# US 11,439,826 B2 · Systems and methods for clinical decision making for a patient receiving a neuromodulation therapy based on deep learning > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,439,826 B2 - Document ID: US11439826B2 - Status: Granted - Kind: B2 - Application number: 16/906,914 - Filed: 2020-06-19 - Published: 2020-10-08 - Granted: 2022-09-13 - Earliest claimed: 2017-10-20 - Assignees: NeuroPace, Inc. - Applicants: NeuroPace, Inc. - Inventors: Sharanya Arcot Desai; Thomas K. Tcheng - Web page: https://patentgrep.com/patent/US11439826B2 ## CPC - A61N 1/36139: {with automatic adjustment} - A61N 1/0534: {Electrodes for deep brain stimulation} - A61N 1/37247: {User interfaces, e.g. input or presentation means} - G16H 20/40: relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients - A61N 1/36064: {Epilepsy} - A61N 1/36171: {Frequency} - A61N 1/36175: {Pulse width or duty cycle} - A61N 1/36178: {Burst or pulse train parameters} - G16H 20/70: relating to mental therapies, e.g. psychological therapy or autogenous training - A61N: ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY (measurement of bioelectric currents A61B; surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body A61B18/00; anaesthetic apparatus in general A61M; incandescent lamps H01K; infrared radiators for heating H05B) - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract 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. ## Claims ### Claim 1 A method of selecting stimulation parameter settings for a neurostimulation system associated with a patient, the method comprising: obtaining at least one input feature vector comprising a plurality of different features extracted by a deep learning algorithm from at least one input record of the patient; obtaining a set of search feature vectors, each comprising a plurality of different features extracted by a deep learning algorithm from a search record included in a set of search records of other patients; applying a similarities algorithm to the at least one input feature vector and the set of search feature vectors to identify a subset of search records having a measure of similarity with the at least one input record, which measure meets a predetermined criterion; and extracting from a database, clinical information associated with one or more of the search records of other patients in the identified subset of search records of other patients, the clinical information comprising the stimulation parameter settings of other patients for the neurostimulation system, wherein the stimulation parameter settings of other patients define a stimulation therapy deliverable by the neurostimulation system and comprise at least one of amplitude, pulse width, burst duration, and frequency. ### Claim 2 (depends on 1) The method of claim 1, wherein the extracted clinical information further comprises at least one of associated patient clinical responses, clinical history, past detection parameter settings, past stimulation settings, and past and current drug type and dosage information. ### Claim 3 (depends on 1) The method of claim 1, further comprising: extracting one or more search records included in the identified subset of search records from the database; and providing an output to a user interface, the output comprising information that enables a user device to display the one or more search records. ### Claim 4 (depends on 1) The method of claim 1, wherein obtaining at least one input feature vector comprises: receiving an input record of the patient; and applying a deep learning algorithm to the input record to extract the different features from the input record and derive a single input feature vector corresponding to the at least one input feature vector. ### Claim 5 (depends on 1) The method of claim 1, wherein obtaining at least one input feature vector comprises: receiving a plurality of input records of the patient; and separately applying a deep learning algorithm to each of the plurality of input records to extract the different features from each of the input records and derive a plurality of input feature vectors corresponding to the at least one input feature vector. ### Claim 6 (depends on 5) The method of claim 5, wherein obtaining at least one input feature vector further comprises: applying a similarities algorithm to the plurality of input feature vectors to identify one of the plurality of input feature vectors as a single input feature vector corresponding to the at least one input feature vector. ### Claim 7 (depends on 5) The method of claim 5, wherein obtaining at least one input feature vector further comprises: grouping the plurality of input feature vectors into sets of input feature vectors based on a common piece of information associated with the input records corresponding to the input feature vectors; and separately applying a similarities algorithm to each set of input feature vectors to identify one of the input features vectors from each set of input feature vectors as one of the plurality of input feature vectors corresponding to the at least one input feature vector. ### Claim 8 (depends on 7) The method of claim 7, wherein the information associated with the input records indicates whether an input record resulted from one of: 1) detection of an abnormal neurological event, 2) patient initiated recording and storage, 3) periodic automated recording and storage, or 4) periodic recording and storage of baseline, normal neurological activity. ### Claim 9 (depends on 1) The method of claim 1, wherein obtaining a set of search feature vectors comprises: receiving the set of search records of other patients; and separately applying the deep learning algorithm to each search record in the set of search records to derive the set of search feature vectors. ### Claim 10 (depends on 1) The method of claim 1, wherein obtaining a set of search feature vectors comprises accessing a database that stores a plurality of search feature vectors. ### Claim 11 (depends on 1) The method of claim 1, wherein applying a similarities algorithm to the at least one input feature vector and the set of search feature vectors comprises, in instances where a plurality of input feature vectors is obtained, separately applying the similarities algorithm to each of the plurality of input feature vectors and the set of search feature vectors to identify a separate subset of search records for each input record. ### Claim 12 (depends on 1) The method of claim 1, wherein the input record and each search record included in the set of search records are in a same format comprising one of data sample of a time series waveform, a time-series waveform image, and a spectrogram image. ### Claim 13 A processor for selecting stimulation parameter settings for a neurostimulation system associated with a patient, the processor comprising: a similarities module configured to: obtain at least one input feature vector comprising a plurality of different features extracted by a deep learning algorithm from at least one input record of the patient; obtain a set of search feature vectors, each comprising a plurality of different features extracted by a deep learning algorithm from a search record included in a set of search records of other patients; apply a similarities algorithm to the at least one input feature vector and the set of search feature vectors to identify a subset of search records having a measure of similarity with the at least one input record, which measure meets a predetermined criterion; and an extraction module configured to extract from a database, clinical information associated with one or more of the search records of other patients in the identified subset of search records of other patients, the clinical information comprising the stimulation parameter settings of other patients for the neurostimulation system, wherein the stimulation parameter settings of other patients define a stimulation therapy deliverable by the neurostimulation system and comprise at least one of amplitude, pulse width, burst duration, and frequency. ### Claim 14 (depends on 13) The processor of claim 13, wherein the extracted clinical information further comprises associated patient clinical responses, clinical history, past detection parameter settings, past stimulation settings, and past and current drug type and dosage information. ### Claim 15 (depends on 13) The processor of claim 13, wherein the extraction module is further configured to: extract one or more search records included in the identified subset of search records from the database; and provide an output to a user interface, the output comprising information that enables a user device to display the one or more search records. ### Claim 16 (depends on 13) The processor of claim 13, further comprising a feature extraction module configured to: receive an input record of the patient; and apply a deep learning algorithm to the input record, the deep learning algorithm configured to extract the different features from the input record and derive a single input feature vector corresponding to the at least one input feature vector. ### Claim 17 (depends on 13) The processor of claim 13, further comprising a feature extraction module configured to: receive a plurality of input records of the patient; and separately apply a deep learning algorithm to each of the plurality of input records, the deep learning algorithm configured to extract the different features from the input record and derive a plurality of input feature vectors corresponding to the at least one input feature vector. ### Claim 18 (depends on 17) The processor of claim 17, wherein the feature extraction module is further configured to: apply a similarities algorithm to the plurality of input feature vectors, the similarities algorithm configured to identify one of the plurality of input feature vectors as a single input feature vector corresponding to the at least one input feature vector. ### Claim 19 (depends on 17) The processor of claim 17, wherein the feature extraction module is further configured to: group the plurality of input feature vectors into sets of input feature vectors based on a common piece of information associated with the input records corresponding to the input feature vectors; and separately apply a similarities algorithm to each set of input feature vectors, the similarities algorithm configured to identify one of the input features vectors from each set of input feature vectors as one of the plurality of input feature vectors corresponding to the at least one input feature vector. ### Claim 20 (depends on 13) The processor of claim 13, further comprising a feature extraction module configured to: receive the set of search records of other patients; and separately apply the deep learning algorithm to each search record in the set of search records, the deep learning algorithm configured to derive the set of search feature vectors. ### Claim 21 (depends on 13) The processor of claim 13, wherein the clinical information further comprises detection parameter settings that define a pattern detectable by the neurostimulation system in an electrical brain activity signal sensed by the neurostimulation system, wherein a detection of the pattern by the neurostimulation system corresponds to an event.