Visualising large audiological data beyond the audiogram for auditory phenotyping
- 1University of Vic - Central University of Catalonia (UVic-UCC)
Abstract
The pure-tone audiogram remains the cornerstone of hearing assessment, yet it captures only part of the functional consequences of cochlear damage. Most phenotyping schemes rely solely on the audiogram, which cannot detect hidden suprathreshold dysfunction when thresholds are normal. How best to represent audiological data -- as discrete phenotypes or as a continuous space -- remains unresolved. Using a retrospective database from the Copenhagen Hearing and Balance Centre, Rigshospitalet (Denmark; 1995-2022; 251,986 ear-session units from 81,883 adults with normal or sensorineural audiograms), we compared linear (PCA) and non-linear (UMAP) embeddings of the audiogram alone and with word recognition in quiet (WRSmax-Q). Here we show that a linear embedding suffices for the audiogram, but a non-linear one becomes advantageous once suprathreshold measures are added. PCA compressed the audiogram onto two interpretable axes, overall level and slope, explaining 91.5% of the variance, with ears forming a continuous cloud that published reference schemes tiled into overlapping regions. For the audiogram alone, UMAP recovered the same organisation. WRSmax-Q varied widely among ears with similar audiograms; adding it left the PCA unchanged but reorganised the UMAP. A synthetic experiment illustrated this: ears with identical audiograms but different WRSmax-Q separated under UMAP, not PCA. Combining thresholds with WRSmax-Q, UMAP yielded a continuous representation -- a prototype Hearing Loss Map -- where each ears position reflects threshold and suprathreshold measures. Representing hearing loss as a location in a continuous space rather than as discrete categories may better reflect its graded nature, with clinical relevance for individual patients.
Related
- Auditory Brainstem abnormalities in infants exposed to congenital TORCH infections: implications for longitudinal audiological monitoring.
- Tricuspid Regurgitation in the Era of Transcatheter Intervention: Beyond Multivalvular Complexity Toward Hemodynamic Phenotyping
- Updated Guidelines for Best Practice in the Audiological Management of Adults with Severe and Profound Hearing Loss.
- Hearing thresholds among dental professionals and students: early identification of occupational hearing loss using conventional and advanced audiological assessments
- Larger Pre-Speech Auditory Modulation Is Associated With Smaller Corrective Responses To Auditory Errors
BibTeX
@misc{encinallamas2026visualising,
title = {{Visualising large audiological data beyond the audiogram for auditory phenotyping}},
author = {G. Encina-Llamas and E. Kjaerbol and A. A. Kressner},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.24.26363901},
url = {https://www.medrxiv.org/content/10.64898/2026.09.24.26363901v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Visualising large audiological data beyond the audiogram for auditory phenotyping
AU - G. Encina-Llamas
AU - E. Kjaerbol
AU - A. A. Kressner
PY - 2026
DA - 2026/09/24
PB - medRxiv
DO - 10.64898/2026.09.24.26363901
UR - https://www.medrxiv.org/content/10.64898/2026.09.24.26363901v1
AB - The pure-tone audiogram remains the cornerstone of hearing assessment, yet it captures only part of the functional consequences of cochlear damage. Most phenotyping schemes rely solely on the audiogram, which cannot detect hidden suprathreshold dysfunction when thresholds are normal. How best to represent audiological data -- as discrete phenotypes or as a continuous space -- remains unresolved. Using a retrospective database from the Copenhagen Hearing and Balance Centre, Rigshospitalet (Denmark; 1995-2022; 251,986 ear-session units from 81,883 adults with normal or sensorineural audiograms), we compared linear (PCA) and non-linear (UMAP) embeddings of the audiogram alone and with word recognition in quiet (WRSmax-Q). Here we show that a linear embedding suffices for the audiogram, but a non-linear one becomes advantageous once suprathreshold measures are added. PCA compressed the audiogram onto two interpretable axes, overall level and slope, explaining 91.5% of the variance, with ears forming a continuous cloud that published reference schemes tiled into overlapping regions. For the audiogram alone, UMAP recovered the same organisation. WRSmax-Q varied widely among ears with similar audiograms; adding it left the PCA unchanged but reorganised the UMAP. A synthetic experiment illustrated this: ears with identical audiograms but different WRSmax-Q separated under UMAP, not PCA. Combining thresholds with WRSmax-Q, UMAP yielded a continuous representation -- a prototype Hearing Loss Map -- where each ears position reflects threshold and suprathreshold measures. Representing hearing loss as a location in a continuous space rather than as discrete categories may better reflect its graded nature, with clinical relevance for individual patients.
ER -