Classifying Residual Inhibition in the Context of Tinnitus: An Interpretable Machine Learning Approach
Residual inhibition (RI) is a phenomenon observed in many tinnitus patients, where tinnitus remains temporarily suppressed for a short duration—typically less than a minute-after the cessation of an appropriate masking stimulus. Despite decades of clinical interest in RI, machine learning (ML)-based, feature-driven classification approaches remain scarce. In this study, we investigate the potential of ML models to classify RI by developing a dedicated data analysis pipeline. Given the heterogeneous nature of the features—including numerical, binary, and ordinal variables-we apply feature importance techniques tailored for mixed-type data to ensure a comprehensive evaluation and improve interpretability. Our results demonstrate a clear separation between RI classes, highlighting the relevance of specific clinical and audiological factors in distinguishing them. Building on this, we assess the predictive power of RI classifications with high confidence within a supervised learning framework to determine their relevance for treatment outcome prediction. While our findings confirm that RI can be effectively classified, they also suggest that RI alone is not sufficient to serve as a reliable predictor for treatment outcomes.
Authors
- Dimitrios Kikidis (ORCID: https://orcid.org/0000-0002-1445-5474)
- José A. López‐Escámez (ORCID: https://orcid.org/0000-0002-8583-1430)
- Milena Engelke (ORCID: https://orcid.org/0000-0002-7346-0441)
- Niklas K. Edvall (ORCID: https://orcid.org/0000-0002-6427-1198)
- Birgit Mazurek (ORCID: https://orcid.org/0000-0002-9587-6632)
- Christopher R. Cederroth (ORCID: https://orcid.org/0000-0001-7267-5136)
- Rilana Cima
- Patrick Neff (ORCID: https://orcid.org/0000-0003-3174-4910)
- Berthold Langguth (ORCID: https://orcid.org/0000-0002-7066-510X)
- Winfried Schlee (ORCID: https://orcid.org/0000-0001-7942-1788)
- Benjamin Noack (ORCID: https://orcid.org/0000-0001-8996-5738)
- Myra Spiliopoulou (ORCID: https://orcid.org/0000-0002-1828-5759)
- Stefan Schoisswohl (ORCID: https://orcid.org/0000-0003-3633-999X)
- Hafez Kader
- Steven C. Marcrum (ORCID: https://orcid.org/0000-0001-7639-5318)
Institutions
- The University of Sydney (AU)
- National and Kapodistrian University of Athens (GR)
- University of Zurich (CH)
- Karolinska Institutet (SE)
- University Hospital Regensburg (DE)
- University Hospital of Zurich (CH)
- Berlin Institute of Health at Charité - Universitätsmedizin Berlin (DE)
- Hippocration General Hospital (GR)
- University of Regensburg (DE)
- Otto-von-Guericke-Universität Magdeburg (DE)
- KU Leuven (BE)
Publication Details
- Published
- 2025-06-18
- DOI
- https://doi.org/10.1109/cbms65348.2025.00127
- Primary Topic
- Ocular and Laser Science Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00