Abstract: Techniques for sectionalizing clinical documents are provided. In one set of embodiments, a computer system can, for each page of a clinical document: identify one or more section header candidates in the page and, for each section header candidate, attempt to classify the section header candidate as corresponding to one of a plurality of section types using a first classifier or a second classifier. The computer system can further partition the page into one or more sections based on corresponding section header candidates that have been successfully classified using either the first classifier or the second classifier, where the partitioning includes associating each section with a section type in the plurality of section types in accordance with the classification of the section's corresponding section header candidate. The computer system can then validate, for each section, the section's section type via an analysis of the body of the section.

Abstract: A computerized dispensary management system and method enhances dispensary product management and are supported by a blister pack separation apparatus. The system and method operate according to a computer-implementable application and at least one computer. A scanner system further cooperates with the application and computer for scan-inputting product- and person-identifying machine-readable code information to the application for processing. The person-identifying code is scannable to identify a person and a product regimen for the person. The application provides a series of sequential screenshots based upon basic filler and dispenser screenshots for filler and dispenser side product management, guiding the user through a regimen-filling and administration. The processes are characterized by screenshot re-arrangements occurring thereto as each successive code is scanned.

Abstract: The present disclosure relates to processing data streams from a surgical procedure using multiple interconnected data structures to generate and/or continuously update an electronic output. Each surgical data structure is used to determine a current node associated with a characteristic of a surgical procedure and present relevant metadata associated with the surgical procedure. Each surgical data structure includes at least one node interconnected to one or more nodes of another data structure. The interconnected nodes between one or more data structures includes relational metadata associated with the surgical procedure.

Abstract: The present invention provides a method for analyzing answers to questions in an electronic document. The method comprises reading, into a memory, the user's answers to the questions and a user's answer history information from the user's answers, wherein the user's answer history information is collected at the time the questions are answered. The method further comprises inputting, into a machine learning model, the user's answers to the questions and the user's answer history information from the user's answers to output an analysis result, wherein the machine learning model is trained, in advance, using one or more sets of training data, each set of training data comprising one or more answers to one or more questions and answer history information from the one or more answers, and a correct result which is obtained by manually judging the one or more answers to the one or more questions.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing brain data using autoencoder neural networks. One of the methods includes obtaining brain data captured by one or more sensors characterizing brain activity of a patient; processing the brain data to generate modified brain data that characterizes a predicted local effect of a future treatment on the brain of the patient; processing the modified brain data using an autoencoder neural network to generate reconstructed brain data; and determining, using the reconstructed brain data, a predicted global effect of the future treatment on the brain of the patient.

Abstract: A network-based, collaborative, medical expert system and method for its use, the system is adapted to receive patient billing data from a plurality of care providers worldwide, the patient billing data including billing codes and de-identified patient data, the system further comprising an analysis component adapted to transform the billing codes and the patient data into multidimensional vectors and super-vectors, analyze the super-vectors via vector analysis to correlate diagnoses, treatment regimens, and treatment results with ailments of human anatomy, physiology, and psychology, and return a collaborative patient treatment guide to a user interface of at least a subset of the plurality of care providers, based on a continuous real time receipt of patient billing data, transformation of the billing data, and analysis of the super-vectors.

Abstract: A blockchain configured system includes a router and a blockchain configured record bank. The router collects data and converts it in a format in accordance with a defined standard. The blockchain configured record bank can include or be coupled to a data repository. The blockchain configured record bank can be configured to be coupled to the data provider through the router over a communication network. The blockchain configured record bank stores the data received from the data provider and can be accessible or searchable from within or outside the blockchain configured record bank. The blockchain configured record bank can be coupled to or include a data logging unit that maintains metadata associated with the data and configured to facilitate natural language processing capabilities. The router and the blockchain configured record bank may be coupled to machine learning system, metadata validation system, and master data validation system.

Abstract: A system for providing a reminder to a user is provided that stores reminder information relating to a task that the user wishes to be reminded about, along with activity information comprising information on activities that are considered to have an effect on the efficacy of the reminder associated with the task. The system monitors the user to determine if the activities in the activity information are being performed to produce a monitoring result, and then determines when to remind the user about the task based on the monitoring result by comparing the monitoring result to a threshold. A reminder alert is then output to the user when the monitoring result meets or exceeds the threshold.

Abstract: Systems and methods are provided for wearable patient identifiers. One embodiment is a labeling system that includes an interface, a memory storing rules that indicate on a patient-by-patient basis whether to print clinical notifications onto wearable patient identifiers, based on fields of electronic health records acquired via Health Level 7 (HL7) messaging, and a controller. The controller presents a Graphical User Interface (GUI) that includes interactive elements that enable alteration of the rules. The interactive elements include, for each rule: a first dialogue that indicates a field storing data to acquire from an electronic health record; a second dialogue that indicates a value to compare to the data; and an operator that logically combines the data and the value to arrive at a Boolean result. The controller determines whether to include a clinical notification in print data for a wearable patient identifier, based on the Boolean result.

Abstract: A system for prioritizing comprehensive diagnoses includes a classification module. The classification module is configured to receive a user identifier entered by a comprehensive advisor located on a graphical user interface operating on a processor, retrieve a user biological marker from a biological marker database, receive classification training data, generate a naïve Bayes classification algorithm utilizing the classification training data to output a biological marker classification label. The system includes a priority treatment module. The priority treatment module is configured to receive a plurality of user comprehensive diagnoses, select a treatment training set, generate using a supervised machine-learning model a treatment model, evaluate one or more prioritized treatment facets, generate a treatment instruction set, and display the treatment instruction set on a graphical user interface.

Abstract: A system and method for tracking emergency room patients, resources and queues and for providing a unified graphical interface structure for facilitating process flow improvements and resource management. The system has a graphical user interface adapted to display in a first screen, the graphical interface having a triage region, bed status region, and patient arrival and acuity surge regions. The specific structure and layout of the graphical user interface aids the hospital staff in quickly and efficiently providing a graphical and unified view of hospital process bottlenecks and resource availability and opportunities. The system analyzes resources and predicts needed actions and alerts appropriate staff and notifies of prescribed actions.