the use of emerging technologies to manage and provide person-centered care to the elderly by collecting patients' data electronically and using them to streamline the care process, which improves the overall quality, accuracy, and efficiency of healthcare. In many countries, healthcare providers still rely on the manual measurement of bioparameters, inconsistent monitoring, and paper-based care plans to manage and deliver care to elderly patients. This can lead to a number of problems, including incomplete and inaccurate record-keeping, errors, and delays in identifying and resolving health problems. The purpose of this study is to develop a geriatric care management system that combines signals from various wearable sensors, noncontact measurement devices, and image recognition techniques to monitor and detect changes in the health status of a person. The system relies on deep learning algorithms and the Internet of Things (IoT) to identify the patient and their six most pertinent poses. In addition, the algorithm has been developed to monitor changes in the patient's position over a longer period of time, which could be important for detecting health problems in a timely manner and taking appropriate measures. Finally, based on expert knowledge and a priori rules integrated in a decision tree-based model, the automated final decision on the status of nursing care plan is generated to support nursing staff.

Comparison of spatio-temporal gait parameters between the GAITRite® platinum plus classic and the GAITRite® CIRFACE among older adults: a retrospective observational study

BACKGROUND

The GAITRite® system is one of the gold standards for gait electronic analysis, especially for older adults. Previous GAITRite® systems were composed of an electronic roll-up walkway. Recently, a new GAITRite® electronic walkway, named CIRFACE, was commercialized. It is composed of a changeable association of stiff plates, unlike previous models. Are the gait parameters measured similar between these two walkways among older adults and according to the cognitive status, the history of falls, and the use of walking aids?

METHODS

In this retrospective observational study, 95 older ambulatory participants (mean, 82.6 ± 5.8 years) were included. Ten spatio-temporal gait parameters were measured simultaneously with the two GAITRite® systems in older adults while walking at comfortable self-selected pace. The GAITRite® Platinum Plus Classic (26') was superimposed on the GAITRite® CIRFACE (VI). Comparisons between the parameters of the two walkways were performed using Bravais-Pearson correlation, between-method differences (corresponding to bias), percentage errors and Intraclass Correlation Coefficients (ICC_2,1). Subgroup analyses were performed according to the cognitive status, the history of falls in the last 12 months and the use of walking aids.

RESULTS

The whole walk parameters recorded by the two walkways were extremely correlated with a Bravais-Pearson correlation coefficient ranging from 0.968 to 0.999, P < .001, indicating a very high correlation. According to the ICC_2,1 calculated for absolute agreement, all gait parameters had excellent reliability (ranging from 0.938 to 0.999). Mean bias for 9 parameters out of 10 were ranged from - 0.27 to 0.54, with clinically acceptable percentage errors (1.2-10.1%). Step length showed a substantially higher bias (1.4 ± 1.2 cm), nevertheless the percentage errors remained clinically acceptable (5%).

CONCLUSION

When walking at comfortable self-selected pace, the standard spatio-temporal walk parameters provided by both the GAITRite® PPC and the GAITRite® CIRFACE seem similar and very highly correlated in older adults with various cognitive or motor status. The data of studies using these systems can be compared and mixed with a very low risk of bias in a meta-analytic process. Also, the geriatric care units can choose the most ergonomic system according to their infrastructure without affecting their gait data.

TRIAL REGISTRATION

NCT04557592 (21/09/2020).

Video-based marker-free tracking and multi-scale analysis of mouse locomotor activity and behavioral aspects in an open field arena: A perspective approach to the quantification of complex gait disturbances associated with Alzheimer's disease

Introduction

Complex gait disturbances represent one of the prominent manifestations of various neurophysiological conditions, including widespread neurodegenerative disorders such as Alzheimer's and Parkinson's diseases. Therefore, instrumental measurement techniques and automatic computerized analysis appears essential for the differential diagnostics, as well as for the assessment of treatment effectiveness from experimental animal models to clinical settings.

Methods

Here we present a marker-free instrumental approach to the analysis of gait disturbances in animal models. Our approach is based on the analysis of video recordings obtained with a camera placed underneath an open field arena with transparent floor using the DeeperCut algorithm capable of online tracking of individual animal body parts, such as the snout, the paws and the tail. The extracted trajectories of animal body parts are next analyzed using an original computerized methodology that relies upon a generalized scalable model based on fractional Brownian motion with parameters identified by detrended partial cross-correlation analysis.

Results

We have shown that in a mouse model representative movement patterns are characterized by two asymptotic regimes characterized by integrated 1/f noise at small scales and nearly random displacements at large scales separated by a single crossover. More detailed analysis of gait disturbances revealed that the detrended cross-correlations between the movements of the snout, paws and tail relative to the animal body midpoint exhibit statistically significant discrepancies in the Alzheimer's disease mouse model compared to the control group at scales around the location of the crossover.

Discussion

We expect that the proposed approach, due to its universality, robustness and clear physical interpretation, is a promising direction for the design of applied analysis tools for the diagnostics of various gait disturbances and behavioral aspects in animal models. We further believe that the suggested mathematical models could be relevant as a complementary tool in clinical diagnostics of various neurophysiological conditions associated with movement disorders.

Quantitative gait analysis in mild cognitive impairment, dementia, and cognitively intact individuals: a cross-sectional case-control study

Background

Cognitive age-related decline is linked to dementia development and gait has been proposed to measure the change in brain function. This study aimed to investigate if spatiotemporal gait variables could be used to differentiate between the three cognitive status groups.

Methods

Ninety-three older adults were screened and classified into three groups; mild cognitive impairment (MCI) (n = 32), dementia (n = 31), and a cognitively intact (n = 30). Spatiotemporal gait variables were assessed under single- and dual-tasks using an objective platform system. Effects of cognitive status and walking task were analyzed using a two-way ANCOVA. Sub-comparisons for between- and within-group were performed by one-way ANCOVA and Paired t-tests. Area Under the Curve (AUC) of Receiver Operating Characteristics (ROC) was used to discriminate between three groups on gait variables.

Results

There were significant effects (P < 0.05) of cognitive status during both single and dual-task walking in several variables between the MCI and dementia and between dementia and cognitively intact groups, while no difference was seen between the MCI and cognitively intact groups. A large differentiation effect between the groups was found for step length, stride length, and gait speed during both conditions of walking.

Conclusions

Spatiotemporal gait variables showed discriminative ability between dementia and cognitively intact groups in both single and dual-tasks. This suggests that gait could potentially be used as a clinical differentiation marker for individuals with cognitive problems.

Gait Characteristics and Cognitive Function in Middle-Aged Adults with and without Type 2 Diabetes Mellitus: Data from ENBIND

Type 2 Diabetes Mellitus (T2DM) in midlife is associated with a greater risk of dementia in later life. Both gait speed and spatiotemporal gait characteristics have been associated with later cognitive decline in community-dwelling older adults. Thus, the assessment of gait characteristics in uncomplicated midlife T2DM may be important in selecting-out those with T2DM at greatest risk of later cognitive decline. We assessed the relationship between Inertial Motion Unit (IMUs)-derived gait characteristics and cognitive function assessed via Montreal Cognitive Assessment (MoCA)/detailed neuropsychological assessment battery (CANTAB) in middle-aged adults with and without uncomplicated T2DM using both multivariate linear regression and a neural network approach. Gait was assessed under (i) normal walking, (ii) fast (maximal) walking and (iii) cognitive dual-task walking (reciting alternate letters of the alphabet) conditions. Overall, 138 individuals were recruited (n = 94 with T2DM; 53% female, 52.8 ± 8.3 years; n = 44 healthy controls, 43% female, 51.9 ± 8.1 years). Midlife T2DM was associated with significantly slower gait velocity on both slow and fast walks (both p < 0.01) in addition to a longer stride time and greater gait complexity during normal walk (both p < 0.05). Findings persisted following covariate adjustment. In analyzing cognitive performance, the strongest association was observed between gait velocity and global cognitive function (MoCA). Significant associations were also observed between immediate/delayed memory performance and gait velocity. Analysis using a neural network approach did not outperform multivariate linear regression in predicting cognitive function (MoCA) from gait velocity. Our study demonstrates the impact of uncomplicated T2DM on gait speed and gait characteristics in midlife, in addition to the striking relationship between gait characteristics and global cognitive function/memory performance in midlife. Further studies are needed to evaluate the longitudinal relationship between midlife gait characteristics and later cognitive decline, which may aid in selecting-out those with T2DM at greatest-risk for preventative interventions.

Mild Cognitive Impairment Subtypes Are Associated With Peculiar Gait Patterns in Parkinson's Disease

Background

Mild cognitive impairment (MCI) is frequent in Parkinson's disease (PD) and represents a risk factor for the development of dementia associated with PD (PDD). Since PDD has been associated with disability, caregiver burden, and an increase in health-related costs, early detection of MCI associated with PD (PD-MCI) and its biomarkers is crucial.

Objective

Given that gait is considered a surrogate marker for cognitive decline in PD, the aim of this study was to compare gait patterns in PD-MCI subtypes in order to verify the existence of an association between specific gait features and particular MCI subtypes.

Methods

A total of 67 patients with PD were consecutively enrolled and assessed by an extensive clinical and cognitive examination. Based on the neuropsychological examination, patients were diagnosed as patients with MCI (PD-MCI) and without MCI (no-PD-MCI) and categorized in MCI subtypes. All patients were evaluated using a motion capture system of a BTS Bioengineering equipped with six IR digital cameras. Gait of the patients was assessed in the ON-state under three different tasks (a single task and two dual tasks). Statistical analysis included the t-test, the Kruskal-Wallis test with post hoc analysis, and the exploratory correlation analysis.

Results

Gait pattern was poorer in PD-MCI vs. no-PD-MCI in all tasks. Among PD-MCI subtypes, multiple-domain PD-MCI and amnestic PD-MCI were coupled with worse gait patterns, notably in the dual task.

Conclusion

Both the magnitude of cognitive impairment and the presence of memory dysfunction are associated with increased measures of dynamic unbalance, especially in dual-task conditions, likely mirroring the progressive involvement of posterior cortical networks.

Relationship Between Aerobic Capacity, Mobility, and Spatial Navigation in Healthy Individuals and Older Adults With Mild Cognitive Impairment: A Cross-Sectional Study

This study aimed to investigate the relationship between physical ability and spatial navigation in older adults with mild cognitive impairment and healthy controls, using the floor maze test. Study participants (n = 58) were subjected to the following tests: floor maze test, sit-to-stand, 8-foot up-and-go, and aerobic steps. Factorial analyses showed that performance of the physical tests combined explained approximately 87% of the sample variability. Mobility (R2 = .22, p ≤ .001) and aerobic capacity (R2 = .27, p ≤ .001) were both associated with delayed maze time in the floor maze test. Low levels of aerobic capacity were also associated with an increased odds to perform poorly in the delayed maze time after controlling for age, sex, and mild cognitive impairment diagnosis (odds ratio = 3.1; 95% confidence interval [1.0, 9.5]; p = .04). Aerobic capacity and mobility are associated with spatial navigation in patients with mild cognitive impairment and healthy older adults.

Cerebral Microbleeds Were Related With Poor Cognitive Performances on the Dual Task Condition in Older Adults

Background: The dual task (DT) was commonly used to assess the risk of falls in older adults and patients with neurological disorders. However, the performance on DT conditions has not been well investigated in patients with cerebral microbleed (CMB). This study is aimed to compare the performance in DT tests between older adults with and without CMB, and to explore the association between CMB and cognitive performances of DT.

Methods: This is a cross-sectional study. A total of 211 old adults participated, involving 68 CMB patients. The task protocol involved two global cognition tests, two single cognitive tests (serial 7 subtraction and semantic fluency), two single motor tasks [8-m walking and timed up and go test (TUG)], and three DT tests [walking and serial subtraction (WSS), walking and semantic fluency (WSF), and TUG and serial subtraction (TUGSS)]. The time taken to complete each task and the number of correct responses were recorded. For each DT condition, the correct response rate (CRR) and the dual-task effect (DTE) for the correct number were calculated.

Results: Compared with subjects without CMB, CMB patients had worse cognitive performances on DT condition in CRR of WSS (p = 0.003), WSF (p = 0.030) and TUGSS (p = 0.006), and DTE of WSS (p = 0.017). Binary logistic regression analysis showed that the presence of CMB was an independent risk factor for the impairment group for CRR of TUGSS (OR, 2.54; 95% CI, 1.11–5.82; p = 0.027) with the adjustment for confounders, rather than CRR of WSS and WSF, or DTE of WSS. Multiple linear regression analysis showed that CRR of TUGSS decreased with the increase of CMB number grades (β, −0.144; 95% CI, −0.027, −0.002; p = 0.028).

Conclusion: The present study indicated that CMBs were closely associated with poor cognitive performances on DT in the elderly. Strongest effect size was seen for CRR of TUGSS, where performance deficits increased in proportion to the degree of CMB burden.

Extraction of gait parameters from marker-free video recordings of Timed Up-and-Go tests: Validity, inter- and intra-rater reliability

BACKGROUND

We study dual-task performance with marker-free video recordings of Timed Up-and-Go tests (TUG) and TUG combined with a cognitive/verbal task (TUG dual-task, TUGdt).

RESEARCH QUESTION

Can gait parameters be accurately estimated from video-recorded TUG tests by a new semi-automatic method aided by a technique for human 2D pose estimation based on deep learning?

METHODS

Thirty persons aged 60-85 years participated in the study, conducted in a laboratory environment. Data were collected by two synchronous video-cameras and a marker-based optoelectronic motion capture system as gold standard, to evaluate the gait parameters step length (SL), step width (SW), step duration (SD), single-stance duration (SSD) and double-stance duration (DSD). For reliability evaluations, data processing aided by a deep neural network model, involved three raters who conducted three repetitions of identifying anatomical keypoints in recordings of one randomly selected step from each of the participants. Validity was analysed using 95 % confidence intervals (CI) and p-values for method differences and Bland-Altman plots with limits of agreement. Inter- and intra-rater reliability were calculated as intraclass correlation coefficients (ICC) and standard errors of measurement. Smallest detectable change was calculated for inter-rater reliability.

RESULTS

Mean ddifferences between video and the motion capture system data for SW, DSD, and SSD were significant (p < 0.001). However, mean differences for all parameters were small (-6.4%-13.0% of motion capture system) indicating good validity. Concerning reliability, almost all 95 % CI of the ICC estimates exceeded 0.90, indicating excellent reliability. Only inter-rater reliability for SW (95 % CI = 0.892;0.973) and one rater's intra-rater reliability for SSD (95 % CI = 0.793;0.951) were lower, but still showed good to excellent reliability.

SIGNIFICANCE

The presented method for extraction of gait parameters from video appears suitable for valid and reliable quantification of gait. This opens up for analyses that may contribute to the knowledge of cognitive-motor interference in dual-task testing.

The use of Motor and Cognitive Dual-Task quantitative assessment on subjects with mild cognitive impairment: A systematic review

Dementia and Alzheimer's Disease (AD) represent a health emergency. The identification of valid and noninvasive markers to identify people with Mild Cognitive Impairment (MCI) is profoundly advocated. This review outlines the use of quantitative Motor and Cognitive Dual-Task (MCDT) on MCI, by technologies aid. We describe the framework and the most valuable researches, displaying the adopted protocols, and the available technologies. PubMed Central, Web of Science, and Scopus were inspected between January 2010 and May 2020. 1939 articles were found in the initial quest. Exclusion criteria allowed the selection of the most relevant papers; 38 papers were included. The articles, regarding four technological solutions "wearable sensors", "personal devices", "optokinetic systems", and "electronic walkways", are organized into three categories: "Quantitative MCDT", "MCDT Inspired by Neuropsychological Test", and "MCDT for MCI Stimulation". MCDT might furnish clinical landmarks, supplying aid for disease stratication, risk prediction, and intervention optimization. Such protocols could foster the use of data mining and machine learning techniques. Notwithstanding, there is still a need to standardize and harmonize such protocols.