Application of supervised machine learning algorithms for the evaluation of utricular function on patients with Meniere's disease: utilizing subjective visual vertical and ocular-vestibular-evoked myogenic potentials.

BACKGROUND: Research on the otolith organs remains inconclusive. OBJECTIVES: This study seeks to further elucidate utricular function in patients with Meniere's disease (MD) in three ways: (1) We aimed to disambiguate the role of the Subjective Visual Vertical (SVV) and Ocular Vestibular Evoked Myogenic Potential (o-VEMP) tests regarding which utricular subsystem each is measuring. (2) We sought to characterize the acute and chronic state of MD by identifying differences in the relationship of SVV and o-VEMP results across patients with acute and chronic MD. (3) We attempted to find a machine-learning algorithm that could predict acute versus chronic MD using SVV and o-VEMP. METHODS: A prospective study with ninety subjects. RESULTS: (1) SVV and o-VEMP tests were found to have a moderate linear relationship in patients with acute MD, suggesting each test measures a different utricular subsystem. (2) Regression analyses statistically differed across the two patient populations, suggesting that SVV results were normalized in chronic MD patients. (3) Logistic regression and Naïve Bayes algorithms were found to predict acute and chronic MD accurately. SIGNIFICANCE: A better understanding of what diagnostic tests measure will lead to a better classification system for MD and more targeted treatment options in the future.

Diagnostic value of refixation saccades in the Video Head Impulse Test (vHIT) in unilateral definite Meniere's disease.

Introduction: We currently interpret the video Head Impulse Test (vHIT) results mainly based on the gain value.Aim: The purpose of this study is to evaluate vHIT results for both gain and re-fixation saccades on unilateral definite Meniere's disease (MD) subjects in comparison with normal healthy subjects.Materials and Methods: Forty unilateral definite MD subjects and age-matched healthy subjects were recruited. Pure tone audiometry, the caloric test, and the vHIT test were performed on MD subjects. The vHIT test was performed on healthy subjects.Results: The velocity regression gain (VRG) of the affected ear in patients with MD is significantly lower than of those in healthy subjects. The total percentage of refixation saccades is significantly higher in patients with MD when compared to healthy subjects. VRG values were not well-correlated with the percentage of refixation saccades. VRG asymmetry values are also not well-correlated with the percentage of unilateral canal weakness. A moderately stronger correlation between the percentage of refixation saccades and percentage of unilateral canal weakness, with an r2 of 0.474.Conclusions: The present study suggests that while VRGs are still a diagnostic parameter of detecting MD, the presence of refixation saccades can also have diagnostic value, especially with normal VRGs, in detecting MD.

Evaluation of the utricular function with the virtual-subject visual vertical system: comparison with ocular vestibular-evoked myogenic potentials.

Introduction: The subjective visual vertical (SVV) is the most frequently assessed modality of verticality perception and has been measured in a variety of clinical situations, including peripheral vestibular lesions.Aim: The main objectives are (1) to collect normative data of Virtual SVV™ from healthy subjects, and (2) to study the correlation between Virtual SVV™ and ocular vestibular-evoked myogenic potentials (o-VEMP) on healthy subjects.Materials and methods: Forty-three healthy subjects were recruited. Air conduction (AC)-elicited oVEMPs and bone conduction (BC)-elicited oVEMPs were measured. BC stimuli were produced with a RadioEar B-81 High Output Bone Transducer. Virtual SVV™ were also measured.Results: Virtual SVV™ data from our healthy subjects were consistent with previously published normative SVV data. Normal Virtual SVV™ data did not correlate with normal AC-elicited and BC-elicited oVEMPs.Conclusions: Virtual SVV™ data from our healthy subjects were consistent with previously published normative SVV data. Virtual SVV™ data from our 43 health subjects only had weak correlation with c-VEMP, AC-elicited and BC-elicited oVEMPs. These data serve as a baseline for a future study of patients with unilateral utricular dysfunction.Significance: The Virtual SVV™ can be an attractive substitute for traditional SVV in clinical settings.