Systems and methods for processing sonified brain signals

    公开(公告)号:US10849553B2

    公开(公告)日:2020-12-01

    申请号:US16367040

    申请日:2019-03-27

    Applicant: CeriBell, Inc.

    Abstract: Systems and methods for sonifying electrical signals obtained from a living subject, particularly EEG signals, are disclosed. A time-domain signal representing the activity of an organ is obtained. A voltage of the time-domain signal over a time block is determined. An acoustic signal based on the time-domain signal over the time block is produced. The acoustic signal comprises one or more audibly discernible variations representative of the activity of the organ. If the determined voltage is over a threshold voltage, the time-domain signal is squelched over at least a portion of the time-block as the acoustic signal is produced. The time-domain signal can be squelched by ramping down the signal as an input to produce the acoustic signal. The frequency spectrum of the acoustic signal can also be adjusted as it is produced, such as by flattening the signal and/or attenuating high frequencies along the frequency spectrum of the signal.

    SYSTEMS AND METHODS FOR SEIZURE PREDICTION AND DETECTION

    公开(公告)号:US20210085235A1

    公开(公告)日:2021-03-25

    申请号:US16923689

    申请日:2020-07-08

    Applicant: CeriBell, Inc.

    Abstract: The present disclosure provides systems and methods for seizure detection. The method for seizure detection may include receiving a plurality of electroencephalography (EEG) signals over a plurality of channels for a subject, preprocessing the plurality of EEG signals by segmenting the plurality of EEG signals for each channel into a plurality of temporal data segments, extracting a plurality of features from each temporal data segment for each channel, and applying a machine learning algorithm to the plurality of features to perform a seizure binary classification for each temporal data segment for each channel. A control policy may be employed to determine a seizure burden on the aggregated seizure binary classifications. When the seizure burden is equal to or exceeds a threshold, a notification may be generated. The notification may be usable by a healthcare practitioner to assess whether the subject may be at risk of having a seizure.

    Systems and methods for seizure prediction and detection

    公开(公告)号:US10743809B1

    公开(公告)日:2020-08-18

    申请号:US16578032

    申请日:2019-09-20

    Applicant: CeriBell, Inc.

    Abstract: The present disclosure provides systems and methods for seizure detection. The method for seizure detection may include receiving a plurality of electroencephalography (EEG) signals over a plurality of channels for a subject, preprocessing the plurality of EEG signals by segmenting the plurality of EEG signals for each channel into a plurality of temporal data segments, extracting a plurality of features from each temporal data segment for each channel, and applying a machine learning algorithm to the plurality of features to perform a seizure binary classification for each temporal data segment for each channel. A control policy may be employed to determine a seizure burden on the aggregated seizure binary classifications. When the seizure burden is equal to or exceeds a threshold, a notification may be generated. The notification may be usable by a healthcare practitioner to assess whether the subject may be at risk of having a seizure.

Patent Agency Ranking