Abstract: A method and system for predicting the likelihood that a patient will suffer from a cardiac event is provided. The method includes receiving electrocardiogram data associated with the patient, providing at least a portion of the electrocardiogram data to a trained model, receiving a risk score indicative of the likelihood the patient will suffer from the cardiac event within a predetermined period of time from when the electrocardiogram data was generated, and outputting the risk score to at least one of a memory or a display for viewing by a medical practitioner or healthcare administrator. The system includes at least one processor executing instructions to carry out the steps of the method.

Abstract: The present disclosure relates to systems and methods for accessing a data structure including a subject identifier identifying a subject and a subject connectivity value derived from at least one of a scan or test provided to the subject, the subject connectivity value representing a magnitude of a connection associated with at least one sub-processing region of a nervous system of the subject; comparing the subject connectivity value to a connectivity threshold value to determine a classification of the subject; determining that the subject connectivity value exceeds the connectivity threshold value, storing in the data structure, an association between the subject identifier and a first classification value corresponding to a first classification or determining that the subject connectivity value is less than the connectivity threshold value, and storing in the data structure, an association between the subject identifier and a second classification value corresponding to a second classification.

Abstract: Disclosed is a method of training the dementia identification model. More particularly, the method may include obtaining test result data through at least one of a first task related to Stroop test, a second task related to a computational power test, and a third task related to a memory test; and labeling the test result data with a score value to train the dementia identification model.

Abstract: Described herein are techniques of using machine learning to automatically extract clinical variable values for subjects from clinical record data. The techniques designate certain clinical variables as hybrid variables that can be assigned values by machine learning model prediction. The techniques process, using a machine learning model trained to predict a value of a hybrid variable, clinical record data associated with a subject to obtain a predicted hybrid variable value and an associated confidence score. The techniques set the value of the hybrid variable for the subject to the predicted hybrid variable value when the model prediction is of sufficiently high confidence.

Abstract: Wearable technologies, such as wearable health monitors, and methods of use are provided. In some embodiments, the wearable technology can be worn at the wrist of an individual and can use an accelerometer, pulse oximeter, and electrocardiogram to measure heart rate, oxygen saturation, blood pressure, pulse wave velocity, and activity. This information can then be provided to the individual. The individual can alter their behaviors and relationships with their own health by using features such as notifications and auto-tagging to better understand their own stress, diet, sleep, and exercise levels over various time periods and subsequently make appropriate behavioral changes.

Abstract: A method includes: obtaining, by a computer, subject response data including audio data, video data, or audio-video data of a subject's response to one or more stimuli presented to the subject over a defined time period; extracting at least one subject descriptor from the subject response data as a function of time, the at least one subject descriptor including data characterizing involuntary or voluntary action of the subject in response to the one or more stimuli; deriving, from the at least one subject descriptor, a first biomarker characterizing a behavior of the subject in response to the one or more stimuli, in which a value of the first biomarker is indicative of a severity of a disease in the subject; and outputting a disease severity level for the disease as a function of the value of the first biomarker.

Abstract: An infection risk prediction system may receive a query associated with an infection risk assessment for a geographic location for an infectious disease and obtain associated infectious disease data. The system detects a plurality of objects at the geographical location and a plurality of material categories for the plurality of objects associated. The system determines a usage frequency indicator and spatial-temporal features for each object and creates a risk prediction model based on the lifespan of the virus on the plurality of material categories for each of the plurality of objects based on the viral disease data and the spatial-temporal features for each object. A risk assessment score for each object is determined and an associated heat map is provided to alert a user of potential virus exposures or to provide a routing application to generate a route that minimizes potential pathogen exposure.

Abstract: In one aspect, the present disclosure is directed to a method for improving the speed of determining a health risk profile associated with a patient. The method may include the step of retrieving patient medical information about the patient, wherein the patient medical information is an uncoded natural language expression in a first language. The method may also include comparing the patient medical information with records in a first database. If the patient medical information matches the preselected medical information, the method includes performing a first data conversion procedure. If the patient medical information fails to match any record in the first database, the method includes performing a second data conversion procedure, wherein the first data conversion procedure is performed faster than the second data conversion procedure.

Abstract: A healthcare delivery system, a wearable computing device and a method are disclosed. The method includes capturing, by the wearable computing device worn by a medical practitioner, medical multimedia data of a patient during a medical procedure. The method further includes displaying one or more selectable options associated with the medical multimedia data on a display screen of the wearable computing device to the medical practitioner. Further, the method includes receiving a selection of a selectable option from among the one or more selectable options. Thereafter, at least one action is performed on the medical multimedia data based on the selection of the selectable option. An example of the at least one action includes sharing at least a part of the medical multimedia data with a third party device.

Abstract: A system and method for generating a total health index and recommending an actionable intervention for managing a health risk of a patient is disclosed. The method includes receiving user-generated data, clinical data, and pharmacy data in association with a patient, determining a social health index score based on the user-generated data, determining a clinical risk index score based on the clinical data, determining a medication adherence index score based on the pharmacy data, determining, using a machine learning model on one or more of the social health index score, the clinical risk index score, and the medication adherence index score, a total health index score and an actionable intervention for managing a health risk in association with the patient based on the total health index score, and automatically initiating the actionable intervention.

Abstract: A computer-implemented method includes a first module of a computing system receiving application-specific data for determining utilization attributes of multiple application programs. A second module of the system receives data for determining patient archetypes. A third module of the system determines a clinical benefit of each application program based on analysis of the application-specific data. The system matches an application program with a particular patient archetype based on analysis of each patient archetype and the determined clinical benefit of the application program. The system selects a particular application program for use by a patient of a first patient group based on: i) a characteristic of the first patient group that is included in a first patient archetype; and ii) the clinical benefit of the particular application exceeding a threshold clinical benefit.

Abstract: A strategic decision support system is disclosed. The system can filter content received from a remote database coupled to a network to provide a graphical user interface to enable strategic decision making to expand utilization of a product. The system can include a local client computer to generate access to content stored in the remote database, at least one filtering scheme, a set of selectable filters configured to filter the content stored in the remote database according to the at least one filtering scheme, and a remote server coupled to the local client computer via the network to analyze access restrictions to the product based on a selected filter and the at least one filtering scheme to generate a graphical user interface displayed on the local client computer.

Abstract: Methods for analyzing omics data and using the omics data to determine prognosis of a cancer, to predict an outcome of a treatment, and/or to determine an effectiveness of a treatment are presented. In preferred methods, blood from a patient having a cancer or suspected to have a cancer is obtained and blood omics data for a plurality of cancer-related, inflammation-related, or DNA repair-related genes are obtained. A cancer score can be calculated based on the omics data, which then can be used to provide a cancer prognosis, a therapeutic recommendation, an effectiveness of a treatment.

Abstract: A machine learning (ML) architecture may be trained to determine an estimated epigenetic status at a target DNA locus based at least in part on epigenetic data associated with one or more other DNA loci. The ML architecture may additionally or alternatively be used to detect a failed epigenetic assay and/or determine a likelihood that a subject has falsified information provided about the subject.

Abstract: Methods for determining treatments for cancer patients are disclosed.

Abstract: A computing system for redirecting electronic prescription refills is disclosed herein. A server computer device executing an electronic health records application constructs an electronic prescription for a patient and causes the electronic prescription to be routed to a first pharmacy device of a first pharmacy. The electronic prescription includes at least one refill. Subsequently, the server computing device receives an identifier for the electronic prescription and an identifier for a second pharmacy from a second server computing device executing a patient portal application, wherein the identifier for the second pharmacy is specified by the patient. The server computing device identifies the electronic prescription, determines a number of refills remaining on the electronic prescription, and constructs a second electronic prescription including the number of refills.

Abstract: A method for providing a healthcare system. The method comprises a machine learning system: obtaining and labelling patient data to produce labelled patient data relating to one or more patients; determining one or more predictions based on the labelled patient data; receiving, from a user, one or more user inputs labelling each of the one or more predictions as a success or a failure; generating training data based on the labelled patient data and the one or more user inputs; and training the machine learning system based on the training data.

Abstract: In one aspect, the present disclosure is directed to a method for improving the speed of determining a health risk profile associated with a patient. The method may include the step of retrieving patient medical information about the patient, wherein the patient medical information is an uncoded natural language expression in a first language. The method may also include comparing the patient medical information with records in a first database. If the patient medical information matches the preselected medical information, the method includes performing a first data conversion procedure. If the patient medical information fails to match any record in the first database, the method includes performing a second data conversion procedure, wherein the first data conversion procedure is performed faster than the second data conversion procedure.

Abstract: A method and system for identifying cohorts of psychiatric disorder patients using electroencephalograph (EEG) are disclosed, which include analyzing a type of brain region mutual interaction characteristics using scalp EEG data from each of a group of patients and obtaining a set of brain region mutual interaction feature matrices, performing a feature enhancement process to the brain region mutual interaction feature matrices to extract prominent mutual interaction features, and applying a machine learning algorithm to identify cohorts of the group of psychiatric disorder patients. The method and system can also be used for patients diagnosed with COVID-19 and suffering from psychiatric disorder symptoms originated from COVID-19. The method and system can be used to identify responsive and non-responsive groups to a clinical treatment, different treatment outcome groups in response to a clinical treatment, or different risk groups to a clinical treatment.

Abstract: A system and method for facilitating employee health screening using an application on a mobile computing device are provided. The system and method can provide a centralized platform for providing a health screening questionnaire for employees to fill out before visiting an employer's facility. The system and method can perform an employee badge activation/deactivation function based on one or more indicators relating to employee health information.