Abstract: A method for determining a category responsive to a user query is disclosed. The method includes receiving a training data set comprising a plurality of data pairs, each data pair including: (i) a query; and (ii) an associated one or more categories that are responsive to the query, wherein the one or more categories in the training data set defines a plurality of categories. The method includes training a machine learning algorithm, according to the training data set, to create a trained model, wherein training the machine learning algorithm includes: creating a first co-occurrence data structure defining co-occurrence of respective word representations of the queries with the plurality of categories, and creating a second co-occurrence data structure defining co-occurrence of respective categories in respective data pairs. The method also includes deploying the trained model to return one or more categories in response to a new query input.

Abstract: A device that may include, or communicate with, sensors such as an electrocardiogram (ECG) sensor, an accelerometer, and/or a photoplethysmograph (PPG) detects sleep-disordered breathing (SDB) events of a patient based on signals from the sensors. The device may have a processor configured to make the detection(s). In an example, the processor may access a memory with processor control instructions. The instructions may be adapted to configure the processor to carry out the detection methodology. The method may include analysing an ECG data of the patient from a signal generated by the ECG sensor, pulse oximetry data of the patient from a signal generated by the PPG, and a three-dimensional (3D) accelerometry data of the patient from a signal generated by the accelerometer to detect the SDB events. The device and methods may be used for screening, diagnosis and monitoring of respiratory disorders.

Abstract: Disclosed is a cardio-pulmonary health monitoring apparatus. The apparatus comprises a contactless motion sensor configured to generate one or more movement signals representing bodily movement of a patient during a monitoring session; a processor; and a memory storing program instructions configured to cause the processor to carry out a method of processing the one or more movement signals. The method comprises extracting one or more sleep disordered breathing features from the one or more movement signals, and predicting whether a clinical event is likely to occur during a predetermined prediction horizon based on the one or more sleep disordered breathing features.

Abstract: A device that may include, or communicate with, sensors such as an electrocardiogram (ECG) sensor, an accelerometer, and/or a photoplethysmograph (PPG) detects sleep-disordered breathing (SDB) events of a patient based on signals from the sensors. The device may have a processor configured to make the detection(s). In an example, the processor may access a memory with processor control instructions. The instructions may be adapted to configure the processor to carry out the detection methodology. The method may include analysing an ECG data of the patient from a signal generated by the ECG sensor, pulse oximetry data of the patient from a signal generated by the PPG, and a three-dimensional (3D) accelerometry data of the patient from a signal generated by the accelerometer to detect the SDB events. The device and methods may be used for screening, diagnosis and monitoring of respiratory disorders.

Abstract: A method includes receiving physiological data associated with a user during at least a portion of an initial sleep session. The method also includes receiving demographic information associated with the user. The method also includes receiving subjective feedback associated with at least a portion of the initial sleep session from the user. The method also includes determining a profile for the user based at least in part on the physiological data associated with the user, the demographic information associated with the user, and the subjective feedback for the initial sleep session. The method also includes determining a recommended therapy for the user and one or more recommended parameters for the recommended therapy based at least in part on a comparison between the determined profile for the user and profiles associated with a plurality of other users.

Abstract: Disclosed is a cardio-pulmonary health monitoring apparatus. The apparatus comprises a contactless motion sensor configured to generate one or more movement signals representing bodily movement of a patient during a monitoring session; a processor; and a memory storing program instructions configured to cause the processor to carry out a method of processing the one or more movement signals. The method comprises extracting one or more sleep disordered breathing features from the one or more movement signals, and predicting whether a clinical event is likely to occur during a predetermined prediction horizon based on the one or more sleep disordered breathing features.

Abstract: A method of configuring a search engine to classify a search query includes receiving a search query data set, the search query data set comprising a plurality of search queries, defining a first set of candidate labels and a second set of candidate labels according to the search queries in the search query data set, concatenating the first set of candidate labels with the second set of candidate labels to generate a concatenated candidate label set, generating a compatibility matrix comprising a similarity between the concatenated candidate label set and the search query data set, and training a classification network according to the compatibility matrix.

Abstract: A method for optimizing sleep for a user of a respiratory therapy system is described herein. The method includes receiving therapy instructions to be implemented using the respiratory therapy system for a sleep session. The therapy instructions include a plurality of prescribed control parameters, each of the plurality of prescribed control parameters having a value or a range of values. The method further includes receiving a desired sleep comfort level for the sleep session, and adjusting one or more of the values or the range of values of the plurality of prescribed control parameters, to one or more adjusted values or range of values based on the desired sleep comfort level. The adjustments to the adjusted values are implemented to aid the user in achieving the desired sleep comfort level.

Abstract: A method includes receiving a plurality of product query arrays each including a plurality of individual product queries received during a single user search session. The method further includes inputting the plurality of product query arrays into the query rewrite model. Text of each of the plurality of individual product queries in each product query array is treated as a whole token. The method further includes receiving a product query from a user electronic device. The method further includes determining a query rewrite for the product query using the query rewrite model and determining search results for the product query using the query rewrite. The method further includes sending information for presenting the search results on a display of the user electronic device responsive to the product query.

Abstract: A method of configuring a search engine to classify a search query includes receiving a search query data set, the search query data set comprising a plurality of search queries, defining a first set of candidate labels and a second set of candidate labels according to the search queries in the search query data set, concatenating the first set of candidate labels with the second set of candidate labels to generate a concatenated candidate label set, generating a compatibility matrix comprising a similarity between the concatenated candidate label set and the search query data set, and training a classification network according to the compatibility matrix.

Abstract: A device that may include, or communicate with, sensors such as an electrocardiogram (ECG) sensor, an accelerometer, and/or a photoplethysmograph (PPG) detects sleep-disordered breathing (SDB) events of a patient based on signals from the sensors. The device may have a processor configured to make the detection(s). In an example, the processor may access a memory with processor control instructions. The instructions may be adapted to configure the processor to carry out the detection methodology. The method may include analysing an ECG data of the patient from a signal generated by the ECG sensor, pulse oximetry data of the patient from a signal generated by the PPG, and a three-dimensional (3D) accelerometry data of the patient from a signal generated by the accelerometer to detect the SDB events. The device and methods may be used for screening, diagnosis and monitoring of respiratory disorders.

Abstract: A method for determining that a patient interface component comprising a vent has been replaced between therapy sessions of treatment of sleep disordered breathing, the method comprising: acquiring or receiving first vent flow rate data representing one or more estimated first vent flow rates of gas through a first vent of a patient interface in use during a first therapy session; acquiring or receiving second vent flow rate data representing one or more estimated second vent flow rates of gas through a second vent of a patient interface in use during a second therapy session after the first therapy session; and identifying, by comparison of the second vent flow rate data to the first vent flow rate data, a difference in resistance to flow through the first vent than through the second vent indicating that the second vent is not the same vent as the first vent.

Abstract: A system and method to determine symptoms of respiratory ailments is disclosed. The system includes a transceiver operable to receive data from a monitor attached to a patient. The monitor includes a plurality of sensors, each of the plurality of sensors outputting physiological data related to respiration of the patient. An analytics platform is coupled to the transceiver to analyze the physiological data to determine the occurrence of a symptom of a respiratory condition, disorder or ailment in the patient.

Abstract: A device that may include, or communicate with, sensors such as an electrocardiogram (ECG) sensor, an accelerometer, and/or a photoplethysmograph (PPG) detects sleep-disordered breathing (SDB) events of a patient based on signals from the sensors. The device may have a processor configured to make the detection(s). In an example, the processor may access a memory with processor control instructions. The instructions may be adapted to configure the processor to carry out the detection methodology. The method may include analysing an ECG data of the patient from a signal generated by the ECG sensor, pulse oximetry data of the patient from a signal generated by the PPG, and a three-dimensional (3D) accelerometry data of the patient from a signal generated by the accelerometer to detect the SDB events. The device and methods may be used for screening, diagnosis and monitoring of respiratory disorders.

Abstract: A method for determining a category responsive to a user query is disclosed. The method includes receiving a training data set comprising a plurality of data pairs, each data pair including: (i) a query; and (ii) an associated one or more categories that are responsive to the query, wherein the one or more categories in the training data set defines a plurality of categories. The method includes training a machine learning algorithm, according to the training data set, to create a trained model, wherein training the machine learning algorithm includes: creating a first co-occurrence data structure defining co-occurrence of respective word representations of the queries with the plurality of categories, and creating a second co-occurrence data structure defining co-occurrence of respective categories in respective data pairs. The method also includes deploying the trained model to return one or more categories in response to a new query input.

Abstract: A method and apparatus monitors chronic disease state of a patient. The method may include extracting, in a processor, for each of a plurality of monitoring sessions, a respiratory feature from a respiratory signal indicative of the patient's respiration during the monitoring session, the respiratory signal derived from at least one sensor; and computing, in a processor, a stability measure of the patient for a monitoring session, the stability measure representing an indication of a change point having occurred at the monitoring session in a statistical distribution of the respiratory feature.

Abstract: A method and apparatus monitors chronic disease state of a patient. The method may include extracting, in a processor, for each of a plurality of monitoring sessions, a respiratory feature from a respiratory signal indicative of the patient's respiration during the monitoring session, the respiratory signal derived from at least one sensor; and computing, in a processor, a stability measure of the patient for a monitoring session, the stability measure representing an indication of a change point having occurred at the monitoring session in a statistical distribution of the respiratory feature.

Abstract: A method of configuring a search engine to classify a search query includes receiving a search query data set, the search query data set comprising a plurality of search queries, defining a first set of candidate labels and a second set of candidate labels according to the search queries in the search query data set, concatenating the first set of candidate labels with the second set of candidate labels to generate a concatenated candidate label set, generating a compatibility matrix comprising a similarity between the concatenated candidate label set and the search query data set, and training a classification network according to the compatibility matrix.

Abstract: Method and apparatus are disclosed for estimating job and career transition capabilities of candidates in a database. An example system for processing a search query indicative of a candidate to hire includes a database including records of a plurality of profiles, a network connector to provide access to the database via an application programming interface, and a computing device. The computing device periodically generates a first score representing a likelihood that a person associated with the respective profile will respond to a communication regarding a job in a particular category. The computing device also, in response to receiving a search query (a) generates a second score representing a probabilistic measurement of a likelihood that the person associated with the retrieved profile will change jobs, (b) generates a third score representative of a percentile level of activity associated with searching for a new job.

Abstract: A method includes receiving a plurality of product query arrays each including a plurality of individual product queries received during a single user search session. The method further includes inputting the plurality of product query arrays into the query rewrite model. Text of each of the plurality of individual product queries in each product query array is treated as a whole token. The method further includes receiving a product query from a user electronic device. The method further includes determining a query rewrite for the product query using the query rewrite model and determining search results for the product query using the query rewrite. The method further includes sending information for presenting the search results on a display of the user electronic device responsive to the product query.