Abstract: Generally, described herein are computer-implemented systems and methods for self-guided education in various aspects of health care. The described systems and methods effect behavior change through a functional relationship between the content of educational case packages comprising a plurality of displays, each of which has one or more completion conditions which must be completed by the user in accordance with a health care procedure to be practiced. The performance of the case by the user habituates behavior change through practice of a health care procedure.

Abstract: A personalized parameter learning method, a sleep-aid device and a non-transitory computer readable medium are provided. The personalized parameter learning method for a sleep-aid device is provided. The personalized parameter learning method includes the following steps. A process device computes a measured sleep quality of a user after operating a sleep-aid device with an inputted parameter setting at least according to a subjective feedback from the user. The processing device generates a plurality of candidate parameter settings according to the measured sleep quality. The processing device generates a plurality of predicting sleep qualities corresponding the candidate parameter settings. The processing device obtains a recommending parameter setting by selecting one of the candidate parameter settings according to the predicting sleep qualities.

Abstract: Evaluating future healthcare event risks of a patient includes receiving, at one or more computers, patient healthcare data for the patient, wherein the patient healthcare data represents a healthcare event and includes one or more healthcare codes, accessing, with the one or more computers, a database that associates the healthcare event and the healthcare codes with risks of potentially preventable healthcare events, and presenting, with the one or more computers, indications of the risks of potentially preventable healthcare events to a user to facilitate mitigation of the risks of potentially preventable healthcare events for the patient.

Abstract: A user interface for clinical personnel provides selectable views of a plurality of medical risk scores. Questions whose answers are needed for calculation of those risk scores are asked in a question and answer area of the user interface, which allows some questions to be answered based on real time patient physiological data streams that are overridable by user provided answers. Where multiple risk score calculations require answers to the same question, the user provided answer may be supplied as an answer to the corresponding question for each risk score, rather than requiring the user to answer multiple times. Sparklines may be provided with the displayed risk scores to show trends in the risk score values, and may be updated in real time based on real time physiological data streams. The display of risk scores may visually distinguish between risk scores that have been validated and those are based on unvalidated answers to the questions.

Abstract: Systems and methods for determining monitoring compliance are provided. Each element in a plurality of data elements is obtained from a medical device connected to a corresponding subject in a first plurality of subjects and interrogated to determine a condition of the device or subject. A medical code and timestamp for evaluation of the device or subject is recorded in the subject's medical record. A determination is made for each epoch in a plurality of epochs, for each subject in a second plurality of subjects, whether the medical code is recorded in the subject's medical record for the epoch by evaluating the time stamps and codes in the medical records. A compliance counter is advanced when a medical record includes the code for a respective epoch and otherwise a noncompliance counter is advanced. Responsive to a compliance request, compliance information or suggested treatment options are provided based on the counters.

Abstract: Methods, systems, and computer-readable media are provided for identifying, stratifying, and prioritizing patients who are eligible for care management services. For each patient, patient health data is used to determine one or more of a disease burden associated with the patient, an amount of health system utilization by the patient, and an amount of money spent on healthcare services for the patient. It is further determined if the patient exceeds a respective threshold value associated with each of these criteria. If the patient exceeds the respective threshold value, the patient is stratified into a category comprising one of high-risk senior, high-risk adult, high-risk pediatrics, or high-risk maternity. The patient may also be prioritized based on one or more factors, and a notification may be sent to the patient informing the patient of his/her eligibility for care management services.

Abstract: A data processing system for machine-learning driven data analysis implements obtaining digital healthcare service provider information associated with one or more digital healthcare service providers and query parameters information from a user searching for digital healthcare service providers that may provide digital healthcare services to employees of the user. The system analyzes query parameter information using a first machine learning model to obtain category information. The system analyzes the category information and the digital health service provider information to predict digital healthcare service providers that provide services that the user may be interested in provided to the employees. These predictions are provided to the user as digital healthcare service recommendations.

Abstract: Methods and apparatus for the application of reinforcement learning to animal medical diagnostics. In one embodiment, a system is disclosed that utilizes two (2) RL agents that are arranged sequentially and that are optimized independently from one another. The first RL agent is an assessment RL agent which takes as input from one or more of: outputs from classification artificial intelligence (AI) engines; outputs from subjective biological data storage devices, and outputs from objective biological data storage devices. Using these input(s), the assessment RL agent outputs a set of assessments which evaluate a set of conditions associated with an animal. This set of assessments is then provided as input to a second RL agent known-as a plan RL agent which determines a set of treatment recommendations and diagnostics based off this determined set of assessments. Methods and computer-readable media are also disclosed.

Abstract: A comprehensive health care data management system is provided. In an embodiment, a Medical Data Governance System records, secures, and provides appropriate access to all patient data. By concentrating all available relevant medical data into a single source, and providing a subset of data to each receiving subsystem with the correct source and time reference, the Medical Data Governance System becomes the True Source of Data and guarantees the data consistency through the use of block chain signatures. In another aspect of the invention, a system of servers is provided, which communicate data in real time with white boards stationed in the operating rooms of a healthcare facility. Medical personnel and healthcare facility staff members can view the formatted data on a white board and input new or revised data directly on the white board or at an input station near the white board.

Abstract: Systems and methods of a cipher-based system for tracking a patient within a clinical pharmacy workflow, the system includes providing a meshed network having patient devices that communicate patient data with aggregators. The patient devices and aggregators located within the space form a meshed network, the aggregators communicate data to a computer in communication with a cloud-based network. A patient device with a mobile application wirelessly communicates with an internet system in communication with the cloud-based network. Receiving by the computer, information about the user patient device entering the meshed network by wireless tags positioned within the space.

Abstract: A computerized method includes determining a clinical opportunity to improve care for a user according to automated triggering of a gap identification rule, generating a persona of the user based on one or more personalization scores that are specific to the user, and generating a care plan for reducing the gap in care based on the persona. The care plan includes a plurality of methods of increasing compliance of the user with the care plan, selected based on the one or more personalization scores, and include different modes of communicating with the user either directly or through at least one of a physician and a pharmacist depending on the one or more personalization scores. The method includes deploying the care plan to provide automated selection of one or more of the different modes of communicating with the user to increase compliance of the user with the care plan.

Abstract: Methods, systems, and computer-readable media are provided for building a score plan for a healthcare organization, its providers, its payers, and/or its patients and presenting the results of the score plan on one or more score card user interfaces. Score cards graphically display an entity's progress towards meeting quality measure objectives. The score cards provide information on percentage completion of one or more quality measure objectives by the entity and/or quality measure objectives that may be difficult for the entity to achieve.

Abstract: Methods, systems, and computer-readable media are provided for computer based healthcare information to automatically provide reminders to a patient to take prescription medications at the appropriate times on the patient's mobile device. The patient enters a medical record number (MRN) into the mobile device and this information is communicated to the patient's electronic medical record. The user device receives the prescription information for the MRN from the patient's electronic medical record. Utilizing the prescription information on the user's device, the user can view and set reminders to take the medication directly from the patient's mobile device.

Abstract: A method for providing treatment recommendations for a patient to a physician is disclosed. The method includes receiving health information associated with the patient, determining a first risk score for the patient based on the health information using a trained predictor model, determining a second risk score for the patient based on the health information and at least one artificially closed care gap included in the health information using the predictor model, determining a predicted risk reduction score based on the first risk score and the second risk score, determining a patient classification based on the predicted risk reduction score, and outputting a report based on at least one of the first risk score, the second risk score, or the predicted risk reduction score.

Abstract: Machine learning-based systems and methods for predicting running-related injuries and related training methods are described herein. An example method for training a machine learning model includes receiving a dataset including running-related data, where the running-related data includes a plurality of samples tagged with respective running-related injury labels. The method also includes augmenting the dataset, where the augmented dataset further includes a plurality of synthetic samples tagged with respective running-related injury labels. The method further includes training a machine learning model using the augmented dataset. The trained machine learning model is configured for predicting risk of running-related injury.

Abstract: An improved alternative therapy identification system increases the efficiency for obtaining information for alternative therapies. The alternative therapy identification system automates alternative therapy identification information from both a product level and a drug cost level. The improved alternative therapy identification system may also increase the efficiency by improving alternative therapy selection to occur at the prescriber level.

Abstract: A method for generating a diagnosis model capable of diagnosing multi-cancer is provided. The method includes steps of: (a) in response to acquiring training data including (i) stratification-related values, (ii) biomarker group-related value information and (iii) its corresponding Ground Truth cancer information, setting initial prediction values of a base classification model capable of classifying cancers for each of the stratification-related values; and (b) generating a first decision tree to a T-th decision tree by using its corresponding previous classification model, wherein the previous classification model has been updated by its corresponding previous iteration via a first iteration to a T-th iteration, and wherein the previous classification model represents the base classification model at the first iteration, to thereby generate the diagnosis model.

Abstract: This disclosure relates to determining a personalized dose of a pharmaceutical for an individual. First data representative of one or more characteristics of the individual prior to administration of the pharmaceutical is received, and second data representative of a measurement of a physiological parameter of the individual after administration of the pharmaceutical is received. A computational model having pharmacokinetic and pharmacodynamic components is used to generate a first target concentration and one or more first doses determined to likely achieve the first target concentration for the pharmaceutical. The computational model is updated to reflect the measurement of the physiological parameter.

Abstract: A device, system, and method determines a reading environment by synthesizing downstream needs. The method at a workflow server includes receiving a request from a physician device utilized by a referring physician, the request directed to performing an imaging procedure. The method includes determining at least one normalized need from the request, the normalized need corresponding to the referring physician. The method includes generating information to be included in a reading environment based on the at least one normalized need, the information assisting an image interpreter in interpreting the imaging procedure.

Abstract: A system for redistributing medication including a computing device configured to receive a communication regarding a medication donation from a donor, wherein the communication includes donor medication information regarding the medication donation. The computing device further configured to verify the medication donation including verifying the identity of the donated medication. Verifying the identity of the donated medication includes collecting actual medication information. The computing device also configured to enter final medication information corresponding to the medication donation into the medication database. The computing device configured to match the donated medication to a recipient selected from a recipient database as a function of a set of associated recipient data.