Abstract: Data from a plurality of parties involved in a discharge of the patient is securely processed in a cloud-computing environment. The cloud-computing environment identifies service providers suitable for the patient using a plurality of matching criteria and information derived at least in part from discharge information provided by the facility from which the patient is being discharged, and can contact the service providers to determine whether the service providers are willing to start caring for the patient. The decision to discharge the patient to a care of a particular suitable care provider and the decision by the care provider to accept such patient to the provider's care can be also be automated. The cloud-computing environment can further update the discharge information based on a request from the service providers. The cloud-computing environment securely stores the data received from all parties.

Abstract: Techniques are described herein for incorporating fall prevention into a personalized activity plan. In various embodiments, a baseline risk of fall for a user may be estimated (302) based on baseline sensor signal(s) (203, 205, 207). Based on a prediction model (215) (which may/may not be associated with the user) and the baseline risk of fall, respective risks of falls associated with various candidate activities may be predicted (304), and then candidate activities may be determined or selected (306) based on the predicted respective risks of falls. Output indicative of the determined candidate activities may be provided (308) to the user, who may provide input (310) identifying one or more of the determined candidate activities as an exercise conducted or to be conducted by the user. Based on the exercise sensor signal(s), a subsequent risk of fall for the user may be estimated (312) and used to update (314) the prediction model.

Abstract: A software application platform which provides a user with the ability to receive customized information relating to an animal's health and/or optimal growth as displayed on a graphical user interface. Specifically, a user may input data (and the system may receive said input data), for example, an animal specific biomarker, and subsequently receive identification relating to a specific subgroup of individual animal(s) who are at risk for growth abnormalities, and further receive information, data, and customized recommendations and/or intervention steps for the specific at risk animal relating to the animal's health, growth abnormality, or similar feature based on an analysis and determination of the biomarker as compared to a reference database.

Abstract: A pre-operative surgical planning system utilizes machine learning classification to provide candidate elements of a pre-operative surgical plan. The pre-operative surgical planning system may comprise a machine learning reconstruction engine that is trained with artificial computer models of physiologically compromised anatomical structures.

Abstract: A personal health system, method and device that maintains a health knowledge base, inputs user characteristics, generates health scores based on the user characteristics and provides recommendations based on the user characteristics, health scores and knowledge base, wherein the recommendations are indicated by the knowledge base to be likely to improve the user's health.

Abstract: Provided are computer implemented methods and systems for providing an interactive discussion platform for a scientific research article. According to an example method for providing an interactive discussion platform for a scientific research article, the scientific research article can be received and presented. At least one public medium associated with the scientific research article can be created. An entry related to the scientific research article can be received via the public medium. The entry can include an audio, a video, and a text. Data from the scientific research article and at least one entry can be extracted and analyzed.

Abstract: One or more processors may be configured to detect whether a patient with diabetes is operating a vehicle based on one or more detected gestures. Based on the detection of operating the vehicle, the one or more processors may cause a patient device to output alerts according to a driving alert protocol. In another example, based on the detection of operating the vehicle, one or more processors may cause an insulin pump to operate according to a driving therapy protocol.

Abstract: Hierarchical data objects are generated via a computer-based system for applying a series of rules to establish episode-specific data objects reflecting a plurality of discrete claim records before further dissecting the generated episode-specific data objects prior to finalization of those episode-specific data objects to identify claim records within the episode-specific data objects that are eligible for generation of one or more sub-episodes within the episode-specific data objects. The identified sub-episodes are reflected within the episode-specific data object to designate complete episodes of care that additionally reflect interactions with the corresponding parent episode.

Abstract: Example methods, apparatus, and articles of manufacture to process insurance claims using artificial intelligence are disclosed herein. An example computer-implemented method, executed by a processor, to process an insurance claim using artificial intelligence includes interacting, with the processor, electronically with at least one of an insured person, a representative of the insured person, or a representative of an insured entity to obtain information related to an insurance claim, processing, with the processor, the information with a machine learning engine to identify an action to be taken for the insurance, and performing, with the processor, the action using a backend processing module that is also used by a person to process an insurance claim.

Abstract: Systems and methods are described, and an example system includes an AI enhanced multi-source health data integration logic that receives a first source electronic health record (EHR) data from a first EHR system and a second source EHR data from a second EHR system, and transforms, according to a knowledge representation schema, health-related information content of the first source EHR data and the second source EHR data to a first source transformed health data and second source transformed health data. The system includes a collaboration platform, configured to host a multi-source transformed health data database, including the transformed first source health data and the transformed second source health data, and hosts AI-enhanced, multiple level telecollaborative analyses by a plurality of participants of the multi-source transformed health data database, generating health management data.

Abstract: A system and method for analyzing a data store of de-identified patient data to generate one or more dynamic user interfaces usable to predict an expected response of a particular patient population or cohort when provided with a certain treatment. The automated analysis of patterns occurring in patient clinical, molecular, phenotypic, and response data, as facilitated by the various user interfaces, provides an efficient, intuitive way for clinicians to evaluate large data sets to aid in the potential discovery of insights of therapeutic significance.

Abstract: Techniques are described for providing live first aid response guidance using a machine learning based cognitive aid planner. In one embodiment, a computer-implemented method is provided that comprises classifying, by a system operatively coupled to a processor, a type of an injury endured by a patient. The method further comprises, employing, by the system, one or more machine learning models to estimate a risk level associated with the injury based on the type of the injury and a current context of the patient.

Abstract: The MIHIC system in various embodiments described herein helps clinicians predict the risk of maternal mortality by detecting diseases early and identifying possible risks in mothers, fetuses and infants across pre, peri and post-natal stages of pregnancy. The system quantifies risk as a single MIHIC score, which through quantification assigns possible risks to the mother, fetus and infant. The MIHIC score uses a specialized algorithm to derive the individual and overall risk as a value between 0 and 1 and uses the risk scores to stratify the patients into High, Medium and Low risk for preventive intervention and improved pregnancy outcome.

Abstract: A system and method for analyzing a data store of de-identified patient data to generate one or more dynamic user interfaces usable to predict an expected response of a particular patient population or cohort when provided with a certain treatment. The automated analysis of patterns occurring in patient clinical, molecular, phenotypic, and response data, as facilitated by the various user interfaces, provides an efficient, intuitive way for clinicians to evaluate large data sets to aid in the potential discovery of insights of therapeutic significance.

Abstract: A system for a physiologically informed virtual support network includes a computing device a support module operating on the computing device, the support module configured to receive a biological extraction related to a user, wherein the biological extraction comprises an element of user physiological data, generate a request for the user to join a support network as a function of the biological extraction, identify a support network for the user from a plurality of support networks, as a function of the biological extraction; and display to the user on the computing device, the identified support network, and a machine-learning module operating on the computing device, the machine-learning module configured to assess a membership of the plurality of support networks, organize member participants of the plurality of support networks utilizing a first machine-learning process and assign member participants to the plurality of support networks as a function of the first machine-learning process.

Abstract: Systems, catheters, and methods for accessing and treating along the central nervous system are disclosed. An example method may manage inflammation of the patient to treat a condition of the patient by processing values related to one or more physiological parameters of a patent, identifying when an inflammation condition of the patient has reached a treatment condition based on the processed values, and automatically providing an indication that the inflammation condition has reached the treatment condition. An example indication may include actuation of a treatment protocol. The example method may be performed with an inflammation management system.

Abstract: A prehospital telemedicine system comprises a physiologic monitor; an electronic patient care reporting system (ePCR) system; and a point-of-care blood analyzer communicatively coupled to the physiologic monitor and the ePCR system. The point-of-care blood analyzer is configured to perform an analysis of a blood sample based on an indication of a need for a specific blood analysis provided by one of the physiologic monitor and the ePCR system, and to automatically transmit a result of the analysis to a remote data receiving system. The indication of a need for a specific blood analysis may be based upon any one of the following: vital signs data obtained for a patient by the physiologic monitor; and/or current documentation or past medical history captured on or available through the ePCR system.

Abstract: A system may receive a query for a patient evaluation. The system may then receive historical patient information or hospital data, current medical information, patient information, and testing information. The system may then use the received information to generate a set of rules using a neural network and uses the rules to process an evaluation for the patient.

Abstract: Computer systems and computer-implemented analysis methods may be used for assistance in planning and/or performing a medical procedure, such as percutaneous nephrolithotomy or percutaneous nephrolithotripsy. The method may include receiving one or more radiographic images of an anatomical structure of a patient, generating a display of the radiographic image(s), generating at least one request for user input to identify features of the anatomical structure, receiving user input identifying the features of the anatomical structure, identifying at least one access plan based on the received user input, and generating a display of the identified access plan(s) associated with the radiographic image(s). The method may include generating a patient template that indicates an insertion site according to the identified access plan(s).

Abstract: Systems and methods for implementing machine-learning models for ovarian stimulation is described herein. In some variations, a computer-implemented method may include optimizing an ovarian stimulation process may include receiving patient-specific data associated with a patient, and predicting an egg outcome for the patient for each of a plurality of treatment options for an ovarian stimulation process based on at least one predictive model and the patient-specific data, where the at least one predictive model is trained using prior patient-specific data associated with a plurality of prior patients.