ECochG is used to monitor the inner ear function of cochlear implant patients during surgery, but currently does not detect trauma with high sensitivity. Trauma detection could be improved by simultaneously recording electric impedance data. But this combination is rarely used because the impedance measurements produce artifacts in the ECochG traces.
To overcome this shortcoming, the HRL Lab has developed, tested, and validated a framework for automated real-time analysis of intraoperative ECochG signals using Autonomous Linear State-Space Models (ALSSMs).
Prof. Dr. med. Stefan Weder, research team leader Auditory Pathway at the ARTORG center “Our methodology offers several advantages. Firstly, it allows us to effectively remove interfering artefacts from the signals. This helps to improve the signal-to-noise ratio, making the recordings more reliable and accurate. Additionally, our methodology enables real-time monitoring and objective evaluation of various ECochG and impedance features. The method thus becomes independent of an expert and will lead to an improved understanding of intracochlear electrophysiological changes during the implantation procedure.”
Testing results from simulation data show that the ALSSM method provides improved accuracy in the amplitude estimation and a more robust confidence metric of ECochG signals compared to the state-of-the-art methods. A first validation with patient data shows promising clinical applicability and consistency with simulation findings, pointing to ALSSMs a valid tool for real-time analysis of ECochG recordings.
Further validation of the algorithms in clinical data is needed.
