RNA sequencing uncovers the key microRNAs potentially contributing to sudden sensorineural hearing loss

Small RNA Deep Sequencing Uncovers microRNAs Associated with Hearing Loss in Vestibular Schwannoma

OBJECTIVE

To analyze the correlation between the miRNA expression profile in vestibular schwannoma (VS) tumor tissue and preoperative patient's hearing status, using the RNA-seq technique.

METHODS

Nineteen tumor samples were collected from patients operated for VS in a Tertiary Academic Center. Samples were classified into "good hearing" and "poor hearing" study group based on the results of audiometric studies. Tumor miRNA expression was analyzed using high-throughput RNA sequencing (RNA-seq) technique, using NovaSeq 6000 Illumina system. Functional analysis was performed with the use of DIANA miRpath v. 4.0 online tool.

RESULTS

The most overexpressed miRNAs in VS samples derived from poor hearing patients belonged to miR 449a/b, miR 15/16-1, and hypoxamiR families. Functional analysis showed that the differentially expressed miRNAs regulate cellular pathways associated with hypoxia, adherence junction functions, and signaling pathways such as Hippo, FOXO, MAPK, and Wnt signaling pathway.

CONCLUSION

Our study identified a specific miRNA expression profile in VS tumor tissues that correlates with hearing impairment. These results suggest potential new molecular mechanisms related to hearing loss in the course of VS.

LEVEL OF EVIDENCE

3 (cohort study) Laryngoscope, 134:3778-3785, 2024.

NcRNA: key and potential in hearing loss

Hearing loss has an extremely high prevalence worldwide and brings incredible economic and social burdens. Mechanisms such as epigenetics are profoundly involved in the initiation and progression of hearing loss and potentially yield definite strategies for hearing loss treatment. Non-coding genes occupy 97% of the human genome, and their transcripts, non-coding RNAs (ncRNAs), are widely participated in regulating various physiological and pathological situations. NcRNAs, mainly including micro-RNAs (miRNAs), long-stranded non-coding RNAs (lncRNAs), and circular RNAs (circRNAs), are involved in the regulation of cell metabolism and cell death by modulating gene expression and protein-protein interactions, thus impacting the occurrence and prognosis of hearing loss. This review provides a detailed overview of ncRNAs, especially miRNAs and lncRNAs, in the pathogenesis of hearing loss. We also discuss the shortcomings and issues that need to be addressed in the study of hearing loss ncRNAs in the hope of providing viable therapeutic strategies for the precise treatment of hearing loss.

Differentially expressed miRNA profiles of serum-derived exosomes in patients with sudden sensorineural hearing loss

Objectives

This study aimed to compare the expressed microRNA (miRNA) profiles of serum-derived exosomes of patients with sudden sensorineural hearing loss (SSNHL) and normal hearing controls to identify exosomal miRNAs that may be associated with SSNHL or serve as biomarkers for SSNHL.

Methods

Peripheral venous blood of patients with SSNHL and healthy controls was collected to isolate exosomes. Nanoparticle tracking analysis, transmission electron microscopy, and Western blotting were used to identify the isolated exosomes, after which total RNA was extracted and used for miRNA transcriptome sequencing. Differentially expressed miRNAs (DE-miRNAs) were identified based on the thresholds of P < 0.05 and |log₂fold change| > 1 and subjected to functional analyses. Finally, four exosomal DE-miRNAs, including PC-5p-38556_39, PC-5p-29163_54, PC-5p-31742_49, and hsa-miR-93-3p_R+1, were chosen for validation using quantitative real-time polymerase chain reaction (RT-qPCR).

Results

Exosomes were isolated from serum and identified based on particle size, morphological examination, and expression of exosome-marker proteins. A total of 18 exosomal DE-miRNAs, including three upregulated and 15 downregulated miRNAs, were found in SSNHL cases. Gene ontology (GO) functional annotation analysis revealed that target genes in the top 20 terms were mainly related to "protein binding," "metal ion binding," "ATP binding," and "intracellular signal transduction." Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis revealed that these target genes were functionally enriched in the "Ras," "Hippo," "cGMP-PKG," and "AMPK signaling pathways." The expression levels of PC-5p-38556_39 and PC-5p-29163_54 were significantly downregulated and that of miR-93-3p_R+1 was highly upregulated in SSNHL. Consequently, the consistency rate between sequencing and RT-qPCR was 75% and sequencing results were highly reliable.

Conclusion

This study identified 18 exosomal DE-miRNAs, including PC-5p-38556_39, PC-5p-29163_54, and miR-93-3p, which may be closely related to SSNHL pathogenesis or serve as biomarkers for SSNHL.

The Expression Levels of MicroRNAs Differentially Expressed in Sudden Sensorineural Hearing Loss Patients' Serum Are Unchanged for up to 12 Months after Hearing Loss Onset

Sudden sensorineural hearing loss (SSNHL) is an acquired idiopathic hearing loss. Serum levels of small, non-coding RNAs and microRNAs (miRNAs) miR-195-5p/-132-3p/-30a-3p/-128-3p/-140-3p/-186-5p/-375-3p/-590-5p are differentially expressed in SSNHL patients within 28 days of hearing loss onset. This study determines if these changes persist by comparing the serum miRNA expression profile of SSNHL patients within 1 month of hearing loss onset with that of patients 3-12 months after hearing loss onset. We collected serum from consenting adult SSNHL patients at presentation or during clinic follow-up. We matched patient samples drawn 3-12 months after hearing loss onset (delayed group, n = 9 patients) by age and sex to samples drawn from patients within 28 days of hearing loss onset (immediate group, n = 14 patients). We compared the real-time PCR-determined expression levels of the target miRNAs between the two groups. We calculated the air conduction pure-tone-averaged (PTA) audiometric thresholds in affected ears at the initial and final follow-up visits. We undertook inter-group comparisons of hearing outcome status and initial and final PTA audiometric thresholds. There was no significant inter-group difference in miRNA expression level, hearing recovery status and initial and final affected ear PTA audiometric thresholds.

Integrating pharmacogenomics into clinical trials of hearing disorders

In 2019, the U.S. Food and Drug Administration issued guidance to increase the efficiency of drug development and support precision medicine, including tailoring treatments to those patients who will benefit based on genetic variation even in the absence of a documented mechanism of action. Although multiple advancements have been made in the field of pharmacogenetics (PGx) for other disease conditions, there are no approved PGx guidelines in the treatment of hearing disorders. In studies of noise-induced hearing loss (NIHL), some progress has been made in the last several years associating genomic loci with susceptibility to noise damage. However, the power of such studies is limited as the underlying physiological responses may vary considerably among the patient populations. Here, we have summarized previous animal studies to argue that NIHL subtyping is a promising strategy to increase the granularity of audiological assessments. By coupling this enhanced phenotyping capability with genetic association studies, we suggest that drug efficacy will be better predicted, increasing the likelihood of success in clinical trials when populations are stratified based on genetic variation or designed with multidrug combinations to reach a broader segment of individuals suffering or at risk from NIHL.

Genome-wide DNA methylation analysis of middle-aged and elderly monozygotic twins with age-related hearing loss in Qingdao, China

OBJECTIVE

To explore the differences in DNA methylation associated with age-related hearing loss in a study of 57 twin pairs from China.

DESIGN

Monozygotic twins were identified through the Qingdao Twin Registration system. The median age of participants was >50 years. Their hearing thresholds were measured using a multilevel pure-tone audiometry assessment. The pure-tone audiometry was calculated at low frequencies (0.5, 1.0, and 2.0 kHz), speech frequencies (0.5, 1.0, 2.0, and 4.0kHz), and high frequencies (4.0 and 8 kHz). The CpG sites were tested using a linear mixed-effects model, and the function of the cis-regulatory regions and ontological enrichments were predicted using the online Genomic Regions Enrichment of Annotations Tool. The differentially methylated regions were identified using a comb-p python library approach.

RESULTS

In each of the PTA categories (low-, speech-, high-frequency), age-related hearing loss was detected in 25.9%, 19.3%, and 52.8% of participants. In the low-, speech- and high-frequency categories we identified 18, 42, and 12 individual CpG sites and 6, 11, and 6 differentially methylated regions. The CpG site located near DUSP4 had the strongest association with low- and speech-frequency, while the strongest association with high-frequency was near C21orf58. We identified associations of ALG10 with high-frequency hearing, C3 and LCK with low- and speech-frequency hearing, and GBX2 with low-frequency hearing. Top pathways that may be related to hearing, such as the Notch signaling pathway, were also identified.

CONCLUSION

Our study is the first of its kind to identify these genes and their associated with DNA methylation may play essential roles in the hearing process. The results of our epigenome-wide association study on twins clarify the complex mechanisms underlying age-related hearing loss.

The role of hypoxia-associated miRNAs in acquired sensorineural hearing loss

Introduction: Sensorineural hearing loss (SNHL) is a prevalent sensory deficit presenting commonly as age-related hearing loss. Other forms of SNHL include noise-induced and sudden SNHL. Recent evidence has pointed to oxidative stress as a common pathogenic pathway in most subtypes of acquired SNHL. MicroRNAs (miRNAs) are small non-coding RNA sequences that suppress target mRNA expression and affect downstream processes. Many studies have shown that miRNAs are integral biomolecules in hypoxia-adaptive responses. They also promote apoptosis in response to oxidative stress resulting in SNHL. Our hypothesis is that miRNAs are involved in the pathophysiological responses to hypoxia and oxidative stress that result in SNHL. This study reviews the evidence for hypoxia-adaptive miRNAs (hypoxamiRs) in different types of acquired SNHL and focuses on miRNAs involved in hypoxia driven SNHL. Methods: Electronic bibliographic databases PubMed, Ovid MEDLINE, Ovid EMBASE, and Web of Science Core Collection were searched independently by two investigators for articles published in English from the inception of individual databases to the end of July 2020. The text word or medical subject heading searches of all fields, titles, abstracts, or subject headings depending on the database were undertaken with combinations of the words "microRNAs", "hypoxia", "hypoxamiRs", "oxidative stress", "ischemia" and "hearing loss". The reference lists of studies meeting the inclusion criteria were searched to identify additional relevant studies. The inclusion criteria included relevant clinical studies with human subjects, animals, and in vitro experiments. The risk of bias was assessed using the Cochrane risk of bias assessment tool for human studies and the Systematic Review Center for Laboratory animal Experimentation (SYRCLE) a risk of bias assessment tool for animal model and in vitro studies. Results: A total of 15 primary articles were selected for full text screening after excluding duplicates, reviews, retracted articles, and articles not published in English. All nine articles meeting the study inclusion criteria were from animal or in vitro model studies and were assessed to be at low risk of bias. miRNAs miR-34a and miR-29b were reported to be involved in SNHL in inner ear cell models exposed to oxidative stress. Signaling pathways Sirtuin 1/peroxisome proliferator-activated receptor gamma coactivator-1-alpha (SIRT1/PGC-1α), SIRT1/p53, and SIRT1/hypoxia-inducible factor 1-alpha (HIF-1α) were identified as underlying pathways involved in acquired SNHL. Conclusion: There is evidence that miR-34a and -29b are involved in hypoxia-driven and other causes of oxidative stress-related acquired SNHL. Further studies are required to determine if these findings are clinically applicable.

MiR-106a facilitates the sensorineural hearing loss induced by oxidative stress by targeting connexin-43

Sensorineural hearing loss (SNHL) is a common clinical side effect resulted from the overusing of aminoglycoside antibacterial drugs, such as gentamicin. Oxidative stress is recently evidenced to be an important inducer for SNHL, which is reported to be associated with the knockdown of connexin-43. MiR-106a is recently found as a regulator of connexin-43. The present study aims to investigate whether miR-106a is a vital mediator in the development of SNHL. Firstly, upregulated miR-106a was observed in the peripheral blood sample of SNHL patients. Glucose oxidase (GO) was utilized to induce oxidative injury in isolated rat cochlear marginal cells (MCs), followed by introducing the miR-106a inhibitor. We found that the declined proliferation ability, increased apoptosis, and activated oxidative stress in GO-stimulated MCs were dramatically abolished by the miR-106a inhibitor, accompanied by the upregulation of connexin-43. The targeting correlation between miR-106a and connexin-43 was predicted and confirmed by the dual luciferase gene reporter assay. Furthermore, the regulatory effect of miR-106a inhibitor against the proliferation, apoptosis, and oxidative stress in GO-treated MCs were dramatically abolished by the knockdown of connexin-43. Gentamicin was utilized to establish the SNHL model in rats, followed by the treatments of antagomir-106a and antagomir-106a combined with carbenoxolone, an inhibitor of connexin-43. The alleviated pathological state, reduced apoptosis, and ameliorated oxidative stress in cochlea tissues were observed in antagomir-106a treated SNHL rats, which were dramatically reversed by the co-administration of carbenoxolone. Collectively, miR-106a facilitated the SNHL induced by oxidative stress via targeting connexin-43.

Evaluating Neurotrophin Signaling Using MicroRNA Perilymph Profiling in Cochlear Implant Patients With and Without Residual Hearing

HYPOTHESIS

MicroRNAs predicted to regulate neurotrophin signaling can be found in human perilymph.

BACKGROUND

Animal and human temporal bone studies suggest that spiral ganglion health can affect cochlear implant (CI) outcomes. Neurotrophins have been identified as a key factor in the maintenance of spiral ganglion health. Changes in miRNAs may regulate neurotrophin signaling and may reflect neurotrophin expression levels.

METHODS

Perilymph sampling was carried out in 18 patients undergoing cochlear implantation or stapedotomy. Expression of miRNAs in perilymph was evaluated using an Agilent miRNA gene chip. Using ingenuity pathway analysis (IPA) software, miRNAs targeting neurotrophin signaling pathway genes present in a cochlear cDNA library were annotated. Expression levels of miRNAs in perilymph were correlated to the patients' preoperative pure-tone average.

RESULTS

Expression of mRNAs coding for neurotrophins and their receptors were identified in tissue obtained from normal human cochlea during skull base surgery. We identified miRNAs predicted to regulate these signaling cascades, including miR-1207-5p, miR-4651, miR-103-3p, miR-100-5p, miR-221-3p, miR-200-3p. There was a correlation between poor preoperative hearing and lower expression of miR-1207 (predicted to regulate NTR3) and miR-4651 (predicted to regulate NTR2). Additionally, miR-3960, miR-4481, and miR-675 showed significant differences in expression level when comparing mild and profound hearing loss patients.

CONCLUSIONS

Expression of some miRNAs that are predicted to regulate neurotrophin signaling in the perilymph of cochlear implant patients vary with the patient's level of residual hearing. These miRNAs may serve as biomarkers for changes in neurotrophin signaling.

MicroRNA Profiling as a Methodology to Diagnose Ménière's Disease: Potential Application of Machine Learning

OBJECTIVE

Diagnosis and treatment of Ménière's disease remains a significant challenge because of our inability to understand what is occurring on a molecular level. MicroRNA (miRNA) perilymph profiling is a safe methodology and may serve as a "liquid biopsy" equivalent. We used machine learning (ML) to evaluate miRNA expression profiles of various inner ear pathologies to predict diagnosis of Ménière's disease.

STUDY DESIGN

Prospective cohort study.

SETTING

Tertiary academic hospital.

SUBJECTS AND METHODS

Perilymph was collected during labyrinthectomy (Ménière's disease, n = 5), stapedotomy (otosclerosis, n = 5), and cochlear implantation (sensorineural hearing loss [SNHL], n = 9). miRNA was isolated and analyzed with the Affymetrix miRNA 4.0 array. Various ML classification models were evaluated with an 80/20 train/test split and cross-validation. Permutation feature importance was performed to understand miRNAs that were critical to the classification models.

RESULTS

In terms of miRNA profiles for conductive hearing loss versus Ménière's, 4 models were able to differentiate and identify the 2 disease classes with 100% accuracy. The top-performing models used the same miRNAs in their decision classification model but with different weighted values. All candidate models for SNHL versus Ménière's performed significantly worse, with the best models achieving 66% accuracy. Ménière's models showed unique features distinct from SNHL.

CONCLUSIONS

We can use ML to build Ménière's-specific prediction models using miRNA profile alone. However, ML models were less accurate in predicting SNHL from Ménière's, likely from overlap of miRNA biomarkers. The power of this technique is that it identifies biomarkers without knowledge of the pathophysiology, potentially leading to identification of novel biomarkers and diagnostic tests.

Circulating microRNAs as potentially new diagnostic biomarkers of idiopathic sudden sensorineural hearing loss

BACKGROUND

Early detection of inner ear cell damage can reduce the chances of permanent damage to hearing ability. However, current inner ear cell damage detection methods can detect damage only after the patient has lost hearing ability. MicroRNA expression levels in circulating systems are affected in diseases or conditions arising from the distant lesions. Therefore, detection of circulating microRNA expression levels could be one of the best ways to obtain information on inaccessible lesion sites.

AIMS/OBJECTIVES

This study aims to establish a method for monitoring idiopathic sudden sensorineural hearing loss (ISSNHL) by analyzing circulating microRNA expression levels. 21 ISSNHL patients and 24 healthy controls were enrolled.

MATERIAL AND METHODS

Real-time quantitative polymerase chain reaction was performed for detecting expression levels of circulating microRNAs.

RESULTS

Among eight circulating microRNAs, expression levels of five circulating microRNAs significantly differed between ISSNHL patients and healthy controls. circulating microRNA expression levels correlates with treatment outcomes and hearing ability.

CONCLUSIONS AND SIGNIFICANCE

Using methods combining the evaluation of miR-183, miR-210, miR-18b, and miR-23a cut-off values identified in ISSNHL patients and healthy controls during receiver operating characteristic curve analysis, sensitivity and specificity of 80.95% (17/21) and 87.50% (21/24) were obtained, respectively.

Study on the differentially expressed genes and signaling pathways in dermatomyositis using integrated bioinformatics method

Dermatomyositis is a common connective tissue disease. The occurrence and development of dermatomyositis is a result of multiple factors, but its exact pathogenesis has not been fully elucidated. Here, we used biological information method to explore and predict the major disease related genes of dermatomyositis and to find the underlying pathogenic molecular mechanism.The gene expression data of GDS1956, GDS2153, GDS2855, and GDS3417 including 94 specimens, 66 cases of dermatomyositis specimens and 28 cases of normal specimens, were obtained from the Gene Expression Omnibus database. The 4 microarray gene data groups were combined to get differentially expressed genes (DEGs). The gene ontology and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichments of DEGs were operated by the database for annotation, visualization and integrated discovery and KEGG orthology based annotation system databases, separately. The protein-protein interaction networks of the DEGs were built from the STRING website. A total of 4097 DEGs were extracted from the 4 Gene Expression Omnibus datasets, of which 2213 genes were upregulated, and 1884 genes were downregulated. Gene ontology analysis indicated that the biological functions of DEGs focused primarily on response to virus, type I interferon signaling pathway and negative regulation of viral genome replication. The main cellular components include extracellular space, cytoplasm, and blood microparticle. The molecular functions include protein binding, double-stranded RNA binding and MHC class I protein binding. KEGG pathway analysis showed that these DEGs were mainly involved in the toll-like receptor signaling pathway, cytosolic DNA-sensing pathway, RIG-I-like receptor signaling pathway, complement and coagulation cascades, arginine and proline metabolism, phagosome signaling pathway. The following 13 closely related genes, XAF1, NT5E, UGCG, GBP2, TLR3, DDX58, STAT1, GBP1, PLSCR1, OAS3, SP100, IGK, and RSAD2, were key nodes from the protein-protein interaction network.This research suggests that exploring for DEGs and pathways in dermatomyositis using integrated bioinformatics methods could help us realize the molecular mechanism underlying the development of dermatomyositis, be of actual implication for the early detection and prophylaxis of dermatomyositis and afford reliable goals for the curing of dermatomyositis.

MicroRNAs in Noise-Induced Hearing Loss and their Regulation by Oxidative Stress and Inflammation

Noise exposure (NE) has been recognized as one of the causes of sensorineural hearing loss (SNHL), which can bring about irreversible damage to sensory hair cells in the cochlea, through the launch of oxidative stress pathways and inflammation. Accordingly, determining the molecular mechanism involved in regulating hair cell apoptosis via NE is essential to prevent hair cell damage. However, the role of microRNAs (miRNAs) in the degeneration of sensory cells of the cochlea during NE has not been so far uncovered. Thus, the main purpose of this study was to demonstrate the regulatory role of miRNAs in the oxidative stress pathway and inflammation induced by NE. In this respect, articles related to noise-induced hearing loss (NIHL), oxidative stress, inflammation, and miRNA from various databases of Directory of Open Access Journals (DOAJ), Google Scholar, PubMed; Library, Information Science & Technology Abstracts (LISTA), and Web of Science were searched and retrieved. The findings revealed that several studies had suggested that up-regulation of miR-1229-5p, miR-451a, 185-5p, 186 and down-regulation of miRNA-96/182/183 and miR-30b were involved in oxidative stress and inflammation which could be used as biomarkers for NIHL. There was also a close relationship between NIHL and miRNAs, but further research is required to prove a causal association between miRNA alterations and NE, and also to determine miRNAs as biomarkers indicating responses to NE.

microRNAs in sudden hearing loss

OBJECTIVES

To compare the circulating microRNA (miRNA) expression profiles between sudden sensory neural hearing loss (SSNHL) patients and age-matched normal hearing controls.

STUDY DESIGN

Prospective cohort multi-center study.

METHODS

Patients presenting within 28 days of onset of SSNHL were prospectively recruited along with contemporaneous age-matched controls. Pooled sera of four patient (n = 09, mean age = 53.0 years; 07, 55.0; 10, 52.9; 10, 51.6) and two control (09, 51.2 and 03, 50.0) groups were assessed using a TaqMan Low Density Array. The patients' sera were also divided into two pools, untreated (04, 57.7) and treated (32, 52.6) for additional analysis. miRNA expression level was derived from cycle threshold (Ct) values normalized to a global mean. Inter-group mean Ct differences with fold changes ≥2.0 and ≤0.5 at P < .05 were considered significant. Bioinformatic databases were used to identify putative target mRNAs or validated genes and their functional annotations.

RESULTS

Thirty-six SSNHL patients (mean age 53.0 ± standard deviation (SD) 15.2 years) and 12 controls (50.9 ± 11.9) were studied. Eight miRNAs hsa-miR-590-5p/ -186-5p/ -195-5p/ -140-3p/ -128-3p/ -132-3p/ -375-3p, and -30a-3p were identified as significantly differentially expressed in SSNHL patients. Most of these miRNAs were abundantly identified in the nervous system and the putative target messenger RNAs (mRNAs) were enriched in signaling pathways such as phosphatidyl inositol 3 kinase/protein Kinase B (PI3K/Akt), Ras and mitogen-activated protein kinase (MAPK).

CONCLUSION

These findings suggest the possible cellular signaling pathways that underlie the disruption of auditory signal transmission in SSNHL.

LEVEL OF EVIDENCE

2 Laryngoscope, 130:E416-E422, 2020.

MicroRNAs in acquired sensorineural hearing loss

OBJECTIVE

This review summarises the current literature on the role of microRNAs in presbyacusis (age-related hearing loss) and sudden sensorineural hearing loss.

METHODS

Medline, PubMed, Web of Science and Embase databases were searched for primary English-language studies, published between 2000 and 2017, which investigated the role of microRNAs in the pathogenesis of presbyacusis or sudden sensorineural hearing loss. Quality of evidence was assessed using the National Institutes of Health quality assessment tool.

RESULTS

Nine of 207 identified articles, 6 of good quality, satisfied the review's inclusion criteria. In presbyacusis, microRNAs in pro-apoptotic and autophagy pathways are upregulated, while microRNAs in proliferative and differentiation pathways are downregulated. Evidence for microRNAs having an aetiological role in sudden hearing loss is limited.

CONCLUSION

A shift in microRNA expression, leading to reduced cellular activity and impaired inner-ear homeostasis, may contribute to the pathogenesis of presbyacusis.

Using Machine Learning to Predict Sensorineural Hearing Loss Based on Perilymph Micro RNA Expression Profile

Hearing loss (HL) is the most common neurodegenerative disease worldwide. Despite its prevalence, clinical testing does not yield a cell or molecular based identification of the underlying etiology of hearing loss making development of pharmacological or molecular treatments challenging. A key to improving the diagnosis of inner ear disorders is the development of reliable biomarkers for different inner ear diseases. Analysis of microRNAs (miRNA) in tissue and body fluid samples has gained significant momentum as a diagnostic tool for a wide variety of diseases. In previous work, we have shown that miRNA profiling in inner ear perilymph is feasible and may demonstrate distinctive miRNA expression profiles unique to different diseases. A first step in developing miRNAs as biomarkers for inner ear disease is linking patterns of miRNA expression in perilymph to clinically available metrics. Using machine learning (ML), we demonstrate we can build disease specific algorithms that predict the presence of sensorineural hearing loss using only miRNA expression profiles. This methodology not only affords the opportunity to understand what is occurring on a molecular level, but may offer an approach to diagnosing patients with active inner ear disease.