Dataset Information

Fall Risk Prediction in Multiple Sclerosis Using Postural Sway Measures: A Machine Learning Approach.

ABSTRACT: Numerous postural sway metrics have been shown to be sensitive to balance impairment and fall risk in individuals with MS. Yet, there are no guidelines concerning the most appropriate postural sway metrics to monitor impairment. This investigation implemented a machine learning approach to assess the accuracy and feature importance of various postural sway metrics to differentiate individuals with MS from healthy controls as a function of physiological fall risk. 153 participants (50 controls and 103 individuals with MS) underwent a static posturography assessment and a physiological fall risk assessment. Participants were further classified into four subgroups based on fall risk: controls, low-risk MS (n?=?34), moderate-risk MS (n?=?27), high-risk MS (n?=?42). Twenty common sway metrics were derived following standard procedures and subsequently used to train a machine learning algorithm (random forest - RF, with 10-fold cross validation) to predict individuals' fall risk grouping. The sway-metric based RF classifier had high accuracy in discriminating controls from MS individuals (>86%). Sway sample entropy was identified as the strongest feature for classification of low-risk MS individuals from healthy controls. Whereas for all other comparisons, mediolateral sway amplitude was identified as the strongest predictor for fall risk groupings.

SUBMITTER: Sun R

PROVIDER: S-EPMC6834625 | biostudies-literature | 2019 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Fall Risk Prediction in Multiple Sclerosis Using Postural Sway Measures: A Machine Learning Approach.

Sun Ruopeng R Hsieh Katherine L KL Sosnoff Jacob J JJ

Scientific reports 20191106 1

Numerous postural sway metrics have been shown to be sensitive to balance impairment and fall risk in individuals with MS. Yet, there are no guidelines concerning the most appropriate postural sway metrics to monitor impairment. This investigation implemented a machine learning approach to assess the accuracy and feature importance of various postural sway metrics to differentiate individuals with MS from healthy controls as a function of physiological fall risk. 153 participants (50 controls an ...[more]

PMID: 31695127

Similar Datasets

Project description:Balance impairment is common in individuals with multiple sclerosis (MS). However, objective assessment of balance usually requires clinical expertise and/or the use of expensive and obtrusive measuring equipment. These barriers to the objective assessment of balance may be overcome with the development of a lightweight inertial sensor system. In this study, we examined the concurrent validity of a novel wireless, skin-mounted inertial sensor system (BioStamp®, MC10 Inc.) to measure postural sway in individuals with MS by comparing measurement agreement between this novel sensor and gold standard measurement tools (force plate and externally validated inertial sensor). A total of 39 individuals with MS and 15 healthy controls participated in the study. Participants with MS were divided into groups based on the amount of impairment (MSMild: EDSS 2-4, n = 19; MSSevere: EDSS ≥6, n = 20). The balance assessment consisted of two 30-s quiet standing trials in each of three conditions: eyes open/firm surface, eyes closed/firm surface, and eyes open/foam surface. For each trial, postural sway was recorded with a force plate (Bertec) and simultaneously using two accelerometers (BioStamp and Xsens) mounted on the participant's posterior trunk at L5. Sway metrics (sway area, sway path length, root mean square amplitude, mean velocity, JERK, and total power) were derived to compare the measurement agreement among the measurement devices. Excellent agreement (intraclass correlation coefficients >0.9) between sway metrics derived from the BioStamp and the MTx sensors were observed across all conditions and groups. Good to excellent correlations (r >0.7) between devices were observed in all sway metrics and conditions. Additionally, the acceleration sway metrics were nearly as effective as the force plate sway metrics in differentiating individuals with poor balance from healthy controls. Overall, the BioStamp sensor is a valid and objective measurement tool for postural sway assessment. This novel, lightweight and portable sensor may offer unique advantages in tracking patient's postural performance.

Project description:Background and purposeFall accidents are a social challenge in Korea and elsewhere. Most previous studies have focused on the effects of reduced visual acuity due to myopia on falls and body balance. The objective of this study was to investigate whether uncorrected hyperopia was a major risk factor for falls and to establish whether the risk of falls was absolutely correlated with visual acuity.MethodsFifty-one young subjects with a mean age of 22.75 ± 2.13 years were enrolled in this study. To induce hyperopic and myopic refractive errors, spherical lenses of ±1.0-6.0 D (1.0 D stepwise) were used. Under each induced condition, fall risk index and sway power were assessed via Fourier transformation of postural sway using a TETRAX system.ResultsThe fall risk index for eyes-closed was significantly greater than that of eyes-open with full correction (t = -5.876, p < 0.05). The fall risk index increased significantly from hyperopia induced with -4.0 D lenses (with visual acuity of 0.69 ± 0.32) compared to eyes-open with full correction (F = 3.213, p < 0.05). However, there was no significant change in the induced myopia conditions, despite a drastic decline in decimal visual acuity. Sway power increased significantly in the low-to-medium frequency band derived from the peripheral vestibular system when hyperopia was induced. A significant difference was detected in hyperopia induced with -6.0 D lenses compared to eyes-open with full correction (F = 4.981, p = 0.017).ConclusionAn uncorrected hyperopia rather than myopia may increase the risk of falls, although eyes may show normal visual acuity due to the inherent accommodation mechanism. Our findings suggest that the corrected state of refractive errors is more important than the level of visual acuity as the criteria for appropriate visual input, which contributes to stable posture. Therefore, clinicians should consider the refractive condition, especially the characteristics of hyperopia, when analyzing body balance, and appropriate correction of uncorrected hyperopia to prevent falls.

Project description:ObjectivesTo stratify patients with multiple sclerosis (pwMS) based on brain MRI-derived volumetric features using unsupervised machine learning.MethodsThe 3-T brain MRIs of relapsing-remitting pwMS including 3D-T1w and FLAIR-T2w sequences were retrospectively collected, along with Expanded Disability Status Scale (EDSS) scores and long-term (10 ± 2 years) clinical outcomes (EDSS, cognition, and progressive course). From the MRIs, volumes of demyelinating lesions and 116 atlas-defined gray matter regions were automatically segmented and expressed as z-scores referenced to external populations. Following feature selection, baseline MRI-derived biomarkers entered the Subtype and Stage Inference (SuStaIn) algorithm, which estimates subgroups characterized by distinct patterns of biomarker evolution and stages within subgroups. The trained model was then applied to longitudinal MRIs. Stability of subtypes and stage change over time were assessed via Krippendorf's α and multilevel linear regression models, respectively. The prognostic relevance of SuStaIn classification was assessed with ordinal/logistic regression analyses.ResultsWe selected 425 pwMS (35.9 ± 9.9 years; F/M: 301/124), corresponding to 1129 MRI scans, along with healthy controls (N = 148; 35.9 ± 13.0 years; F/M: 77/71) and external pwMS (N = 80; 40.4 ± 11.9 years; F/M: 56/24) as reference populations. Based on 11 biomarkers surviving feature selection, two subtypes were identified, designated as "deep gray matter (DGM)-first" subtype (N = 238) and "cortex-first" subtype (N = 187) according to the atrophy pattern. Subtypes were consistent over time (α = 0.806), with significant annual stage increase (b = 0.20; p < 0.001). EDSS was associated with stage and DGM-first subtype (p ≤ 0.02). Baseline stage predicted long-term disability, transition to progressive course, and cognitive impairment (p ≤ 0.03), with the latter also associated with DGM-first subtype (p = 0.005).ConclusionsUnsupervised learning modelling of brain MRI-derived volumetric features provides a biologically reliable and prognostically meaningful stratification of pwMS.Key points• The unsupervised modelling of brain MRI-derived volumetric features can provide a single-visit stratification of multiple sclerosis patients. • The so-obtained classification tends to be consistent over time and captures disease-related brain damage progression, supporting the biological reliability of the model. • Baseline stratification predicts long-term clinical disability, cognition, and transition to secondary progressive course.

Dataset Information

Fall Risk Prediction in Multiple Sclerosis Using Postural Sway Measures: A Machine Learning Approach.

Publications

Fall Risk Prediction in Multiple Sclerosis Using Postural Sway Measures: A Machine Learning Approach.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets