SYSTEMS AND METHODS FOR OBTAINING A CLINICAL RESPONSE ESTIMATE BIOMARKER USING MACHINE-LEARNED MODELS TRAINED ON IMPLANTED NEUROSTIMULATOR DATA

    公开(公告)号:US20220323019A1

    公开(公告)日:2022-10-13

    申请号:US17709159

    申请日:2022-03-30

    申请人: NeuroPace, Inc.

    IPC分类号: A61B5/00 G06N20/20

    摘要: A clinical response estimate (CRE) biomarker of a patient having an implanted neurostimulation system is monitored. To this end, an input dataset is derived from a subject-patient dataset that includes various different data types and different features of the patient. The data types are based on electrical activity the patient's brain sensed and stored by the implanted neurostimulation system. The input dataset is a subset of the larger subject-patient dataset, and the specific data types and patient features included in that subset are derived based on a plurality of key inputs of the subject-patient dataset. Once the input dataset is derived, it is processed by a clinical response estimator having machine-learned models. First and second machine-learned models of the clinical response estimator are applied to the input dataset to provide model inputs to an ensemble machine-learned model to determine the CRE biomarker.

    Multimodal brain sensing lead
    2.
    发明授权

    公开(公告)号:US11026617B2

    公开(公告)日:2021-06-08

    申请号:US16442424

    申请日:2019-06-14

    申请人: NeuroPace, Inc.

    发明人: Thomas K. Tcheng

    摘要: A medical lead with at least a distal portion thereof implantable in the brain of a patient is described, together with methods and systems for using the lead. The lead is provided with at least two sensing modalities (e.g., two or more sensing modalities for measurements of field potential measurements, neuronal single unit activity, neuronal multi unit activity, optical blood volume, optical blood oxygenation, voltammetry and rheoencephalography). Acquisition of measurements and the lead components and other components for accomplishing a measurement in each modality are also described as are various applications for the multimodal brain sensing lead.

    MULTIMODAL BRAIN SENSING LEAD
    3.
    发明申请

    公开(公告)号:US20190298211A1

    公开(公告)日:2019-10-03

    申请号:US16442424

    申请日:2019-06-14

    申请人: NeuroPace, Inc.

    发明人: Thomas K. Tcheng

    摘要: A medical lead with at least a distal portion thereof implantable in the brain of a patient is described, together with methods and systems for using the lead. The lead is provided with at least two sensing modalities (e.g., two or more sensing modalities for measurements of field potential measurements, neuronal single unit activity, neuronal multi unit activity, optical blood volume, optical blood oxygenation, voltammetry and rheoencephalography). Acquisition of measurements and the lead components and other components for accomplishing a measurement in each modality are also described as are various applications for the multimodal brain sensing lead.

    Responsive electrical stimulation for movement disorders

    公开(公告)号:US09186508B2

    公开(公告)日:2015-11-17

    申请号:US14059090

    申请日:2013-10-21

    申请人: NeuroPace, Inc.

    IPC分类号: A61N1/36

    CPC分类号: A61N1/36067 A61N1/36135

    摘要: An implantable neurostimulator system for treating movement disorders includes a sensor, a detection subsystem capable of identifying episodes of a movement disorder by analyzing a signal received from the sensor, and a therapy subsystem capable of supplying therapeutic electrical stimulation to treat the movement disorder. The system treats movement disorders by detecting physiological conditions characteristic of an episode of symptoms of the movement disorder and selectively initiating therapy when such conditions are detected.

    SYSTEMS AND METHODS FOR LABELING LARGE DATASETS OF PHYSIOLOGICAL RECORDS BASED ON UNSUPERVISED MACHINE LEARNING

    公开(公告)号:US20230017756A1

    公开(公告)日:2023-01-19

    申请号:US17948947

    申请日:2022-09-20

    申请人: NeuroPace, Inc.

    IPC分类号: G06K9/62 G06N3/08 G06F9/30

    摘要: A deep learning model and dimensionality reduction are applied to each of a plurality of records of physiological information to derive a plurality of feature vectors. A similarities algorithm is applied to the plurality of feature vectors to form a plurality of clusters, each including a set of feature vectors. An output comprising information that enables a display of one or more of the plurality of clusters is provided, and a mechanism for selecting at least one feature vector within a selected cluster of the plurality of clusters is enabled. Upon selection of a feature vector, an output comprising information that enables a display of the record of physiological information corresponding to the selected feature vector is provided, and a mechanism for assigning a label to the displayed record is enabled. The assigned label is then automatically assigned to the records corresponding to the remaining feature vectors in the selected cluster.

    SYSTEMS AND METHODS FOR LABELING LARGE DATASETS OF PHYSIOLOGIAL RECORDS BASED ON UNSUPERVISED MACHINE LEARNING

    公开(公告)号:US20200272857A1

    公开(公告)日:2020-08-27

    申请号:US16796692

    申请日:2020-02-20

    申请人: NeuroPace, Inc.

    IPC分类号: G06K9/62 G06N3/08 G06F9/30

    摘要: A deep learning model and dimensionality reduction are applied to each of a plurality of records of physiological information to derive a plurality of feature vectors. A similarities algorithm is applied to the plurality of feature vectors to form a plurality of clusters, each including a set of feature vectors. An output comprising information that enables a display of one or more of the plurality of clusters is provided, and a mechanism for selecting at least one feature vector within a selected cluster of the plurality of clusters is enabled. Upon selection of a feature vector, an output comprising information that enables a display of the record of physiological information corresponding to the selected feature vector is provided, and a mechanism for assigning a label to the displayed record is enabled. The assigned label is then automatically assigned to the records corresponding to the remaining feature vectors in the selected cluster.

    Systems and methods for clinical decision making for a patient receiving a neuromodulation therapy based on deep learning

    公开(公告)号:US10729907B2

    公开(公告)日:2020-08-04

    申请号:US15849492

    申请日:2017-12-20

    申请人: NeuroPace, Inc.

    摘要: Information relevant to making clinical decisions for a patient is identified based on electrical activity records of the patient's brain and electrical activity records of other patients' brains. A deep learning algorithm is applied to an electrical activity record of the patient, i.e., an input record, and to a set of electrical activity records of other patients, i.e., a set of search records, to obtain an input feature vector of the patient and a set of search feature vectors, each including features extracted by the deep learning algorithm. A similarities algorithm is applied to the input feature vector and the set of search feature vectors to identify a subset of search records most like the input record. Clinical information associated with one or more search records in the identified subset of search records is extracted from a database and used to make decisions regarding the patient's neuromodulation therapies.