Skip to main content

An intracochlear electrocochleography dataset: From raw data to objective analysis using deep learning


Schuerch, Klaus et al. (2023), An intracochlear electrocochleography dataset: From raw data to objective analysis using deep learning, Dryad, Dataset,


Electrocochleography (ECochG) measures electrophysiological inner ear potentials in response to acoustic stimulation. These potentials reflect the state of the inner ear and provide important information about its residual function. For cochlear implant (CI) recipients, we can measure ECochG signals directly within the cochlea using the implant electrode. We are able to perform these recordings during and at any point after implantation.
However, the analysis and interpretation of ECochG signals are not trivial. To assist the scientific community, we provide our intracochlear ECochG data set, which consists of approximately 5,000 signals recorded from 46 ears with a cochlear implant. We collected data either immediately after electrode insertion or postoperatively in subjects with residual acoustic hearing. This data descriptor aims to provide the research community access to our comprehensive electrophysiological data set and algorithms. It includes all steps from raw data acquisition to signal processing and objective analysis using Deep Learning. In addition, we collected subject demographic data, hearing thresholds, subjective loudness levels, impedance telemetry, radiographic findings, and classification of ECochG signals.

Usage notes

The database has been split into seven data parts and the empty Bern_ECochG database to facilitate downloading. Each part is saved as a .csv file and can be imported into the Bern_ECochG database individually. We recommend downloading all parts and assembling them using sqlitebrowser, available at The Python scripts provided will only work when the database is fully assembled. The Python scripts show how to access the database. Along with the Python scripts, a .yml file is provided to install all dependencies to run the scripts.


CTU Bern

Swiss National Science Foundation, Award: 320030_173081