Background: Questionnaires have been used in the past 2 decades to predict the diagnosis of vertigo and assist clinical decision-making. A questionnaire-based machine learning model is expected to improve the efficiency of diagnosis of vestibular disorders. Objective: This study aims to develop and validate a questionnaire-based machine learning model that predicts the diagnosis of vertigo. Methods: In this multicenter prospective study, patients presenting with vertigo entered a consecutive cohort at their first visit to the ENT and vertigo clinics of 7 tertiary referral centers from August 2019 to March 2021, with a follow-up period of 2 months. All participants completed a diagnostic questionnaire after eligibility screening. Patients who received only 1 final diagnosis by their treating specialists for their primary complaint were included in model development and validation. The data of patients enrolled before February 1, 2021 were used for modeling and cross-validation, while patients enrolled afterward entered external validation. Results: A total of 1693 patients were enrolled, with a response rate of 96.2% (1693/1760). The median age was 51 (IQR 38-61) years, with 991 (58.5%) females; 1041 (61.5%) patients received the final diagnosis during the study period. Among them, 928 (54.8%) patients were included in model development and validation, and 113 (6.7%) patients who enrolled later were used as a test set for external validation. They were classified into 5 diagnostic categories. We compared 9 candidate machine learning methods, and the recalibrated model of light gradient boosting machine achieved the best performance, with an area under the curve of 0.937 (95% CI 0.917-0.962) in cross-validation and 0.954 (95% CI 0.944-0.967) in external validation. Conclusions: The questionnaire-based light gradient boosting machine was able to predict common vestibular disorders and assist decision-making in ENT and vertigo clinics. Further studies with a larger sample size and the participation of neurologists will help assess the generalization and robustness of this machine learning method.

Introduction: In utero, exposure to sevoflurane (a commonly used inhalation anesthetic) can lead to hearing impairment in offspring mice, but the underlying impairment mechanism is not known. Materials and Methods: Day-15 pregnant mice were treated with 2.5% sevoflurane for 2 h to investigate sevoflurane ototoxicity. Cochleae from offspring mice were harvested for hair-cell and ribbon-synapse assessments. Hearing in offspring mice was assessed at postnatal day 30 using an auditory brainstem-response (ABR) test. Cochlear-explant cultures from offspring mice were exposed to 2.5% sevoflurane for 6 h. Immediately after treatment, explants were assessed for hair-cell morphology, mitochondrial oxidative stress, and autophagy. Results: In utero, sevoflurane exposure impaired hearing in the offspring is demonstrated by a decrease in ABR wave I amplitudes, a marker for ribbon-synapse functionality. Sevoflurane exposure caused no obvious damage to hair cells, but cochlear ribbon synapses were reduced in postnatal day 15 offspring, and partially recovered by postnatal day 30. Sevoflurane treatment also increased mitochondrial reactive-oxygen species stress and decreased autophagy in the cochlear explants. Conclusion: These results suggest that oxidative stress and reduced autophagy may underly ribbon-synapse involvement in sevoflurane-induced hearing loss.

Mammalian sensory hair cells (HCs) have limited capacity for regeneration, which leads to permanent hearing loss after HC death. Here, we used in vitro RNA-sequencing to show that the Hippo signaling pathway is involved in HC damage and self-repair processes. Turning off Hippo signaling through Mst1/2 inhibition or Yap overexpression induces YAP nuclear accumulation, especially in supporting cells, which induces supernumerary HC production and HC regeneration after injury. Mechanistically, these effects of Hippo signaling work synergistically with the Notch pathway. Importantly, the supernumerary HCs not only express HC markers, but also have cilia structures that are able to form neural connections to auditory regions in vivo. Taken together, regulating Hippo suggests new strategies for promoting cochlear supporting cell proliferation, HC regeneration, and reconnection with neurons in mammals.

Introduction: Exposure to gamma-aminobutyric acid-mimetics and N-methyl-d-aspartate-receptor antagonists during pregnancy may lead to hearing loss and long-term behavioral abnormalities in the offspring. The purpose of this study was to explore the association between prenatal exposure to sevoflurane (SEV) anesthesia and hearing impairment in mice. Materials and methods: On gestational day 15, pregnant Kunming mice were exposed for 2 hours to 2.5% SEV plus 100% oxygen (anesthesia group) or 100% oxygen alone (control group). Results: During auditory brainstem response testing on P30, offspring of the anesthesia group mice exhibited higher hearing thresholds at 8, 16, 24, and 32 kHz; longer peak latency of wave II at all four frequencies; and longer interpeak latencies from waves II to V at 16, 24, and 32 kHz, compared to the control offspring. Caspase-3, iNOS, and COX-2 activation occurred in the fetal cochlea of the anesthesia group. Mitochondrial swelling was observed in the anesthesia group offspring at P1 and P15.
Conclusion: Our results suggest that SEV exposure during pregnancy may cause detrimental effects on the developing auditory system.