Abstract: Systems and methods for managing patient diagnostic and therapy workflows in a hospital and/or radiology centers. A radiology recommendation agent is trained using reinforcement learning and a simulation environment in which the agent takes actions and receives feedback from the simulation environment based on how its action affect the simulation environment over time.

Abstract: Various systems, devices, and methods for predicting and identifying root causes of pressure injuries in a clinical environment are described. An example method includes identifying, based on an electronic medical record (EMR) of a patient, that the patient has an injury; receiving, from one or more sensors, sensor data indicating one or more parameters of the patient; determining, based on the sensor data, at least one root cause of the injury; and transmitting, to an external computing device, a report indicating the at least one root cause of the injury.

Abstract: A method of generating physical activity recommendations comprising: calculating an active time and a moderate time based on user historical data comprising data of physical activities of a user, the active time representing an amount of time of physical activities with any intensity that the user performed in a period of analysis and the moderate time representing an the amount of time of physical activities with an intensity higher than a predetermined threshold performed by the user during the period of analysis. The method includes calculating a user state representing a current amount of physical activities performed by the user in the period of analysis; and determining a goal recommendation for a subsequent period and a target amount of physical activity, wherein the goal recommendation comprises a goal for the active time and a goal for the moderate time to increase, decrease or maintain the amount of physical activities.

Abstract: This disclosure is directed to modifying a computing record based on generating and updating a computing report associated with an event. The disclosed method includes: receiving a first source file associated with an event; generating a first computing record based on the first source file; determining, based on the first computing record, a severity indicator, a location, and a computing group; generating a first configuration; executing, based on the first computing record, the first configuration, thereby generating a computing report; modifying, based on the computing report, the first computing record; receiving a second source file associated with the event; generating a second computing record based on the second source file; comparing the first computing record and the second computing record; executing the first configuration or a second configuration, thereby generating an updated computing report; and modifying, based on the updated computing record and the comparing, the first computing record.

Abstract: A system having a system backend having a backend processor configured to define a patient clinical team associated with a patient clinical process comprising of a series of patient clinical tasks effected within the healthcare facility, each patient clinical task with an associated patient clinical task location within the healthcare facility, a group of mobile devices communicably connected via a network to the system backend, each mobile device being associated with and configured for use by at least one care member of the patient clinical team, a low energy (LE) beacon array arranged in a predetermined relationship with and differentiating between different patient clinical task locations, and communicably connected to each of the mobile devices that is configured to resolve its proximity, from the beacon array, relative to the at least one patient clinical task location.

Abstract: The systems and methods of the invention provide several improvements directed at fertility treatment. These improvements include an expert/AI system configured to guide a caregiver, e.g., a physician, through the process of providing fertility treatment. They also include a communication system between the caregiver and a patient, which is moderated by the expert/AI system.

Abstract: A fleet management system includes apheresis devices and a fleet management device remotely located from and in communication with the apheresis devices. Each apheresis device has a controller, firmware and firmware settings. The fleet management device includes an interface to allow a user to interact with the fleet management device, a server and a processor. The server receives information regarding the firmware/firmware settings of each of the apheresis devices and a firmware file from the user and/or a remote repository. The processor processes the information to determine which of the apheresis devices requires an update to the firmware/firmware settings. The server then distributes the firmware file to each apheresis device that requires the update. The system may also develop a fleet model for one or more donation centers that includes a recommend quantity of devices for the location(s) and/or whether devices should be moved from one location to another.

Abstract: A system and method for using a graph-based data structure to capture complex relations between different healthcare entities, analyze and mine healthcare data. The system sets up a framework for analyzing and mining historical healthcare data to help clinical patients and practitioners to guide care and make early decisions for interventions. More particularly, the system and method use graph embedding and machine learning modeling to process healthcare data in order to match member/patients with healthcare facilities or providers for performing a particular medical procedure or other health intervention needed by the patient.

Abstract: In some instances, a method is provided. The method comprises obtaining one or more care gap machine learning-artificial intelligence (ML-AI) models; obtaining individual information of an individual, wherein the individual information indicates one or more medical conditions of the individual and personal information of the individual; determining care gap information of the individual based on using the one or more care gap ML-AI models and the individual information, wherein the care gap information indicates one or more predictions for expectancy of a care gap of the individual, and wherein the care gap is associated with a gap in time that the individual has a lapse in receiving medical care for the one or more medical conditions; and performing one or more care gap interventions based on the care gap information.

Abstract: A method and system for automated differential medical diagnosis. Final diagnosis information including a final diagnosis for one or more patient complaints for a specific patient at a medical facility and differential diagnosis information including one or more likely differential diagnoses and one or more critical differential diagnoses associated with the final diagnosis for the specific patient at the medical facility, a visit summary, a medical record and a treatment plan or the specific patient at the medical facility are determined. Plural different types of complexities and plural types of risks associated with determining the final diagnosis, the one or more differential diagnoses, the one or more critical diagnosis associated with the final diagnosis, the visit summary, the medical record and the treatment plan for the one or more patient complaints for the specific patient at the medical facility are reduced.

Abstract: A computer implemented method for determining a dosage of semaglutide for administering to a patient for the treatment of obesity includes receiving patient data relating to a patient, wherein the patient data includes patient weight data; processing the patient data with a dosage calculator to determine the dosage of semaglutide for administering to the patient; and administering the dosage.

Abstract: Systems and methods for tracking biological samples are presented. Intrinsic and extrinsic biological sample data and/or intrinsic and extrinsic patient data may be used to label a biological sample obtained at a point-of-care facility, which may be sent to a processing facility, wherein the labeled biological sample undergoes analysis and/or processing into a labeled therapeutic. The labeled therapeutic is delivered back to the point-of-care facility, wherein the labeled therapeutic is tested for the presence of the additives prior to administration to a patient. Multi-factor validation is performed, including validating the identity of the patient to a container, validating the identity of the labeled biological sample/therapeutic to the container, and thus, validating the identity of the labeled therapeutic to the patient. The entire life cycle of a biological sample used to generate a personalized therapeutic is validated, and ensures that mix-ups or errors in administration are reduced or eliminated.

Abstract: Provided are computer implemented method and systems for providing and monitoring patient compliance with a patient healthcare treatment plan. The method includes receiving, from a healthcare provider over a network, application features for generating a patient application including patient instructions for using a medical therapy, and generating an application for a patient. The application includes at least an input for the user to input data for use in evaluating patient compliance with a treatment plan. In addition, the method includes receiving, from the healthcare provider over the network, a prescription for the application for the patient, and activating the application after the patient receives training on use of the application. The method also may include receiving patient compliance data from the application over the network based on the input.

Abstract: A method includes receiving patient medical record information from each of a plurality of providers, the plurality of providers being associated with a plurality of different organizational managing entities, respectively; querying the patient medical record information of each of the plurality of providers using selection criteria to identify a first subset patients having first characteristics that match first screening requirements for a clinical trial; identifying, using an artificial intelligence engine, ones of the first subset of patients whose medical record information includes second characteristics that match second screening requirements for the clinical trial as clinical trial patient candidates; and communicating identities of the clinical trial patient candidates to ones of the plurality of providers that provide healthcare services to the clinical trial patient candidates, respectively.

Abstract: Techniques for improved machine learning are provided. Patient data for a patient is received, the patient data relating to an action performed by a caregiver. A medical code is generated for the action by processing the patient data using a machine learning model, and the action is associated with the medical code. An event record, including the medical code, is generated for the patient.

Abstract: A method includes obtaining patient medical record information from a plurality of providers until a demographic profile of patients associated with the patient medical record information meets a desired demographic profile; querying the patient medical record information using selection criteria to identify a first subset of patients having first characteristics that match first screening requirements for a clinical trial; identifying, using an artificial intelligence engine, ones of the first subset of patients whose medical record information includes second characteristics that match second screening requirements for the clinical trial as clinical trial patient candidates; and communicating identities of the clinical trial patient candidates to ones of the plurality of providers that provide healthcare services to the clinical trial patient candidates, respectively. The plurality of providers are associated with a plurality of different organizational managing entities, respectively.

Abstract: A computing machine accesses a pharmacy transaction data set and a medical procedure transaction data set. The computing machine filters, from the pharmacy data set and the medical procedure transaction data set, transactions relevant to a biological condition. The computing machine identifies one or more lines of therapy from the filtered pharmacy data set and the filtered medical procedure transaction data set.

Abstract: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: obtaining medical health user data from respective ones of a plurality of UE devices by a virtual network function (VNF) layer which VNF layer has assigned logical channels to respective ones of the UE devices for wireless transmission of the user data, wherein the VNF layer maintains user to logical channel association data associating user identifying data to logical channels assigned to users identified by the user identifying data; examining, by a service orchestration layer that runs on top of the VNF layer, medical health data of the user medical health data, wherein the service orchestration layer is configured so that the service orchestration layer is restricted from accessing the user identifying data of the user to logical channel association data; and performing processing in dependence on the examining.

Abstract: Disclosed are systems and methods for predicting patient response to a treatment option. In one embodiment, the image slides from patient tissue samples are divided into patches and morphological patterns correlated with a disease outcome are labeled and given a patch-level score, based on whether the morphological patterns occur only in patients with good outcomes or patients with poor outcomes. A patient-level score can be generated based, at least partly, on the patch-level scores. Patch-level scores can identify regions of interest for targeted biomarker identification.

Abstract: Systems, methods and computer-readable media are provided for determining conformity to performance of meaningful use measures in human health care delivery. A Bayesian Markov Chain Monte Carlo statistical process is utilized to achieve reliable estimates for such measures despite the small subgroup sample sizes accruing during each measurement period. One embodiment utilizes zero- and one-inflated beta regression that is robust against moderate prevalence of zero or one counts in the numerators for such measurements and determinations of statistical associations with such factors as clinician, care venue, and patient attributes. Based on the determined conformity, a notification is provided to provider clinicians or organization management indicating the conformity and, in some instances, a degree of conformity.