Abstract: A computer-implemented method for determining a heart failure status of a patient, comprising the steps of providing a first data set comprising cardiac current curve data of a patient acquired by an implantable medical device, applying a first machine learning algorithm and/or a rule-based algorithm to the cardiac current curve data for classification of a medical relevance of a parameter deviation from a norm of the cardiac current curve data, and applying a second machine learning algorithm to the third data set for determining the heart failure status of the patient. In addition, the invention relates to a corresponding system and methods for providing a first and second trained machine learning algorithm respectively.

Abstract: Medical monitoring systems and methods for reducing the frequency of notifications of transient alarms are disclosed. A medical monitoring system can collect a signal representative of the physiological condition of a patient and can determine a physiological parameter using the collected signal. The medical monitoring system can detect an alarm condition for the physiological parameter. The medical monitoring system can then delay notification of the alarm condition until it persists for a predetermined alarm notification delay time.

Abstract: An inbound message including medical record content may be received. The inbound message may indicate a healthcare entity and a vendor entity. It may be determined, from the healthcare entity and stored correspondences between medical record formats and healthcare entities, that the medical record content of the inbound message is in a first medical record format. Which configuration record of stored configuration records specifying combinations of sets of rules may be determined to apply as a translation to the inbound message based upon the medical record content of the inbound message and the first medical record format. The sets of rules as indicated by the configuration record may be accessed and applied to the inbound message to translate the medical record content in the inbound message from the first medical record format to the standardized format. The standardized format may be transmitted to the vendor entity.

Abstract: Examples are directed to methods, devices, systems, computer-readable storage medium. An example non-transitory computer-readable storage medium comprises instructions that when executed cause a processing resource to present a graphical user interface (GUI) associated with a clinician portal, the GUI including a plurality of GUI portions that are individually and selectively displayable to present patient data for a plurality of patients based on at least one filter for different classes of the plurality of patients.

Abstract: A method is includes receiving a set of treatment plans that, when applied to patients, cause outcomes to be achieved by the patients, receiving a set of monetary value amounts associated with the set of treatment plans, receiving a set of constraints, where the set of constraints comprises rules pertaining to billing codes associated with the set of treatment plans. The method includes generating, by an artificial intelligence engine, customized treatment plans for a patient, where the generating is based on the set of treatment plans, the set of monetary value amounts, and the set of constraints. Each of the customized treatment plans complies with the set of constraints and represents a patient outcome and an associated monetary value amount generated. The method includes transmitting the customized treatment plans to a computing device. The method includes receiving a selection of a treatment plan and controlling an electromechanical machine.

Abstract: Systems and methods for monitoring heart failure status in a patient are discussed. A medical-device system receives physiological and clinical information of the patient, and classifies the patient into one of a plurality of phenotypes using the received information. The plurality of phenotypes each can be characterized by a cluster physiological, clinical, demographic, or comorbidity features in a multi-dimensional feature space. Based on the classified phenotype, a heart failure detector determines a heart failure detection setting for the patient, and detects a heart failure status in the patient using the heart failure detection setting. A therapy circuit can deliver or adjust a heart failure therapy in response to the detected heart failure status.

Abstract: Systems and methods include at least one processor performing adaptive exercise schedule modification operations comprising initially accessing exercise-related data, and based on the exercise-related data, controlling electronic exercise equipment to initiate an exercise session of an initial predetermined duration. The exercise session includes a series of varied electronically controlled exercises selected to further an exercise goal. The operations further include receiving input to modify the initial predetermined duration to an alternative duration, subsequently accessing the exercise-related data, and based on the alternative duration, the exercise-related data, a record of the series, and the exercise goal, adjusting the exercise session by altering a time of the exercise session and in a manner furthering the exercise goal.

Abstract: A method of treating the spine of a patient comprising capturing by a three-dimensional imaging and processing system electronic imaging data of at least the head and shoulder of the patient. The electronic imaging data includes at least images collected during rotation and tilting of the head and shoulders of the patient. A processor in electronic communication with the imaging system computes values representing rotational and tilt data of the head and shoulders from the electronic imaging data captured by the imaging system. Alignment data is computed from the stored values and a spinal treatment protocol is output to a database. The spinal treatment protocol is retrieved from the database and the spine of a patient is treated based on the spinal treatment protocol.

Abstract: Embodiments of the invention include a cloud-assisted rehabilitation system for assisting in the rehabilitation of musculoskeletal conditions, and a method for rehabilitating patients having musculoskeletal conditions. A rehabilitation portal can aggregate and de-identified musculoskeletal rehabilitation information that is gathered from various intelligent musculoskeletal rehabilitation apparatuses attached to a group of patients. The rehabilitation portal can facilitate crowd communication among the group of patients. A particular rehabilitation experience can be compared with other rehabilitation experiences and data from other patients. The rehabilitation portal can also facilitate crowd communication among a group of healthcare professionals so that the plurality of healthcare professionals can communicate with each other and compare information regarding different rehabilitation experiences based at least on the aggregated de-identified musculoskeletal rehabilitation information.

Abstract: A computer-implemented system assists resolution of service cases for medical imaging devices by retrieving device and case data, estimating likelihoods and timeframes for multiple resolution pathways, and presenting results in a user interface. Input may include images of device error messages captured by a camera; optical character recognition extracts text, and language detection and translation normalize messages for analysis. Models leverage historical repair data, technician profiles, and part replacement indicators to score pathways and forecast durations. A cost metric can combine likelihood and timeframe with service and scheduling costs to recommend actions and trigger service calls. The approach reduces downtime and improves dispatch and repair efficiency across customer and provider personnel.

Abstract: The present invention offers a novel, integrated, multi-source input, data-based personalized health, exercise and fitness system and method. The system offers personalized fitness plans based on a user's disparate input sources. The system can ingest both asynchronous and synchronous inputs to improve health fitness results. A screen with camera, preferably in a mirror design is a central component of the invention.

Abstract: A computer-implemented method is described for contextualizing medical events and detecting errors, for example, in claims data. The method may include receiving medical event data from one or more reporting entities, and converting the received data by normalizing and grouping by provider and by medical event. The converted data is presented to the subject of the medical event(s), via a user interface (UI). The UI includes one or more interactive graphical elements (e.g., virtual buttons) each configured to provide feedback on specific aspects of the converted data for the medical event. Based on input from the subject via the UI, it is determined whether the subject believes the received data is correct. If the data is indicated to be incorrect, further investigation may be triggered, and the payor and/or reporting entity may be alerted.

Abstract: A computer-implemented system and method enable real-time healthcare transaction processing based on ambient audio captured during physician-patient conversations. The system includes one or more microphones to receive spoken dialogue and a speech recognition engine to transcribe the audio into text. A natural language processing module analyzes the text to identify clinical intents corresponding to healthcare transactions. The identified intent is standardized into a structured query format and transmitted to an external system via a communications interface. In response, the system receives external data such as insurance coverage status, cost estimates, or authorization requirements. A user interface displays the external response in real time during the clinical encounter, allowing the physician or patient to make informed decisions. Additional modules may include context monitoring logic to suppress non-actionable utterances and a secure storage engine to log queries and responses.

Abstract: A method for determining a social health score for a region includes receiving first data for a geographical area. The first data includes values for multiple features corresponding to multiple domains (such as economic, education, and environmental). The method includes, for a first domain, selecting a first set of features (for example, an environmental domain may include a feature that describes the amount of the geographical area covered by impervious surfaces), and determining weights for the first set of features. The method includes receiving second data for the region and determining a first region domain score based on the second data and the first feature weights. The method includes determining a total score for the region based on the first region domain score that indicates a level of resource access for a population of the region.

Abstract: Provided herein are systems, methods, and apparatuses for providing a real-time global bio-surveillance and response solution. The systems and apparatuses may include one or more sentinel subsystems and one or more surge subsystems that each include a real-time, cloud-based, distributed, interconnected set of hardware, software, and/or firmware for comprehensive surveillance, complete detection, and immediate response various to biological, chemical, and/or bio-chemical anomalies, for example, a new or emerging pathogen or other health condition.

Abstract: A cloud-based, query management and education system enables provider organizations to query and educate clinicians on how to clarify clinical documentation, resulting in more accurate reimbursement, public reporting, research and policy decisions. Query authors create compliant queries from stored templates which may be supplemented by attaching and/or annotating selected documentation from the patient record. Clinician responses to such queries automatically generate addenda in the relevant patient record. All events around a query are tracked and reportable through a graphical performance scorecards and reporting dashboards.

Abstract: A clinical documentation improvement (CDI) smart scoring method may include predicting, via per-condition diagnosis machine learning (ML) models and based on clinical evidence received by a system, a probability that a medical condition is under-documented and, via per-condition documentation ML models and based on documentation received by the system, a probability that a medical condition is over-documented. The under- and over-documentation scores are combined in view of special indicators and queryability factors, which can also be evaluated using ML query prediction models, to generate an initial CDI score. This CDI score can be further adjusted, if necessary or desired, to account for factors such as length of stay, payer, patient location, CDI review timing, etc. The final CDI score can be used to prioritize patient cases for review by CDI specialists to quickly and efficiently identify meaningful CDI opportunities.

Abstract: A system and process for dynamically managing a procedure. The system includes a data collection device(s) that objectively monitor a subject and transmit such information to the system and real time position components that report on the availability of an individual(s) to perform the procedure. The system reviews the information, provides a subject diagnosis and recommends equipment. The system can also schedule and monitor the procedure. The individual(s) performing the procedure have the option of consulting with relevant experts and visually interacting with the experts.

Abstract: Point of care ultrasound examinations can be routed and processed in a computer network via the platforms, systems, and methods disclosed herein. The platforms, systems, and/or methods can use computing devices that are configured to provide a client application and at least one server processor for enabling use of an application. The examinations can be managed using an interface that allows an administrator user to assign user roles to other users, which can enable interactions within the network for processing and serving an ultrasound exam object. The ultrasound exam object can include patient data, images, and/or other relevant information.

Abstract: A computer-implemented method for determining risk scores using machine learning based on sensor data. The method includes receiving sensor data and demographic data for a user, determining a pattern of behavior based on the sensor data and demographic data, identifying a plurality of test groups based on other users that exhibit similar patterns of behavior to each other where sensor data from other users' electronic devices are received, identifying a test group corresponding to the user from among the plurality of test groups, determining a risk score using a trained risk analyzer machine learning model trained with historical sensor data, historical demographic data, and feedback data indicative of incidents, identifying risk mitigation strategies based on the risk score, refining the risk mitigation strategies using an iterative machine learning process as additional feedback data is collected, and retrieving risk mitigation communications from a database when the risk score exceeds a threshold.