The advantages of artificial intelligence-based gait assessment in detecting, predicting, and managing Parkinson's disease

Background

Parkinson's disease is a neurological disorder that can cause gait disturbance, leading to mobility issues and falls. Early diagnosis and prediction of freeze episodes are essential for mitigating symptoms and monitoring the disease.

Objective

This review aims to evaluate the use of artificial intelligence (AI)-based gait evaluation in diagnosing and managing Parkinson's disease, and to explore the potential benefits of this technology for clinical decision-making and treatment support.

Methods

A thorough review of published literature was conducted to identify studies, articles, and research related to AI-based gait evaluation in Parkinson's disease.

Results

AI-based gait evaluation has shown promise in preventing freeze episodes, improving diagnosis, and increasing motor independence in patients with Parkinson's disease. Its advantages include higher diagnostic accuracy, continuous monitoring, and personalized therapeutic interventions.

Conclusion

AI-based gait evaluation systems hold great promise for managing Parkinson's disease and improving patient outcomes. They offer the potential to transform clinical decision-making and inform personalized therapies, but further research is needed to determine their effectiveness and refine their use.

A New Software for Quantifying Motor Deficit After Stroke: A Case-Control Feasibility Pilot Study

Introduction: The degree of disability after stroke needs to be objectively measured to implement adequate rehabilitation programs. Here, we evaluate the feasibility of a custom-built software to assess motor status after stroke.

Methods: This is a prospective, case–control pilot study comparing stroke patients with healthy volunteers. A workout evaluation that included trunk and upper limb movement was captured with Kinect® and kinematic metrics were extracted with Akira®. Trunk and joint angles were analyzed and compared between cases and controls. Patients were evaluated within the first week from stroke onset using the National Institutes of Health Stroke Scale (NIHSS), Fulg-Meyer Assessment (FMA), and modified Rankin Scale (mRS) scales; the relationship with kinematic measurements was explored.

Results: Thirty-seven patients and 33 controls were evaluated. Median (IQR) NIHSS of cases was 2 (0–4). The kinematic metrics that showed better discriminatory capacity were body sway during walking (less in cases than in controls, p = 0.01) and the drift in the forearm–trunk angle during shoulder abduction in supination (greater in cases than in controls, p = 0.01). The body sway during walking was moderately correlated with NIHSS score (Rho = −0.39; p = 0.01) but better correlated with mRS score (Rho = −0.52; p < 0.001) and was associated with the absence of disability (mRS 0–1) (OR = 0.64; p = 0.02). The drift in the forearm–trunk angle in supination was associated with the presence of disability (mRS >1) (OR = 1.27; p = 0.04).

Conclusion: We present a new software that detects even mild motor impairment in stroke patients underestimated by clinical scales but with an impact on patient functionality.

Structured Observation of Motor Performance in Infants: Level and quality associated with later motor development

AIM

The aim of this study was to investigate the level of motor development and the quality of motor performance during the first 10 months in relation to the Bayley Scales of Infant Development-third edition (Bayley-III) motor index at 2.5 years.

METHODS

Children born very preterm from a population-based study (n = 113) were assessed with the Structured Observation of Motor Performance in Infants (SOMP-I) at 2, 4, 6 and 10 months corrected age and the Bayley-III motor index at 2.5 years corrected age (n = 98). Logistic regressions were performed to investigate the independent association of each SOMP-I domain to Bayley-III motor index.

RESULTS

There were significant associations between the SOMP-I-scores and Bayley-III motor index per every assessment age. At 4 months, both level and quality were independently associated with a later motor outcome, OR for level was 1.26 (95% CI = 1.08-1.50, P = .002) and for quality, 0.75 (95% CI = 0.63-0.90, P = .002). Quality was independently associated with the Bayley-III motor index at 6 and 10 months: OR 0.080 (95% CI = 0.67-0.95 P = .010) and 0.79 (95% CI = 0.64-0.97, P = .026).

CONCLUSION

Both SOMP-I domains, level and quality, are markers to identify motor problems early. Quality became more important with age.

The Frail'BESTest. An Adaptation of the "Balance Evaluation System Test" for Frail Older Adults. Description, Internal Consistency and Inter-Rater Reliability

Introduction

The Balance Evaluation System Test (BESTest) and the Mini-BESTest were developed to assess the complementary systems that contribute to balance function. These tests include functional tasks involving several high-level exercises to assess the balance function, which may be even more difficult in case of frailty. The Frail'BESTest has been developed to make it possible to include frail older adults in systemic assessment. In this first paper, the objective is to present the Frail'BESTest and to describe the usefulness and complementarity of each system and to test the inter-rater reliability of the score measurements in two health centers.

Methods

In the first center, 192 frail and non-frail older patients were enrolled to test I) the contribution of each system, II) internal consistency, and III) the threshold and ceiling effects. The scores of 32 patients from center 1 and 32 patients recruited in another center (center 2) were used to measure the inter-rater reliability of the measurements by means of Kendall's tau coefficients.

Results

The internal consistency was moderate to good for five systems and limited for "biomechanical constraints". The distribution of the Frail'BESTest was more centered than that of the Tinetti and Mini-Motor tests. The Kendall's tau showed strong concordance in center 1 for all systems and only for 4 on 6 systems in center 2.

Discussion

Completing a systemic evaluation, the therapist may prioritize the patient's needs identifying the most challenging systems. This paper presents the Frail'BESTest and confirms the psychometric properties at a first step level.

An Instrumented Assessment of a Rhythmic Finger Task among Children with Motor Coordination Difficulties

BACKGROUND

Coordination is crucial for motor function, yet objective clinical evaluations are limited. We therefore developed and tested the reliability and validity of a low-cost sensorized evaluation of a rhythmic finger task.

METHODS

Children with coordination difficulties (n = 24) and typically developing children (n = 24) aged from 5 to 7 years performed the Sensorized Finger Sequencing Test (SFST), a finger sequencing test that records the correct sequence, total time, and the standard deviation (SD) of touch time. Additionally, motor performance tests and parents' reports were applied in order to test the reliability and validity of the SFST.

RESULTS

The study group had significantly greater thumb-finger test scores-total time in the dominant hand (p = 0.035) and the SD of the touch time in both dominant (p = 0.036) and non-dominant (p = 0.032) hands. Motor performance tests were not correlated with the SFST. Test-retest reliability in 10 healthy children was found for the SD of touch time in the dominant hand (r = 0.87, p = 0.003).

CONCLUSIONS

The SFST was successful in assessing the movement pattern variability reported in children with motor difficulties. This exploratory study indicates that the low-cost SFST could be utilized as an objective measure for the assessment of proprioception components, which currently are overlooked by standardized motor performance assessments.

Relative and Absolute Reliability of a Motor Assessment System Using KINECT® Camera

(1) Background: Virtual reality is currently useful in different clinical specialties as a diagnostic and therapeutic tool. In this study, we analyzed the relative and absolute reliability of the motor evaluation with the Kinect camera, a markerless motion system. (2) Methods: Observational study in healthy people, whose inclusion criteria were: healthy people, age 18 to 40 years old without pathologies or injuries in osteoarticular structures or ligamentous muscle and pharmacological treatment with influence on motor skills. Fifty-two subjects were evaluated. (3) Results: The results of the relative reliability were favorable in variables such as the amplitude of passage of the right leg (ICC (Intraclass Correlation Coefficient) = 0.95 ± 0.03), the step width of the left leg (ICC = 0.92 ± 0.04) or balance of the left leg (ICC = 0.90 ± 0.05). Moderate values were found for other variables. The absolute reliability, measured by the coefficient of variation, was favorable in most of the variables. (4) Conclusions: The results reflect a favorable intraclass correlation in the evaluation of the variation and asymmetry of movements of the upper limbs, the balance of both legs, the side step width and the evaluation of the sitting and standing positions. The reliability of the evaluation of the variation of movements and the asymmetry of the lower limbs must be further improved.

Apkinson: the smartphone application for telemonitoring Parkinson's patients through speech, gait and hands movement

Aim: This paper introduces Apkinson, a mobile application for motor evaluation and monitoring of Parkinson's disease patients. Materials & methods: The App is based on previously reported methods, for instance, the evaluation of articulation and pronunciation in speech, regularity and freezing of gait in walking, and tapping accuracy in hand movement. Results: Preliminary experiments indicate that most of the measurements are suitable to discriminate patients and controls. Significance is evaluated through statistical tests. Conclusion: Although the reported results correspond to preliminary experiments, we think that Apkinson is a very useful App that can help patients, caregivers and clinicians, in performing a more accurate monitoring of the disease progression. Additionally, the mobile App can be a personal health assistant.

Inter and Intra Operator Reliability of Motor and Palpation Evaluation in Fascial Manipulation in individuals with coxarthrosis

OBJECTIVE

An inter and intra rater reliability (INTERR and INTRAR) study was designed.

METHODS

71 subjects, with primary hip coxarthrosis, were included and randomly divided in a study group (SG= 36) and a control group (CG= 35) to assess the efficacy of the Fascial Manipulation® (FM®) method. The primary objective was the assessment of INTERR and INTRAR about movement verification (MV) and palpation verification (PV) of FM® performed by two physiotherapists (PtA and PtB). The secondary objective was evaluate the efficacy of FM® through MV, PV and pain score. Pain was assessed using the Numeric Rating Scale (NRS). SG received three weekly sessions of FM® byPtA. PtB re-evaluated all the subjects at the end of the study.

RESULTS

Results of the INTERR analysis showed for SG: MV (ICC= 0.92, k= 72.7%); PV (ICC= 0.91, k= 75.7%). For CG : MV (ICC= 0.95, k= 84.2%); PV (ICC= 0.90, k= 75%). Results of the INTRAR analysis for SG reported: MV (ICC= 0.82, k= 74,8%); PV (ICC= 0.60, k= 46.8%); for CG: MV (ICC= 0.93, k= 78.7%); PV (ICC= 0.84, k= 53.3%). Statistical significance were reported in NRS (p = 0.001), MV (p = 0.0003) and PV (p < 0.0001) with better results for SG using "Intention To Treat" method.

DISCUSSION

This study demonstrates that FM® assessment procedures have a high reliability even if applied by practitioners with basic experience. Furthermore FM® treatment can improve pain and ROM in individuals with primary coxarthrosis.