Abstract: Embodiments of the invention provide methods for identifying suspect heart or lung sounds and methods for generating an isolated sound sample. In some embodiments, a method for identifying suspect heart or lung sounds comprises obtaining, by processing circuitry, an instance of data samples comprising at least two audio samples and respiratory and/or cardiac cycle data, the audio samples comprising auscultation sounds of an individual, based on the respiratory and/or cardiac cycle data, processing the at least two audio samples to generate a plurality of sound samples, identifying a primary sound sample, generating at least one of a modified secondary sound or a modified baseline sample and combining the modified secondary sound sample or the modified baseline sample with the primary sound sample to generate an isolated sound sample.

Abstract: A computing system includes a storage device and processing circuitry. The processing circuitry is configured to obtain an image frame that comprises a plurality of pixels that form a pixel array. Additionally, the processing circuitry is configured to determine that a region of the image frame belongs to a trigger content type. Based on determining that the region of the image frame belongs to the trigger content type, the processing circuitry is configured to modify the region of the image frame to adjust a luminance of pixels of the region of the image frame based on part on an ambient light level in a viewing area of the user; and output, for display by a display device in the viewing area of the user, a version of the image frame that contains the modified region.

Abstract: An example method includes obtaining first audio data representing one or more initial utterances during an interactive voice session with an interactive voice system (IVS); generating, based on the first audio data, a prediction regarding whether a subsequent utterance of the user in the interactive voice session will contain sensitive information; obtaining second audio data representing the subsequent utterance; determining, based on the prediction, whether to transmit the second audio data to the IVS via a first communication channel; based on a determination not to transmit the second audio data to the IVS via the first communication channel: transmitting third audio data to the IVS via the first communication channel in place of the second audio data; and transmitting the second audio data to a server via a second communication channel that bypasses the IVS.

Abstract: An example method comprises determining, by a computing system, that a message-sending computing device has received an indication of user input indicating an intent to send a message to a user of a message-recipient computing device; prior to the message being delivered to the message-recipient computing device, calculating, by the computing system, a screen sharing risk score (SSRS) that indicates a risk that the message-recipient computing device is currently sharing screen content of a screen of the message-recipient computing device with a screen-recipient computing device associated with an untrusted screen-recipient user; and based on the SSRS indicating that the risk is above a risk threshold, causing the message-sending computing device to output an alert indicating that the message-recipient computing device is possibly sharing the screen content of the message-recipient computing device with the screen-recipient computing device associated with the untrusted screen-recipient user.

Abstract: There is a need for more effective and efficient predictive data analysis. This need can be addressed by, for example, solutions for performing/executing demographic-aware federated machine learning. In one example, a method includes receiving local machine learning model data objects from model data object provider agents; for each inference-profile pair that is associated with a corresponding inference identifier and a corresponding model profile, generating a global machine learning model data object based at least in part on a related local model subset of the local machine learning model data objects for the inference-profile pair; and providing, based at least in part on each global machine learning model data object, a demographic-aware predictive data analysis application programming interface (API), wherein the demographic-aware predictive data analysis API is accessible by the model data object provider agents.

Abstract: Various embodiments of the present disclosure facilitate recommendation prediction using machine learning. In one example, an embodiment provides for generating embeddings data related to one or more provider entities, predicting a set of provider entities for a patient entity based on a provider machine learning model, ranking provider entities in the set of provider entities to generate a ranked set of provider entities, and performing one or more actions to provide a recommendation for the patient entity based on the ranked set of provider entities.

Abstract: A method comprising: monitoring, by a computing system, a callee device for missed phone calls from a caller; determining, by the computing system, based on a behavioral history of the callee, callee health parameters of the callee, and a number of the missed phone calls from the caller, whether an unresponsiveness condition is satisfied; and based on a determination that the unresponsiveness condition is satisfied and in response to a missed phone call from the caller, causing a caller device to present callee health data to the caller.

Abstract: A centrifuge includes a chamber configured to contain a set of one or more samples, an image sensor configured to generate image data, and processing circuitry. The processing circuitry is configured to: initiate centrifugation of the set of samples about a central axis; obtain a set of image data generated by the image sensor during centrifugation of the set of samples; and for each respective sample of the set of samples, apply a machine learning model configured to generate, based on image data representative of the respective sample in the set of image data, a viability score for the respective sample; determine whether the viability score for the respective sample satisfies a viability condition; and output whether the viability score for the respective sample satisfies the viability condition.

Abstract: Methods, apparatuses, systems, computing devices, and/or the like are provided. An example method may include generating edges connecting attribute vertices to a member vertex in a healthcare graph data object, determining, using at least one graph-based machine learning model and based at least in part on the attribute vertices, historical member vertices from the healthcare graph data object, determining, using the at least one graph-based machine learning model and based at least in part on the historical member vertices, historical member query vertices from the healthcare graph data object, generating, based at least in part on the historical member query vertices, predicted member query vertices in the healthcare graph data object, and performing one or more prediction-based actions based at least in part on the one or more predicted member query vertices.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing predictive data analysis. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform predictive data analysis by using affirmative fingerprint distance measures and negative fingerprint distance measures.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing predictive data analysis operations. For example, certain embodiments of the present invention utilize systems, methods, and computer program products that perform predictive data analysis operations by an end-to-end machine learning framework that performs at least the following steps/operations: (i) a service request data object is processed by a diagnosis prediction machine learning model to generate a probabilistic diagnosis data object, (ii) the probabilistic diagnosis data object is processed by the hybrid diagnosis-provider classification machine learning model to generate a variable-length classification for the service request data object, and (iii) the variable-length classification is processed by a telehealth visit recommendation scoring machine learning model to generate a telehealth visit recommendation score for the service request data object.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing predictive data analysis operations. For example, certain embodiments of the present invention utilize systems, methods, and computer program products that perform predictive data analysis operations by generating predicted redirection scores based at least in part on: (i) generic redirection scores that are generated using provider evaluation machine learning models, and (ii) real-time redirection scores that are generated using real-time adjustment machine learning models.

Abstract: An example method includes obtaining, by processing circuity, an image depicting a face of a person wearing eyewear and a reflection pattern generated by projecting light onto a lens of the eyewear and determining, by the processing circuitry, an optical parameter of the lens based on the image. The method further includes receiving, by the processing circuitry and from an electronic database, a personal characteristic data relating to a previously identified person and comparing, by the processing circuitry, the optical parameter of the lens to the personal characteristic data. The method further includes determining, by the processing circuitry and based on the comparison, a score indicative of a match between the person wearing eyewear and the previously identified person.

Abstract: Various embodiments of the present disclosure provide methods, apparatuses, systems, computing devices, computing entities, and/or the like for providing audio stimulation and monitoring patient response information associated therewith. For example, various embodiments provide techniques for generating audio treatment profiles using audio stimulus prediction machine learning models and for use in conjunction with patient monitoring devices.

Abstract: A system and method for selecting a user profile for use with a platform based on an optimal persona of the user includes inferring a context of a user based on data received from a plurality of data sources, determining a persona of the user according to the context of the user from a plurality of user personas, and selecting a user profile associated with a platform that corresponds to the persona, in response to detecting that the user is accessing the platform.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing predictive data analysis operations. For example, certain embodiments of the present invention utilize systems, methods, and computer program products that perform predictive data analysis operations by an end-to-end machine learning framework that performs at least the following steps/operations: (i) a service request data object is processed by a diagnosis prediction machine learning model to generate a probabilistic diagnosis data object, (ii) the probabilistic diagnosis data object is processed by the hybrid diagnosis-provider classification machine learning model to generate a variable-length classification for the service request data object, and (iii) the variable-length classification is processed by a recommendation scoring machine learning model to generate a consultation recommendation score for the service request data object.

Abstract: Apparatus, systems, and methods for real time monitoring of a patient's breathing utilizing automatically controlled devices and machine learning based techniques to determine a full breath of a patient and to identify splinting points, and to thereby transmit stimulation signals to the patient so as to assist the patient breathe through splinting points. In some embodiments, a wearable breathing monitoring device comprising of one or more sensors configured to monitor the user's breathing and a stimulator apparatus comprising one or more transmitters configured to transmit stimulation signals to the patient at a time corresponding to a detected splinting point is provided. The stimulator apparatus is configured to apply electrical pulses according to a stimulation schedule via the transmitters to target nerves of the user's body.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing natural language processing (NLP) operations on multi-segment documents. For example, certain embodiments of the present invention utilize systems, methods, and computer program products that perform NLP operations on multi-segment documents by generating document segmentation machine learning models, using document segmentation machine learning models to determine document segments of input multi-segment documents, enabling adaptive multi-segment summarization of multi-segment documents, and enabling guided interaction with multi-segment documents.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing optimized breathing therapy. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform optimized breathing therapy using at least one of interruption score generation machine learning models, observed inspiration-expiration pattern, expected inspiration-expiration patterns, expected musical patterns, and inferred musical patterns.

Abstract: Various embodiments of the present disclosure provide methods, apparatuses, systems, computing devices, computing entities, and/or the like for monitoring a user's movement in real-time and providing or augmenting stimulation. For example, various embodiments provide techniques generating movement prediction profiles using movement prediction machine learning models and for use in conjunction with wearable devices.