Mapping the Diagnostic Space of Auditory Brainstem Responses: An Interpretable Framework for Classification
- 1Fundation IRCCS Neurological Institute Carlo Besta
Abstract
BackgroundAuditory Brainstem Responses (ABRs) are objective and highly standardized evoked potentials, but their clinical interpretation still largely depends on expert visual assessment. Most automated ABR approaches focus on signal detection, threshold estimation, or waveform recognition, whereas the diagnostic reasoning linking ABR features to clinically meaningful categories remains insufficiently formalized.
MethodsWe developed a theoretical, rule-based framework for ABR classification. Nine clinically relevant descriptors were defined: amplitudes of waves I, III, and V; latencies of waves I, III, and V; the I/V amplitude ratio; and the I-V and III-V interpeak intervals. The complete theoretical combinatorial space was generated and progressively reduced using rules that accounted for non-applicable descriptors, algebraic consistency, and neurobiological plausibility. Two expert raters independently labeled valid configurations and compared with language-model-assisted and logic-based rule systems. Agreement was assessed using percentage concordance and Cohens O_SCPLOWKC_SCPLOWO_SCPCAP.C_SCPCAP Descriptor importance was explored using Random Forest analysis.
ResultsThe initial space of 5,832 possible ABR configurations was reduced to 343 valid configurations. Expert raters showed high agreement, with 84.55% concordance and Cohens O_SCPLOWKC_SCPLOW = 0.620. Agreement between expert classifications and language-model-assisted rules was lower, whereas logic-based rules showed higher agreement with both raters and were retained as the final proposed rule set. The diagnostic space was highly asymmetric, with NORM, PPSHA, and PPC occupying narrow regions, and PB and MIXED representing broader diagnostic domains. Wave I amplitude was the most influential descriptor across classification agents.
ConclusionsThis work provides an interpretable framework for ABR classification by transforming a broad theoretical combinatorial space into a constrained diagnostic domain. This proof-of-concept study supports the feasibility of modelling ABR interpretation as a structured diagnostic space grounded in auditory neurobiology, providing a reproducible foundation for future clinical validation and semi-automated decision-support tools.
HighlightsO_LIAuditory Brainstem Response (ABR) interpretation can be formalized as a constrained diagnostic space. C_LIO_LIA theoretical space of 5,832 ABR configurations was reduced to 343 valid patterns. C_LIO_LILogic-based rules provided an interpretable bridge between ABR descriptors and diagnostic classification. C_LI
Related
- KT-CBHNET: a spatio-temporal deep learning framework for interpretable ECG signal classification for cardiovascular disease prediction
- The value of brainstem auditory evoked potentials in the diagnostic assessment of dysphagia after craniocerebral injury.
- Normal Early Investigations Do Not Exclude Bickerstaff Brainstem Encephalitis: Highlighting Diagnostic and Treatment Pitfalls
- Brainstem Cavernous Malformation Mimicking Glioma in Neurofibromatosis Type 1: A Rare Diagnostic Pitfall.
- Interpretable Diabetic Retinopathy Classification Using Hybrid ConvNeXt–MLP-Mixer and ConvNeXt–PoolFormer Architectures
BibTeX
@misc{clementi2026mapping,
title = {{Mapping the Diagnostic Space of Auditory Brainstem Responses: An Interpretable Framework for Classification}},
author = {L. Clementi and D. Cazzato and E. Visani and M. Nicolis Di Robilant and A. Gallone and V. Iacobelli and P. Lanteri and D. Rossi Sebastiano},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.14.26363001},
url = {https://www.medrxiv.org/content/10.64898/2026.09.14.26363001v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Mapping the Diagnostic Space of Auditory Brainstem Responses: An Interpretable Framework for Classification
AU - L. Clementi
AU - D. Cazzato
AU - E. Visani
AU - M. Nicolis Di Robilant
AU - A. Gallone
AU - V. Iacobelli
AU - P. Lanteri
AU - D. Rossi Sebastiano
PY - 2026
DA - 2026/09/14
PB - medRxiv
DO - 10.64898/2026.09.14.26363001
UR - https://www.medrxiv.org/content/10.64898/2026.09.14.26363001v1
AB - BackgroundAuditory Brainstem Responses (ABRs) are objective and highly standardized evoked potentials, but their clinical interpretation still largely depends on expert visual assessment. Most automated ABR approaches focus on signal detection, threshold estimation, or waveform recognition, whereas the diagnostic reasoning linking ABR features to clinically meaningful categories remains insufficiently formalized. MethodsWe developed a theoretical, rule-based framework for ABR classification. Nine clinically relevant descriptors were defined: amplitudes of waves I, III, and V; latencies of waves I, III, and V; the I/V amplitude ratio; and the I-V and III-V interpeak intervals. The complete theoretical combinatorial space was generated and progressively reduced using rules that accounted for non-applicable descriptors, algebraic consistency, and neurobiological plausibility. Two expert raters independently labeled valid configurations and compared with language-model-assisted and logic-based rule systems. Agreement was assessed using percentage concordance and Cohens O_SCPLOWKC_SCPLOWO_SCPCAP.C_SCPCAP Descriptor importance was explored using Random Forest analysis. ResultsThe initial space of 5,832 possible ABR configurations was reduced to 343 valid configurations. Expert raters showed high agreement, with 84.55% concordance and Cohens O_SCPLOWKC_SCPLOW = 0.620. Agreement between expert classifications and language-model-assisted rules was lower, whereas logic-based rules showed higher agreement with both raters and were retained as the final proposed rule set. The diagnostic space was highly asymmetric, with NORM, PPSHA, and PPC occupying narrow regions, and PB and MIXED representing broader diagnostic domains. Wave I amplitude was the most influential descriptor across classification agents. ConclusionsThis work provides an interpretable framework for ABR classification by transforming a broad theoretical combinatorial space into a constrained diagnostic domain. This proof-of-concept study supports the feasibility of modelling ABR interpretation as a structured diagnostic space grounded in auditory neurobiology, providing a reproducible foundation for future clinical validation and semi-automated decision-support tools. HighlightsO_LIAuditory Brainstem Response (ABR) interpretation can be formalized as a constrained diagnostic space. C_LIO_LIA theoretical space of 5,832 ABR configurations was reduced to 343 valid patterns. C_LIO_LILogic-based rules provided an interpretable bridge between ABR descriptors and diagnostic classification. C_LI
ER -