Walking stability in patients with benign paroxysmal positional vertigo: an objective assessment using wearable accelerometers and machine learning

Abstract

Background Benign paroxysmal positional vertigo (BPPV) is one of the most common peripheral vestibular disorders leading to balance difficulties and increased fall risks. This study aims to investigate the walking stability of BPPV patients in clinical settings and propose a machine-learning-based classification method for determining the severity of gait disturbances of BPPV. Methods Twenty-seven BPPV outpatients and twenty-seven healthy subjects completed level walking trials at self-preferred speed in clinical settings while wearing two accelerometers on the head and lower trunk, respectively. Temporo-spatial variables and six walking stability related variables [root mean square (RMS), harmonic ratio (HR), gait variability, step/stride regularity, and gait symmetry] derived from the acceleration signals were analyzed. A support vector machine model (SVM) based on the gait variables of BPPV patients were developed to differentiate patients from healthy controls and classify the handicapping effects of dizziness imposed by BPPV. Results The results showed that BPPV patients employed a conservative gait and significantly reduced walking stability compared to the healthy controls. Significant different mediolateral HR at the lower trunk and anteroposterior step regularity at the head were found in BPPV patients among mild, moderate, and severe DHI (dizziness handicap inventory) subgroups. SVM classification achieved promising accuracies with area under the curve (AUC) of 0.78, 0.83, 0.85 and 0.96 respectively for differentiating patients from healthy controls and classifying the three stages of DHI subgroups. Study results suggest that the proposed gait analysis that is based on the coupling of wearable accelerometers and machine learning provides an objective approach for assessing gait disturbances and handicapping effects of dizziness imposed by BPPV.

Differentiation benign paroxysmal positional vertigo from vestibular migraine via walking stability analysis: a cross- sectional and machine-learning study

“…VM patients also presented shorter step lengths. The results were identical to our previous study [33]. Remarkably, there is no signi cant difference in temporospatial parameters between VM and BPPV groups.…”

Wearable Sensor for Assessing Gait and Postural Alterations in Patients with Diabetes: A Scoping Review

“…Thus, they are useful for implementing strategies to reduce the risk of falls which represents a major public health problem [50]. Recent reports suggest that IMUs, besides being useful in evaluating and to monitoring gait alterations in patients with neurodegenerative diseases such as Parkinson's disease [51][52][53], are useful for; patients with osteoarthritis [54], with benign paroxysmal positional vertigo, the most common peripheral vestibular disorder, leading to balance difficulties and increased fall risks [55] and walking disturbances in sarcopenic patients [56], they are also useful for gait event detection and analysis of gait alterations in patients with diabetes secondary to DPN [23,24,[27][28][29]31]. In spatiotemporal gait parameters recorded using a wearable sensor in patients with DPN, Kang et al showed that gait initiation steps and dynamic balance may be more sensitive than gait speed for detecting gait deterioration due to DPN [23], and Najafi et al demonstrated that gait alteration in patients with DPN is most pronounced while walking barefoot over longer distances [31].…”

Identifying the Effects of Age and Speed on Whole-Body Gait Symmetry by Using a Single Wearable Sensor

“…Recently, advanced classification procedures, such as machine learning-based algorithms, have relied on data captured by inertial sensors to differentiate clinical scores and to monitor a precision rehabilitation intervention [50] or to differentiate patients from healthy controls for determining the severity of gait disturbances [51]. In this last study, the gait symmetry was one of the relevant measures processed by the machine learning algorithms to determine a reliable severity score of gait disorders.…”