The understanding of tinnitus has always been elusive and is largely prevented by its intrinsic heterogeneity. To address this issue, scientific research has aimed at defining stable and easily identifiable subphenotypes of tinnitus. This would allow better disentangling the multiple underlying pathophysiological mechanisms of tinnitus. In this study, three-dimensionality reduction techniques and two clustering methods were benchmarked on a database of 2772 tinnitus patients in order to obtain a reliable segmentation of subphenotypes. In this database, tinnitus patients’ endotypes (i.e., parts of a population with a condition with distinct underlying mechanisms) are reported when diagnosed by an ENT expert in tinnitus management. This partial labeling of the dataset enabled the design of an original semi-supervised framework. The objective was to perform a benchmark of different clustering methods to get as close as possible to the initial ENT expert endotypes. To do so, two metrics were used: a primary one, the quality of the separation of the endotypes already identified in the database, as well as a secondary one, the stability of the obtained clusterings. The relevance of the results was finally reviewed by two ENT experts in tinnitus management. A 20-cluster clustering was selected as the best-performing, the most-clinically relevant, and the most-stable through bootstrapping. This clustering used a T-SNE method as the dimensionality reduction technique and a k-means algorithm as the clustering method. The characteristics of this clustering are presented in this article.

Introduction Tinnitus is a debilitating auditory symptom that globally impacts the quality of life of patients. Sound exposure, stress, and somatosensory stimuli (e.g. neck and jaw movements) are tinnitus modulators that have been commonly described and studied. Napping may also increase tinnitus loudness upon awakening in a minority of subjects. To our best knowledge this modulation and its potential pathophysiological mechanisms has never been systematically assessed. Methods For this observational prospective study, we studied 37 tinnitus subjects complaining of significant naps-related tinnitus modulations. All subjects performed 6 naps attempts under polysomnography over 2 days. Audiological, electrophysiological as well as jaw and neck muscles mobility and sensitivity assessments were completed before and after each nap. In addition, subjects filled a screening questionnaire and underwent a tinnitus pitch-matching procedure. Results 197 naps attempts were collected. It was confirmed that overall naps were increasing tinnitus loudness (p< 0.001). First naps of the day yielded more important tinnitus modulations than second (p< 0.05) and third naps (p< 0.01) suggesting a saturation effect. Analyses conducted so far highlight that nap sleep duration correlates with observed tinnitus modulation (p< 0.05) and that audiometric thresholds at tinnitus closest frequency do not seem to be affected by tinnitus modulation. Neither jaw mobility nor sensitivity were correlated with tinnitus modulation. Analyses to come will assess if sleep apnea, sleep bruxism, cervical mobility or sleep position may correlate with tinnitus nap modulations. Conclusion This study demonstrated that in a subgroup of tinnitus patients naps may modulate tinnitus. Nap sleep duration more than jaw muscles sensitivity seem to be correlated with these modulations. Support (if any) This study was supported by Felicia and Jean-Jacques Lopez-Loreta Foundation, Robin Guillard EIRL and Université Paris Cité VIFASOM