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.

Bridging the electrode-neuron gap: finite element modeling of in vitro neurotrophin gradients to optimize neuroelectronic interfaces in the inner ear.

Although cochlear implant (CI) technology has allowed for the partial restoration of hearing over the last few decades, persistent challenges (e.g., poor performance in noisy environments and limited ability to decode intonation and music) remain. The "electrode-neuron gap" is inherent to these challenges and poses the most significant obstacle to advancing past the current plateau in CI performance. We propose the development of a "neuro-regenerative nexus"-a biological interface that doubly preserves native spiral ganglion neurons (SGNs) while precisely directing the growth of neurites arising from transplanted human pluripotent stem cell (hPSC)-derived otic neuronal progenitors (ONPs) toward the native SGN population. We hypothesized that the Polyhedrin Delivery System (PODS®-recombinant human brain-derived neurotrophic factor [rhBDNF]) could stably provide the adequate BDNF concentration gradient to hPSC-derived late-stage ONPs to facilitate otic neuronal differentiation and directional neurite outgrowth. To test this hypothesis, a finite element model (FEM) was constructed to simulate BDNF concentration profiles generated by PODS®-rhBDNF based on initial concentration and culture device geometry. For biological validation of the FEM, cell culture experiments assessing survival, differentiation, neurite growth direction, and synaptic connections were conducted using a multi-chamber microfluidic device. We were able to successfully generate the optimal BDNF concentration gradient to enable survival, neuronal differentiation toward SGNs, directed neurite extension of hPSC-derived SGNs, and synaptogenesis between two hPSC-derived SGN populations. This proof-of-concept study provides a step toward the next generation of CI technology. STATEMENT OF SIGNIFICANCE: Our study demonstrates that the generation of in vitro neurotrophin concentration gradients facilitates survival, neuronal differentiation toward auditory neurons, and directed neurite extension of human pluripotent stem cell-derived auditory neurons. These findings are indispensable to designing a bioactive cochlear implant, in which stem cell-derived neurons are integrated into a cochlear implant electrode strip, as the strategy will confer directional neurite growth from the transplanted cells in the inner ear. This study is the first to present the concept of a "neuro-regenerative nexus" congruent with a bioactive cochlear implant to eliminate the electrode-neuron gap-the most significant barrier to next-generation cochlear implant technology.