Explainable AI for Intraoperative Motor-Evoked Potential Muscle Classification in Neurosurgery: Bicentric Retrospective Study
This study demonstrates the effectiveness of ML techniques and the importance of XAI in enhancing trust in and reliability of artificial intelligence-driven IONM applications. Further, it may help to identify new intrinsic features of MEP signals so far overlooked in conventional warning criteria. By reducing the risk of muscle mislabeling and by providing the basis for possible new warning criteria, this study may help to increase patient safety during surgical procedures.
Authors
- Qendresa Parduzi (ORCID: https://orcid.org/0009-0007-2640-7246)
- Kathleen Seidel (ORCID: https://orcid.org/0000-0002-7360-3852)
- Jonathan Wermelinger (ORCID: https://orcid.org/0000-0003-1372-7690)
- Andreas Raabe (ORCID: https://orcid.org/0000-0002-3886-466X)
- Murat Sariyar (ORCID: https://orcid.org/0000-0003-3432-2860)
- Ulf C. Schneider (ORCID: https://orcid.org/0000-0001-7352-7645)
- Simon Domingo Koller
Institutions
- University of Bern (CH)
- Bern University of Applied Sciences (CH)
- University of Lucerne (CH)
- University Hospital of Bern (CH)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-02-04
- DOI
- https://doi.org/10.2196/63937
- Citations
- 6
- Primary Topic
- Intraoperative Neuromonitoring and Anesthetic Effects
- Type
- article
- Field-Weighted Citation Impact
- 12.04