Tinnitus risk factors and its evolution over time

Subjective tinnitus is an auditory percept unrelated to external sounds, for which the limited understanding of its risk factors complicates the prevention and management. In this study, we train two distinct machine learning models to predict tinnitus presence (how often individuals perceive tinnitus) and severity separately using socio-demographic, psychological, and health-related predictors with the UK Biobank dataset (192,993 participants, 41,042 with tinnitus). We show that hearing health was the primary risk factor of both presence and severity, while mood, neuroticism, and sleep predicted severity. The severity model accurately predicts tinnitus progression over nine years, with a large effect size for individuals developing severe tinnitus (Cohen's d = 1.3, ROC = 0.78). This result is validated on 463 individuals from the Tinnitus Research Initiative database. We simplify the severity model to a six-item clinical questionnaire that detects individuals at risk of severe tinnitus, for which early supportive care would be crucial.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2025-05-07
DOI
https://doi.org/10.1038/s41467-025-59445-3
Citations
9
Primary Topic
Hearing, Cochlea, Tinnitus, Genetics
Type
article
Field-Weighted Citation Impact
13.18

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Tinnitus risk factors and its evolution over time

Étienne Vachon‐Presseau, Christophe Tanguay-Sabourin, Alain Londero, Matthew Fillingim et al.
9 citations
Nature Communications
Hearing, Cochlea, Tinnitus, Genetics
13.18
article

Tinnitus risk factors and its evolution over time

Étienne Vachon‐Presseau, Christophe Tanguay-Sabourin, Alain Londero, Matthew Fillingim, Lise Hobeika, Mathieu Roy, Séverine Samson
article en
9 citations

Abstract

Subjective tinnitus is an auditory percept unrelated to external sounds, for which the limited understanding of its risk factors complicates the prevention and management. In this study, we train two distinct machine learning models to predict tinnitus presence (how often individuals perceive tinnitus) and severity separately using socio-demographic, psychological, and health-related predictors with the UK Biobank dataset (192,993 participants, 41,042 with tinnitus). We show that hearing health was the primary risk factor of both presence and severity, while mood, neuroticism, and sleep predicted severity. The severity model accurately predicts tinnitus progression over nine years, with a large effect size for individuals developing severe tinnitus (Cohen's d = 1.3, ROC = 0.78). This result is validated on 463 individuals from the Tinnitus Research Initiative database. We simplify the severity model to a six-item clinical questionnaire that detects individuals at risk of severe tinnitus, for which early supportive care would be crucial.

Nature CommunicationsVol. 16(1)
Centre National de la Recherche Scientifique (FR), Inserm (FR), Institut Pasteur (FR), Université Paris Cité (FR), Université de Lille (FR), McGill University Health Centre (CA), Sorbonne Université (FR), Assistance Publique – Hôpitaux de Paris (FR), Hôpital Lariboisière (FR), Pitié-Salpêtrière Hospital (FR), Institut du Cerveau (FR), McGill University (CA), Université de Montréal (CA)
Fondation Pour l'Audition, European Commission, Agence Nationale de la Recherche, Canada First Research Excellence Fund, Louise and Alan Edwards Foundation, Fondation des Gueules Cassées, HORIZON EUROPE Framework Programme, Canadian Institutes of Health Research, CIHR Skin Research Training Centre
Openalex Percentile: Top 1%
Hearing, Cochlea, Tinnitus, Genetics
13.18
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.